{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modeling/papers/4","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":142,"rows_per_page":100,"rows":[301,400],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modeling","prev":"/task/language-modeling/papers/3","next":"/task/language-modeling/papers/5","papers":[{"url":"/paper/optimizing-prompts-for-text-to-image-1","slug":"optimizing-prompts-for-text-to-image-1","title":"Optimizing Prompts for Text-to-Image Generation","date":"2022-12-19","arxiv_id":"2212.09611","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/optimizing-prompts-for-text-to-image-1#ran","syntology_url":"https://syntology.ai/paper/2212.09611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09611"}},"official":{"repos":["microsoft/lmops"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/unnatural-instructions-tuning-language-models","slug":"unnatural-instructions-tuning-language-models","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","date":"2022-12-19","arxiv_id":"2212.09689","repositories_listed":3,"syntology":null},{"url":"/paper/contrastive-search-is-what-you-need-for","slug":"contrastive-search-is-what-you-need-for","title":"Contrastive Search Is What You Need For Neural Text Generation","date":"2022-10-25","arxiv_id":"2210.14140","repositories_listed":3,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contrastive-search-is-what-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2210.14140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14140"}},"official":{"repos":["yxuansu/contrastive_search_is_what_you_need"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/draft-sketch-and-prove-guiding-formal-theorem","slug":"draft-sketch-and-prove-guiding-formal-theorem","title":"Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs","date":"2022-10-21","arxiv_id":"2210.12283","repositories_listed":3,"syntology":null},{"url":"/paper/multi-granularity-prediction-for-scene-text","slug":"multi-granularity-prediction-for-scene-text","title":"Multi-Granularity Prediction for Scene Text Recognition","date":"2022-09-08","arxiv_id":"2209.03592","repositories_listed":3,"syntology":null},{"url":"/paper/recurrent-memory-transformer","slug":"recurrent-memory-transformer","title":"Recurrent Memory Transformer","date":"2022-07-14","arxiv_id":"2207.06881","repositories_listed":3,"syntology":{"n":13,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/recurrent-memory-transformer#ran","syntology_url":"https://syntology.ai/paper/2207.06881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06881"}},"official":{"repos":["booydar/lm-rmt","booydar/transformer-xl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["community","official","unlocated"]}}},{"url":"/paper/e2efold-3d-end-to-end-deep-learning-method","slug":"e2efold-3d-end-to-end-deep-learning-method","title":"Accurate RNA 3D structure prediction using a language model-based deep learning approach","date":"2022-07-04","arxiv_id":"2207.01586","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/e2efold-3d-end-to-end-deep-learning-method#ran","syntology_url":"https://syntology.ai/paper/2207.01586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01586"}},"official":{"repos":["ml4bio/rhofold","ml4bio/rna-fm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-video-question-answering-via-frozen","slug":"zero-shot-video-question-answering-via-frozen","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","date":"2022-06-16","arxiv_id":"2206.08155","repositories_listed":3,"syntology":{"n":34,"n_ran":14,"n_constructed":9,"n_ran_checked":14,"n_instrument":0,"n_unverified":20,"n_honours":1,"n_violates":1,"n_no_contract":12,"n_pointer_only":1,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified","sample_list":"/paper/zero-shot-video-question-answering-via-frozen#ran","syntology_url":"https://syntology.ai/paper/2206.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08155"}},"official":{"repos":["antoyang/FrozenBiLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-generalist-agent","slug":"a-generalist-agent","title":"A Generalist Agent","date":"2022-05-12","arxiv_id":"2205.06175","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/a-generalist-agent#ran","syntology_url":"https://syntology.ai/paper/2205.06175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.06175"}},"official":null}},{"url":"/paper/enhancing-chinese-pre-trained-language-model","slug":"enhancing-chinese-pre-trained-language-model","title":"Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics Graph","date":"2022-05-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/do-as-i-can-not-as-i-say-grounding-language","slug":"do-as-i-can-not-as-i-say-grounding-language","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","date":"2022-04-04","arxiv_id":"2204.01691","repositories_listed":3,"syntology":null},{"url":"/paper/shallow-fusion-of-weighted-finite-state","slug":"shallow-fusion-of-weighted-finite-state","title":"Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization","date":"2022-03-29","arxiv_id":"2203.15917","repositories_listed":3,"syntology":null},{"url":"/paper/block-recurrent-transformers","slug":"block-recurrent-transformers","title":"Block-Recurrent Transformers","date":"2022-03-11","arxiv_id":"2203.07852","repositories_listed":3,"syntology":{"n":23,"n_ran":18,"n_constructed":2,"n_ran_checked":9,"n_instrument":9,"n_unverified":5,"n_honours":2,"n_violates":3,"n_no_contract":4,"n_pointer_only":4,"phrase":"18 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 3 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/block-recurrent-transformers#ran","syntology_url":"https://syntology.ai/paper/2203.07852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07852"}},"official":{"repos":["google-research/meliad"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/a-systematic-evaluation-of-large-language","slug":"a-systematic-evaluation-of-large-language","title":"A Systematic Evaluation of Large Language Models of Code","date":"2022-02-26","arxiv_id":"2202.13169","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-systematic-evaluation-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2202.13169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13169"}},"official":{"repos":["eleutherai/gpt-neox","vhellendoorn/code-lms"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cosformer-rethinking-softmax-in-attention-1","slug":"cosformer-rethinking-softmax-in-attention-1","title":"cosFormer: Rethinking Softmax in Attention","date":"2022-02-17","arxiv_id":"2202.08791","repositories_listed":3,"syntology":null},{"url":"/paper/ernie-3-0-titan-exploring-larger-scale","slug":"ernie-3-0-titan-exploring-larger-scale","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","date":"2021-12-23","arxiv_id":"2112.12731","repositories_listed":3,"syntology":null},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/debertav3-improving-deberta-using-electra","slug":"debertav3-improving-deberta-using-electra","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","date":"2021-11-18","arxiv_id":"2111.09543","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/debertav3-improving-deberta-using-electra#ran","syntology_url":"https://syntology.ai/paper/2111.09543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09543"}},"official":{"repos":["microsoft/DeBERTa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-transformers-are-more-efficient","slug":"hierarchical-transformers-are-more-efficient","title":"Hierarchical Transformers Are More Efficient Language Models","date":"2021-10-26","arxiv_id":"2110.13711","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hierarchical-transformers-are-more-efficient#ran","syntology_url":"https://syntology.ai/paper/2110.13711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13711"}},"official":{"repos":["google/trax"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/8-bit-optimizers-via-block-wise-quantization","slug":"8-bit-optimizers-via-block-wise-quantization","title":"8-bit Optimizers via Block-wise Quantization","date":"2021-10-06","arxiv_id":"2110.02861","repositories_listed":3,"syntology":null},{"url":"/paper/lm-critic-language-models-for-unsupervised","slug":"lm-critic-language-models-for-unsupervised","title":"LM-Critic: Language Models for Unsupervised Grammatical Error Correction","date":"2021-09-14","arxiv_id":"2109.06822","repositories_listed":3,"syntology":null},{"url":"/paper/raise-a-child-in-large-language-model-towards","slug":"raise-a-child-in-large-language-model-towards","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","date":"2021-09-13","arxiv_id":"2109.05687","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/raise-a-child-in-large-language-model-towards#ran","syntology_url":"https://syntology.ai/paper/2109.05687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05687"}},"official":{"repos":["alibaba/AliceMind","pkunlp-icler/childtuning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/truthfulqa-measuring-how-models-mimic-human","slug":"truthfulqa-measuring-how-models-mimic-human","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","date":"2021-09-08","arxiv_id":"2109.07958","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/truthfulqa-measuring-how-models-mimic-human#ran","syntology_url":"https://syntology.ai/paper/2109.07958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07958"}},"official":{"repos":["sylinrl/truthfulqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/long-short-transformer-efficient-transformers","slug":"long-short-transformer-efficient-transformers","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","date":"2021-07-05","arxiv_id":"2107.02192","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-short-transformer-efficient-transformers#ran","syntology_url":"https://syntology.ai/paper/2107.02192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02192"}},"official":{"repos":["NVIDIA/transformer-ls"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/chinesebert-chinese-pretraining-enhanced-by","slug":"chinesebert-chinese-pretraining-enhanced-by","title":"ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information","date":"2021-06-30","arxiv_id":"2106.16038","repositories_listed":3,"syntology":null},{"url":"/paper/xlm-e-cross-lingual-language-model-pre","slug":"xlm-e-cross-lingual-language-model-pre","title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA","date":"2021-06-30","arxiv_id":"2106.16138","repositories_listed":3,"syntology":null},{"url":"/paper/efficient-large-scale-language-model-training","slug":"efficient-large-scale-language-model-training","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","date":"2021-04-09","arxiv_id":"2104.04473","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/efficient-large-scale-language-model-training#ran","syntology_url":"https://syntology.ai/paper/2104.04473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.04473"}},"official":{"repos":["NVIDIA/Megatron-LM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/fastmoe-a-fast-mixture-of-expert-training","slug":"fastmoe-a-fast-mixture-of-expert-training","title":"FastMoE: A Fast Mixture-of-Expert Training System","date":"2021-03-24","arxiv_id":"2103.13262","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fastmoe-a-fast-mixture-of-expert-training#ran","syntology_url":"https://syntology.ai/paper/2103.13262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13262"}},"official":{"repos":["davidmrau/mixture-of-experts","laekov/fastmoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/self-diagnosis-and-self-debiasing-a-proposal","slug":"self-diagnosis-and-self-debiasing-a-proposal","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","date":"2021-02-28","arxiv_id":"2103.00453","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-diagnosis-and-self-debiasing-a-proposal#ran","syntology_url":"https://syntology.ai/paper/2103.00453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00453"}},"official":{"repos":["timoschick/self-debiasing"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-audio-visual-speech-recognition","slug":"end-to-end-audio-visual-speech-recognition","title":"End-to-end Audio-visual Speech Recognition with Conformers","date":"2021-02-12","arxiv_id":"2102.06657","repositories_listed":3,"syntology":null},{"url":"/paper/semglove-semantic-co-occurrences-for-glove","slug":"semglove-semantic-co-occurrences-for-glove","title":"SemGloVe: Semantic Co-occurrences for GloVe from BERT","date":"2020-12-30","arxiv_id":"2012.15197","repositories_listed":3,"syntology":null},{"url":"/paper/learning-contextual-representations-for","slug":"learning-contextual-representations-for","title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","date":"2020-12-18","arxiv_id":"2012.10309","repositories_listed":3,"syntology":null},{"url":"/paper/extracting-training-data-from-large-language","slug":"extracting-training-data-from-large-language","title":"Extracting Training Data from Large Language Models","date":"2020-12-14","arxiv_id":"2012.07805","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/extracting-training-data-from-large-language#ran","syntology_url":"https://syntology.ai/paper/2012.07805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.07805"}},"official":{"repos":["ftramer/LM_Memorization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-word-lexical-simplification","slug":"multi-word-lexical-simplification","title":"Multi-Word Lexical Simplification","date":"2020-12-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/on-the-sentence-embeddings-from-pre-trained","slug":"on-the-sentence-embeddings-from-pre-trained","title":"On the Sentence Embeddings from Pre-trained Language Models","date":"2020-11-02","arxiv_id":"2011.05864","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-sentence-embeddings-from-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2011.05864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.05864"}},"official":{"repos":["bohanli/BERT-flow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/let-s-stop-incorrect-comparisons-in-end-to","slug":"let-s-stop-incorrect-comparisons-in-end-to","title":"Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!","date":"2020-09-22","arxiv_id":"2009.10684","repositories_listed":3,"syntology":null},{"url":"/paper/upb-at-semeval-2020-task-6-pretrained","slug":"upb-at-semeval-2020-task-6-pretrained","title":"UPB at SemEval-2020 Task 6: Pretrained Language Models for Definition Extraction","date":"2020-09-11","arxiv_id":"2009.05603","repositories_listed":3,"syntology":null},{"url":"/paper/is-supervised-syntactic-parsing-beneficial","slug":"is-supervised-syntactic-parsing-beneficial","title":"Is Supervised Syntactic Parsing Beneficial for Language Understanding? An Empirical Investigation","date":"2020-08-15","arxiv_id":"2008.06788","repositories_listed":3,"syntology":null},{"url":"/paper/bertweet-a-pre-trained-language-model-for","slug":"bertweet-a-pre-trained-language-model-for","title":"BERTweet: A pre-trained language model for English Tweets","date":"2020-05-20","arxiv_id":"2005.10200","repositories_listed":3,"syntology":null},{"url":"/paper/enabling-language-models-to-fill-in-the","slug":"enabling-language-models-to-fill-in-the","title":"Enabling Language Models to Fill in the Blanks","date":"2020-05-11","arxiv_id":"2005.05339","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enabling-language-models-to-fill-in-the#ran","syntology_url":"https://syntology.ai/paper/2005.05339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05339"}},"official":{"repos":["chrisdonahue/ilm","worksheets.codalab.org/worksheets/0x9987b5d9cce74cf4b2a5f84b54ee447b"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}},"official":{"repos":["linjieli222/HERO"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/macsen-a-voice-assistant-for-speakers-of-a","slug":"macsen-a-voice-assistant-for-speakers-of-a","title":"Macsen: A Voice Assistant for Speakers of a Lesser Resourced Language","date":"2020-05-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/probabilistically-masked-language-model","slug":"probabilistically-masked-language-model","title":"Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order","date":"2020-04-24","arxiv_id":"2004.11579","repositories_listed":3,"syntology":{"n":35,"n_ran":21,"n_constructed":1,"n_ran_checked":12,"n_instrument":9,"n_unverified":14,"n_honours":4,"n_violates":3,"n_no_contract":5,"n_pointer_only":29,"phrase":"21 ran (of which 1 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 3 violated, 5 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/probabilistically-masked-language-model#ran","syntology_url":"https://syntology.ai/paper/2004.11579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.11579"}},"official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":1,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/amr-parsing-via-graph-sequence-iterative","slug":"amr-parsing-via-graph-sequence-iterative","title":"AMR Parsing via Graph-Sequence Iterative Inference","date":"2020-04-12","arxiv_id":"2004.05572","repositories_listed":3,"syntology":{"n":31,"n_ran":21,"n_constructed":11,"n_ran_checked":16,"n_instrument":5,"n_unverified":10,"n_honours":1,"n_violates":1,"n_no_contract":14,"n_pointer_only":1,"phrase":"21 ran (of which 11 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/amr-parsing-via-graph-sequence-iterative#ran","syntology_url":"https://syntology.ai/paper/2004.05572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05572"}},"official":{"repos":["jcyk/AMR-gs"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/dynabert-dynamic-bert-with-adaptive-width-and","slug":"dynabert-dynamic-bert-with-adaptive-width-and","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","date":"2020-04-08","arxiv_id":"2004.04037","repositories_listed":3,"syntology":{"n":8,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dynabert-dynamic-bert-with-adaptive-width-and#ran","syntology_url":"https://syntology.ai/paper/2004.04037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04037"}},"official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/felix-flexible-text-editing-through-tagging","slug":"felix-flexible-text-editing-through-tagging","title":"Felix: Flexible Text Editing Through Tagging and Insertion","date":"2020-03-24","arxiv_id":"2003.10687","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/felix-flexible-text-editing-through-tagging#ran","syntology_url":"https://syntology.ai/paper/2003.10687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10687"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/beheshti-ner-persian-named-entity-recognition","slug":"beheshti-ner-persian-named-entity-recognition","title":"Beheshti-NER: Persian Named Entity Recognition Using BERT","date":"2020-03-19","arxiv_id":"2003.08875","repositories_listed":3,"syntology":null},{"url":"/paper/self-supervised-log-parsing","slug":"self-supervised-log-parsing","title":"Self-Supervised Log Parsing","date":"2020-03-17","arxiv_id":"2003.07905","repositories_listed":3,"syntology":null},{"url":"/paper/unilmv2-pseudo-masked-language-models-for","slug":"unilmv2-pseudo-masked-language-models-for","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","date":"2020-02-28","arxiv_id":"2002.12804","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unilmv2-pseudo-masked-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2002.12804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12804"}},"official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-much-knowledge-can-you-pack-into-the","slug":"how-much-knowledge-can-you-pack-into-the","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","date":"2020-02-10","arxiv_id":"2002.08910","repositories_listed":3,"syntology":null},{"url":"/paper/dual-multi-head-co-attention-for-multi-choice","slug":"dual-multi-head-co-attention-for-multi-choice","title":"DUMA: Reading Comprehension with Transposition Thinking","date":"2020-01-26","arxiv_id":"2001.09415","repositories_listed":3,"syntology":null},{"url":"/paper/automatic-creation-of-text-corpora-for-low","slug":"automatic-creation-of-text-corpora-for-low","title":"Automatic Creation of Text Corpora for Low-Resource Languages from the Internet: The Case of Swiss German","date":"2019-11-30","arxiv_id":"1912.00159","repositories_listed":3,"syntology":null},{"url":"/paper/multi-stage-document-ranking-with-bert","slug":"multi-stage-document-ranking-with-bert","title":"Multi-Stage Document Ranking with BERT","date":"2019-10-31","arxiv_id":"1910.14424","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-stage-document-ranking-with-bert#ran","syntology_url":"https://syntology.ai/paper/1910.14424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.14424"}},"official":null}},{"url":"/paper/fuse-multi-faceted-set-expansion-by-coherent","slug":"fuse-multi-faceted-set-expansion-by-coherent","title":"FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams","date":"2019-10-10","arxiv_id":"1910.04345","repositories_listed":3,"syntology":null},{"url":"/paper/pre-trained-language-model-for-biomedical","slug":"pre-trained-language-model-for-biomedical","title":"Pre-trained Language Model for Biomedical Question Answering","date":"2019-09-18","arxiv_id":"1909.08229","repositories_listed":3,"syntology":null},{"url":"/paper/tree-transformer-integrating-tree-structures","slug":"tree-transformer-integrating-tree-structures","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","date":"2019-09-14","arxiv_id":"1909.06639","repositories_listed":3,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tree-transformer-integrating-tree-structures#ran","syntology_url":"https://syntology.ai/paper/1909.06639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.06639"}},"official":{"repos":["yaushian/Tree-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/kg-bert-bert-for-knowledge-graph-completion","slug":"kg-bert-bert-for-knowledge-graph-completion","title":"KG-BERT: BERT for Knowledge Graph Completion","date":"2019-09-07","arxiv_id":"1909.03193","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kg-bert-bert-for-knowledge-graph-completion#ran","syntology_url":"https://syntology.ai/paper/1909.03193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03193"}},"official":{"repos":["yao8839836/kg-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adapt-or-get-left-behind-domain-adaptation","slug":"adapt-or-get-left-behind-domain-adaptation","title":"Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification","date":"2019-08-30","arxiv_id":"1908.11860","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adapt-or-get-left-behind-domain-adaptation#ran","syntology_url":"https://syntology.ai/paper/1908.11860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.11860"}},"official":{"repos":["deepopinion/domain-adapted-atsc"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/remedying-bilstm-cnn-deficiency-in-modeling","slug":"remedying-bilstm-cnn-deficiency-in-modeling","title":"Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER","date":"2019-08-29","arxiv_id":"1908.11046","repositories_listed":3,"syntology":null},{"url":"/paper/finbert-financial-sentiment-analysis-with-pre","slug":"finbert-financial-sentiment-analysis-with-pre","title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","date":"2019-08-27","arxiv_id":"1908.10063","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/finbert-financial-sentiment-analysis-with-pre#ran","syntology_url":"https://syntology.ai/paper/1908.10063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.10063"}},"official":null}},{"url":"/paper/a-hybrid-neural-network-model-for-commonsense","slug":"a-hybrid-neural-network-model-for-commonsense","title":"A Hybrid Neural Network Model for Commonsense Reasoning","date":"2019-07-27","arxiv_id":"1907.11983","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-hybrid-neural-network-model-for-commonsense#ran","syntology_url":"https://syntology.ai/paper/1907.11983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11983"}},"official":{"repos":["namisan/mt-dnn"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/eli5-long-form-question-answering","slug":"eli5-long-form-question-answering","title":"ELI5: Long Form Question Answering","date":"2019-07-22","arxiv_id":"1907.09190","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/eli5-long-form-question-answering#ran","syntology_url":"https://syntology.ai/paper/1907.09190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.09190"}},"official":{"repos":["facebookresearch/ELI5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/gpt-based-generation-for-classical-chinese","slug":"gpt-based-generation-for-classical-chinese","title":"GPT-based Generation for Classical Chinese Poetry","date":"2019-06-29","arxiv_id":"1907.00151","repositories_listed":3,"syntology":null},{"url":"/paper/how-multilingual-is-multilingual-bert","slug":"how-multilingual-is-multilingual-bert","title":"How multilingual is Multilingual BERT?","date":"2019-06-04","arxiv_id":"1906.01502","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-multilingual-is-multilingual-bert#ran","syntology_url":"https://syntology.ai/paper/1906.01502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01502"}},"official":null}},{"url":"/paper/language-model-embeddings-improve-sentiment","slug":"language-model-embeddings-improve-sentiment","title":"LANGUAGE MODEL EMBEDDINGS IMPROVE SENTIMENT ANALYSIS IN RUSSIAN","date":"2019-05-29","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/stochastic-gradient-methods-with-layer-wise","slug":"stochastic-gradient-methods-with-layer-wise","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","date":"2019-05-27","arxiv_id":"1905.11286","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stochastic-gradient-methods-with-layer-wise#ran","syntology_url":"https://syntology.ai/paper/1905.11286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11286"}},"official":null}},{"url":"/paper/videobert-a-joint-model-for-video-and","slug":"videobert-a-joint-model-for-video-and","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","date":"2019-04-03","arxiv_id":"1904.01766","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videobert-a-joint-model-for-video-and#ran","syntology_url":"https://syntology.ai/paper/1904.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01766"}},"official":null}},{"url":"/paper/model-unit-exploration-for-sequence-to","slug":"model-unit-exploration-for-sequence-to","title":"On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition","date":"2019-02-05","arxiv_id":"1902.01955","repositories_listed":3,"syntology":null},{"url":"/paper/pay-less-attention-with-lightweight-and","slug":"pay-less-attention-with-lightweight-and","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","date":"2019-01-29","arxiv_id":"1901.10430","repositories_listed":3,"syntology":null},{"url":"/paper/improving-neural-network-quantization-without","slug":"improving-neural-network-quantization-without","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","date":"2019-01-28","arxiv_id":"1901.09504","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/improving-neural-network-quantization-without#ran","syntology_url":"https://syntology.ai/paper/1901.09504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09504"}},"official":{"repos":["NervanaSystems/distiller","cornell-zhang/dnn-quant-ocs"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visual-re-ranking-with-natural-language","slug":"visual-re-ranking-with-natural-language","title":"Visual Re-ranking with Natural Language Understanding for Text Spotting","date":"2018-10-29","arxiv_id":"1810.12738","repositories_listed":3,"syntology":null},{"url":"/paper/adaptive-input-representations-for-neural","slug":"adaptive-input-representations-for-neural","title":"Adaptive Input Representations for Neural Language Modeling","date":"2018-09-28","arxiv_id":"1809.10853","repositories_listed":3,"syntology":null},{"url":"/paper/unsupervised-statistical-machine-translation","slug":"unsupervised-statistical-machine-translation","title":"Unsupervised Statistical Machine Translation","date":"2018-09-04","arxiv_id":"1809.01272","repositories_listed":3,"syntology":null},{"url":"/paper/learning-approximate-inference-networks-for","slug":"learning-approximate-inference-networks-for","title":"Learning Approximate Inference Networks for Structured Prediction","date":"2018-03-09","arxiv_id":"1803.03376","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-approximate-inference-networks-for#ran","syntology_url":"https://syntology.ai/paper/1803.03376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03376"}},"official":null}},{"url":"/paper/variational-autoencoders-for-collaborative-1","slug":"variational-autoencoders-for-collaborative-1","title":"Variational Autoencoders for Collaborative Filtering","date":"2018-02-16","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/dp-gan-diversity-promoting-generative","slug":"dp-gan-diversity-promoting-generative","title":"DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text","date":"2018-02-05","arxiv_id":"1802.01345","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dp-gan-diversity-promoting-generative#ran","syntology_url":"https://syntology.ai/paper/1802.01345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.01345"}},"official":{"repos":["lancopku/DPGAN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-multilayer-convolutional-encoder-decoder","slug":"a-multilayer-convolutional-encoder-decoder","title":"A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction","date":"2018-01-26","arxiv_id":"1801.08831","repositories_listed":3,"syntology":null},{"url":"/paper/generating-sentences-by-editing-prototypes","slug":"generating-sentences-by-editing-prototypes","title":"Generating Sentences by Editing Prototypes","date":"2017-09-26","arxiv_id":"1709.08878","repositories_listed":3,"syntology":null},{"url":"/paper/empower-sequence-labeling-with-task-aware","slug":"empower-sequence-labeling-with-task-aware","title":"Empower Sequence Labeling with Task-Aware Neural Language Model","date":"2017-09-13","arxiv_id":"1709.04109","repositories_listed":3,"syntology":null},{"url":"/paper/semi-supervised-multitask-learning-for","slug":"semi-supervised-multitask-learning-for","title":"Semi-supervised Multitask Learning for Sequence Labeling","date":"2017-04-24","arxiv_id":"1704.07156","repositories_listed":3,"syntology":null},{"url":"/paper/a-hybrid-convolutional-variational","slug":"a-hybrid-convolutional-variational","title":"A Hybrid Convolutional Variational Autoencoder for Text Generation","date":"2017-02-08","arxiv_id":"1702.02390","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-hybrid-convolutional-variational#ran","syntology_url":"https://syntology.ai/paper/1702.02390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02390"}},"official":{"repos":["stas-semeniuta/textvae"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improving-lstm-based-video-description-with","slug":"improving-lstm-based-video-description-with","title":"Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text","date":"2016-04-06","arxiv_id":"1604.01729","repositories_listed":3,"syntology":null},{"url":"/paper/neural-language-correction-with-character","slug":"neural-language-correction-with-character","title":"Neural Language Correction with Character-Based Attention","date":"2016-03-31","arxiv_id":"1603.09727","repositories_listed":3,"syntology":null},{"url":"/paper/recurrent-batch-normalization","slug":"recurrent-batch-normalization","title":"Recurrent Batch Normalization","date":"2016-03-30","arxiv_id":"1603.09025","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/recurrent-batch-normalization#ran","syntology_url":"https://syntology.ai/paper/1603.09025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.09025"}},"official":null}},{"url":"/paper/long-short-term-memory-networks-for-machine","slug":"long-short-term-memory-networks-for-machine","title":"Long Short-Term Memory-Networks for Machine Reading","date":"2016-01-25","arxiv_id":"1601.06733","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-short-term-memory-networks-for-machine#ran","syntology_url":"https://syntology.ai/paper/1601.06733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1601.06733"}},"official":null}},{"url":"/paper/grounding-of-textual-phrases-in-images-by","slug":"grounding-of-textual-phrases-in-images-by","title":"Grounding of Textual Phrases in Images by Reconstruction","date":"2015-11-12","arxiv_id":"1511.03745","repositories_listed":3,"syntology":null},{"url":"/paper/unifying-visual-semantic-embeddings-with","slug":"unifying-visual-semantic-embeddings-with","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","date":"2014-11-10","arxiv_id":"1411.2539","repositories_listed":3,"syntology":null},{"url":"/paper/one-billion-word-benchmark-for-measuring","slug":"one-billion-word-benchmark-for-measuring","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","date":"2013-12-11","arxiv_id":"1312.3005","repositories_listed":3,"syntology":null},{"url":"/paper/desta2-5-audio-toward-general-purpose-large","slug":"desta2-5-audio-toward-general-purpose-large","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","date":"2025-07-03","arxiv_id":"2507.02768","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/desta2-5-audio-toward-general-purpose-large#ran","syntology_url":"https://syntology.ai/paper/2507.02768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.02768"}},"official":{"repos":["kehanlu/desta2.5-audio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-finding-sparse-and-flat-minima-to","slug":"safe-finding-sparse-and-flat-minima-to","title":"SAFE: Finding Sparse and Flat Minima to Improve Pruning","date":"2025-06-07","arxiv_id":"2506.06866","repositories_listed":2,"syntology":{"n":18,"n_ran":10,"n_constructed":1,"n_ran_checked":4,"n_instrument":6,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/safe-finding-sparse-and-flat-minima-to#ran","syntology_url":"https://syntology.ai/paper/2506.06866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.06866"}},"official":{"repos":["LOG-postech/safe-torch","log-postech/safe-jax"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/llamea-bo-a-large-language-model-evolutionary","slug":"llamea-bo-a-large-language-model-evolutionary","title":"LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms","date":"2025-05-27","arxiv_id":"2505.21034","repositories_listed":2,"syntology":null},{"url":"/paper/imgedit-a-unified-image-editing-dataset-and","slug":"imgedit-a-unified-image-editing-dataset-and","title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","date":"2025-05-26","arxiv_id":"2505.20275","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imgedit-a-unified-image-editing-dataset-and#ran","syntology_url":"https://syntology.ai/paper/2505.20275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20275"}},"official":{"repos":["pku-yuangroup/imgedit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/path-attention-position-encoding-via","slug":"path-attention-position-encoding-via","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","date":"2025-05-22","arxiv_id":"2505.16381","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/path-attention-position-encoding-via#ran","syntology_url":"https://syntology.ai/paper/2505.16381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16381"}},"official":{"repos":["fla-org/flash-linear-attention","sustcsonglin/flash-linear-attention"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/wirelessagent-large-language-model-agents-for-1","slug":"wirelessagent-large-language-model-agents-for-1","title":"WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks","date":"2025-05-02","arxiv_id":"2505.01074","repositories_listed":2,"syntology":null},{"url":"/paper/taste-text-aligned-speech-tokenization-and","slug":"taste-text-aligned-speech-tokenization-and","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","date":"2025-04-09","arxiv_id":"2504.07053","repositories_listed":2,"syntology":{"n":20,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":20,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/taste-text-aligned-speech-tokenization-and#ran","syntology_url":"https://syntology.ai/paper/2504.07053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07053"}},"official":{"repos":["mtkresearch/taste-spokenlm"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/representation-bending-for-large-language","slug":"representation-bending-for-large-language","title":"Representation Bending for Large Language Model Safety","date":"2025-04-02","arxiv_id":"2504.01550","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/representation-bending-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2504.01550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01550"}},"official":{"repos":["aim-intelligence/repbend"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/whisper-lm-improving-asr-models-with-language","slug":"whisper-lm-improving-asr-models-with-language","title":"Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages","date":"2025-03-30","arxiv_id":"2503.23542","repositories_listed":2,"syntology":null},{"url":"/paper/generalized-few-shot-3d-point-cloud","slug":"generalized-few-shot-3d-point-cloud","title":"Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model","date":"2025-03-20","arxiv_id":"2503.16282","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/generalized-few-shot-3d-point-cloud#ran","syntology_url":"https://syntology.ai/paper/2503.16282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16282"}},"official":{"repos":["zhaochongan/gfs-vl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/smoldocling-an-ultra-compact-vision-language","slug":"smoldocling-an-ultra-compact-vision-language","title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion","date":"2025-03-14","arxiv_id":"2503.11576","repositories_listed":2,"syntology":null},{"url":"/paper/block-diffusion-interpolating-between","slug":"block-diffusion-interpolating-between","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","date":"2025-03-12","arxiv_id":"2503.09573","repositories_listed":2,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/block-diffusion-interpolating-between#ran","syntology_url":"https://syntology.ai/paper/2503.09573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09573"}},"official":{"repos":["kuleshov-group/bd3lms"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}}],"record_sha256":"42771f9601f9315b5aa1b205663d6fa310a30d7fad9119b45192aa519d3858c7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}