{"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-modelling/papers/11","list_of":"/task/language-modelling","task":"Language Modelling","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":11,"pages_in_order":177,"rows_per_page":100,"rows":[1001,1100],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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-modelling","prev":"/task/language-modelling/papers/10","next":"/task/language-modelling/papers/12","papers":[{"url":"/paper/time-masking-for-temporal-language-models","slug":"time-masking-for-temporal-language-models","title":"Time Masking for Temporal Language Models","date":"2021-10-12","arxiv_id":"2110.06366","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/time-masking-for-temporal-language-models#ran","syntology_url":"https://syntology.ai/paper/2110.06366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06366"}},"official":{"repos":["guyrosin/tempobert"],"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":["listed","official"]}}},{"url":"/paper/xlm-k-improving-cross-lingual-language-model","slug":"xlm-k-improving-cross-lingual-language-model","title":"XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge","date":"2021-09-26","arxiv_id":"2109.12573","repositories_listed":2,"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/xlm-k-improving-cross-lingual-language-model#ran","syntology_url":"https://syntology.ai/paper/2109.12573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12573"}},"official":{"repos":["microsoft/Unicoder"],"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/dziribert-a-pre-trained-language-model-for","slug":"dziribert-a-pre-trained-language-model-for","title":"DziriBERT: a Pre-trained Language Model for the Algerian Dialect","date":"2021-09-25","arxiv_id":"2109.12346","repositories_listed":2,"syntology":null},{"url":"/paper/allocating-large-vocabulary-capacity-for","slug":"allocating-large-vocabulary-capacity-for","title":"Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training","date":"2021-09-15","arxiv_id":"2109.07306","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/allocating-large-vocabulary-capacity-for#ran","syntology_url":"https://syntology.ai/paper/2109.07306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07306"}},"official":{"repos":["bozheng-hit/vocapxlm"],"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/rationales-for-sequential-predictions","slug":"rationales-for-sequential-predictions","title":"Rationales for Sequential Predictions","date":"2021-09-14","arxiv_id":"2109.06387","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rationales-for-sequential-predictions#ran","syntology_url":"https://syntology.ai/paper/2109.06387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06387"}},"official":{"repos":["keyonvafa/sequential-rationales"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/bert-mbert-or-bibert-a-study-on","slug":"bert-mbert-or-bibert-a-study-on","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","date":"2021-09-09","arxiv_id":"2109.04588","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 1 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/bert-mbert-or-bibert-a-study-on#ran","syntology_url":"https://syntology.ai/paper/2109.04588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04588"}},"official":{"repos":["fe1ixxu/BiBERT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/debiasing-methods-in-natural-language","slug":"debiasing-methods-in-natural-language","title":"Debiasing Methods in Natural Language Understanding Make Bias More Accessible","date":"2021-09-09","arxiv_id":"2109.04095","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-nearest-neighbor-language-models","slug":"efficient-nearest-neighbor-language-models","title":"Efficient Nearest Neighbor Language Models","date":"2021-09-09","arxiv_id":"2109.04212","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-nearest-neighbor-language-models#ran","syntology_url":"https://syntology.ai/paper/2109.04212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04212"}},"official":{"repos":["jxhe/efficient-knnlm"],"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/it-is-ai-s-turn-to-ask-human-a-question","slug":"it-is-ai-s-turn-to-ask-human-a-question","title":"It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books","date":"2021-09-08","arxiv_id":"2109.03423","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-contribution-of-per-icd-attention","slug":"on-the-contribution-of-per-icd-attention","title":"On the Contribution of Per-ICD Attention Mechanisms to Classify Health Records in Languages with Fewer Resources than English","date":"2021-09-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/on-the-multilingual-capabilities-of-very","slug":"on-the-multilingual-capabilities-of-very","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","date":"2021-08-30","arxiv_id":"2108.13349","repositories_listed":2,"syntology":null},{"url":"/paper/dealing-with-typos-for-bert-based-passage","slug":"dealing-with-typos-for-bert-based-passage","title":"Dealing with Typos for BERT-based Passage Retrieval and Ranking","date":"2021-08-27","arxiv_id":"2108.12139","repositories_listed":2,"syntology":null},{"url":"/paper/simvlm-simple-visual-language-model","slug":"simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","arxiv_id":"2108.10904","repositories_listed":2,"syntology":{"n":37,"n_ran":22,"n_constructed":8,"n_ran_checked":16,"n_instrument":6,"n_unverified":15,"n_honours":1,"n_violates":3,"n_no_contract":12,"n_pointer_only":32,"phrase":"22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 3 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/simvlm-simple-visual-language-model#ran","syntology_url":"https://syntology.ai/paper/2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}},"official":null}},{"url":"/paper/smedbert-a-knowledge-enhanced-pre-trained","slug":"smedbert-a-knowledge-enhanced-pre-trained","title":"SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining","date":"2021-08-20","arxiv_id":"2108.08983","repositories_listed":2,"syntology":null},{"url":"/paper/demix-layers-disentangling-domains-for","slug":"demix-layers-disentangling-domains-for","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","date":"2021-08-11","arxiv_id":"2108.05036","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/demix-layers-disentangling-domains-for#ran","syntology_url":"https://syntology.ai/paper/2108.05036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.05036"}},"official":{"repos":["kernelmachine/demix","kernelmachine/demix-data"],"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/bros-a-layout-aware-pre-trained-language","slug":"bros-a-layout-aware-pre-trained-language","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","date":"2021-08-10","arxiv_id":"2108.04539","repositories_listed":2,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"13 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bros-a-layout-aware-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2108.04539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04539"}},"official":{"repos":["clovaai/bros"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledgeable-prompt-tuning-incorporating","slug":"knowledgeable-prompt-tuning-incorporating","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","date":"2021-08-04","arxiv_id":"2108.02035","repositories_listed":2,"syntology":null},{"url":"/paper/look-back-again-dual-parallel-attention","slug":"look-back-again-dual-parallel-attention","title":"Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition","date":"2021-08-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/h-transformer-1d-fast-one-dimensional","slug":"h-transformer-1d-fast-one-dimensional","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","date":"2021-07-25","arxiv_id":"2107.11906","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":1,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/h-transformer-1d-fast-one-dimensional#ran","syntology_url":"https://syntology.ai/paper/2107.11906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.11906"}},"official":null}},{"url":"/paper/a-comparison-of-methods-for-oov-word","slug":"a-comparison-of-methods-for-oov-word","title":"A Comparison of Methods for OOV-word Recognition on a New Public Dataset","date":"2021-07-16","arxiv_id":"2107.08091","repositories_listed":2,"syntology":null},{"url":"/paper/flex-unifying-evaluation-for-few-shot-nlp","slug":"flex-unifying-evaluation-for-few-shot-nlp","title":"FLEX: Unifying Evaluation for Few-Shot NLP","date":"2021-07-15","arxiv_id":"2107.07170","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/flex-unifying-evaluation-for-few-shot-nlp#ran","syntology_url":"https://syntology.ai/paper/2107.07170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07170"}},"official":{"repos":["allenai/flex","allenai/unifew"],"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/deduplicating-training-data-makes-language","slug":"deduplicating-training-data-makes-language","title":"Deduplicating Training Data Makes Language Models Better","date":"2021-07-14","arxiv_id":"2107.06499","repositories_listed":2,"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/deduplicating-training-data-makes-language#ran","syntology_url":"https://syntology.ai/paper/2107.06499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06499"}},"official":{"repos":["google-research/deduplicate-text-datasets"],"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/combiner-full-attention-transformer-with","slug":"combiner-full-attention-transformer-with","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","date":"2021-07-12","arxiv_id":"2107.05768","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/combiner-full-attention-transformer-with#ran","syntology_url":"https://syntology.ai/paper/2107.05768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05768"}},"official":{"repos":["google-research/google-research"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/symbolicgpt-a-generative-transformer-model","slug":"symbolicgpt-a-generative-transformer-model","title":"SymbolicGPT: A Generative Transformer Model for Symbolic Regression","date":"2021-06-27","arxiv_id":"2106.14131","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/symbolicgpt-a-generative-transformer-model#ran","syntology_url":"https://syntology.ai/paper/2106.14131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14131"}},"official":{"repos":["git.uwaterloo.ca/data-analytics-lab/symbolicgpt2"],"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/multi-objective-asynchronous-successive","slug":"multi-objective-asynchronous-successive","title":"Multi-objective Asynchronous Successive Halving","date":"2021-06-23","arxiv_id":"2106.12639","repositories_listed":2,"syntology":null},{"url":"/paper/distributed-deep-learning-in-open","slug":"distributed-deep-learning-in-open","title":"Distributed Deep Learning in Open Collaborations","date":"2021-06-18","arxiv_id":"2106.10207","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/distributed-deep-learning-in-open#ran","syntology_url":"https://syntology.ai/paper/2106.10207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10207"}},"official":{"repos":["learning-at-home/hivemind","yandex-research/DeDLOC"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"url":"/paper/golos-russian-dataset-for-speech-research","slug":"golos-russian-dataset-for-speech-research","title":"Golos: Russian Dataset for Speech Research","date":"2021-06-18","arxiv_id":"2106.10161","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/golos-russian-dataset-for-speech-research#ran","syntology_url":"https://syntology.ai/paper/2106.10161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10161"}},"official":{"repos":["sberdevices/golos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/top-kast-top-k-always-sparse-training-1","slug":"top-kast-top-k-always-sparse-training-1","title":"Top-KAST: Top-K Always Sparse Training","date":"2021-06-07","arxiv_id":"2106.03517","repositories_listed":2,"syntology":null},{"url":"/paper/luna-linear-unified-nested-attention","slug":"luna-linear-unified-nested-attention","title":"Luna: Linear Unified Nested Attention","date":"2021-06-03","arxiv_id":"2106.01540","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/luna-linear-unified-nested-attention#ran","syntology_url":"https://syntology.ai/paper/2106.01540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01540"}},"official":{"repos":["XuezheMax/fairseq-apollo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/shuowen-jiezi-linguistically-informed","slug":"shuowen-jiezi-linguistically-informed","title":"Sub-Character Tokenization for Chinese Pretrained Language Models","date":"2021-06-01","arxiv_id":"2106.00400","repositories_listed":2,"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":4,"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/shuowen-jiezi-linguistically-informed#ran","syntology_url":"https://syntology.ai/paper/2106.00400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00400"}},"official":{"repos":["thunlp/subchartokenization"],"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","unlocated"]}}},{"url":"/paper/ucphrase-unsupervised-context-aware-quality","slug":"ucphrase-unsupervised-context-aware-quality","title":"UCPhrase: Unsupervised Context-aware Quality Phrase Tagging","date":"2021-05-28","arxiv_id":"2105.14078","repositories_listed":2,"syntology":null},{"url":"/paper/fedscale-benchmarking-model-and-system","slug":"fedscale-benchmarking-model-and-system","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","date":"2021-05-24","arxiv_id":"2105.11367","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"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; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fedscale-benchmarking-model-and-system#ran","syntology_url":"https://syntology.ai/paper/2105.11367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11367"}},"official":{"repos":["SymbioticLab/FedScale"],"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":["listed","official"]}}},{"url":"/paper/neural-language-models-for-nineteenth-century","slug":"neural-language-models-for-nineteenth-century","title":"Neural Language Models for Nineteenth-Century English","date":"2021-05-24","arxiv_id":"2105.11321","repositories_listed":2,"syntology":null},{"url":"/paper/from-masked-language-modeling-to-translation","slug":"from-masked-language-modeling-to-translation","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","date":"2021-05-15","arxiv_id":"2105.07316","repositories_listed":2,"syntology":null},{"url":"/paper/e-vil-a-dataset-and-benchmark-for-natural","slug":"e-vil-a-dataset-and-benchmark-for-natural","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","date":"2021-05-08","arxiv_id":"2105.03761","repositories_listed":2,"syntology":{"n":15,"n_ran":7,"n_constructed":3,"n_ran_checked":6,"n_instrument":1,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":15,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/e-vil-a-dataset-and-benchmark-for-natural#ran","syntology_url":"https://syntology.ai/paper/2105.03761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03761"}},"official":{"repos":["maximek3/e-ViL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/handwritten-mathematical-expression","slug":"handwritten-mathematical-expression","title":"Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer","date":"2021-05-06","arxiv_id":"2105.02412","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 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) · 0 unverified","sample_list":"/paper/handwritten-mathematical-expression#ran","syntology_url":"https://syntology.ai/paper/2105.02412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02412"}},"official":{"repos":["Green-Wood/BTTR"],"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/electramed-a-new-pre-trained-language","slug":"electramed-a-new-pre-trained-language","title":"ELECTRAMed: a new pre-trained language representation model for biomedical NLP","date":"2021-04-19","arxiv_id":"2104.09585","repositories_listed":2,"syntology":null},{"url":"/paper/operationalizing-a-national-digital-library","slug":"operationalizing-a-national-digital-library","title":"Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model","date":"2021-04-19","arxiv_id":"2104.09617","repositories_listed":2,"syntology":null},{"url":"/paper/misinfo-belief-frames-a-case-study-on-covid","slug":"misinfo-belief-frames-a-case-study-on-covid","title":"Misinfo Reaction Frames: Reasoning about Readers' Reactions to News Headlines","date":"2021-04-18","arxiv_id":"2104.08790","repositories_listed":2,"syntology":null},{"url":"/paper/towards-open-world-text-guided-face-image","slug":"towards-open-world-text-guided-face-image","title":"Towards Open-World Text-Guided Face Image Generation and Manipulation","date":"2021-04-18","arxiv_id":"2104.08910","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-open-world-text-guided-face-image#ran","syntology_url":"https://syntology.ai/paper/2104.08910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08910"}},"official":{"repos":["weihaox/TediGAN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/decrypting-cryptic-crosswords-semantically","slug":"decrypting-cryptic-crosswords-semantically","title":"Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP","date":"2021-04-17","arxiv_id":"2104.08620","repositories_listed":2,"syntology":null},{"url":"/paper/temporal-adaptation-of-bert-and-performance","slug":"temporal-adaptation-of-bert-and-performance","title":"Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media","date":"2021-04-16","arxiv_id":"2104.08116","repositories_listed":2,"syntology":null},{"url":"/paper/text2app-a-framework-for-creating-android","slug":"text2app-a-framework-for-creating-android","title":"Text2App: A Framework for Creating Android Apps from Text Descriptions","date":"2021-04-16","arxiv_id":"2104.08301","repositories_listed":2,"syntology":null},{"url":"/paper/learning-how-to-ask-querying-lms-with","slug":"learning-how-to-ask-querying-lms-with","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","date":"2021-04-14","arxiv_id":"2104.06599","repositories_listed":2,"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/learning-how-to-ask-querying-lms-with#ran","syntology_url":"https://syntology.ai/paper/2104.06599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06599"}},"official":{"repos":["hiaoxui/soft-prompts"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/large-scale-contextualised-language-modelling","slug":"large-scale-contextualised-language-modelling","title":"Large-Scale Contextualised Language Modelling for Norwegian","date":"2021-04-13","arxiv_id":"2104.06546","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/large-scale-contextualised-language-modelling#ran","syntology_url":"https://syntology.ai/paper/2104.06546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06546"}},"official":{"repos":["ltgoslo/NorBERT","ltgoslo/norec_sentence"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/factual-probing-is-mask-learning-vs-learning","slug":"factual-probing-is-mask-learning-vs-learning","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","date":"2021-04-12","arxiv_id":"2104.05240","repositories_listed":2,"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/factual-probing-is-mask-learning-vs-learning#ran","syntology_url":"https://syntology.ai/paper/2104.05240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05240"}},"official":{"repos":["princeton-nlp/OptiPrompt"],"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/alephbert-a-hebrew-large-pre-trained-language","slug":"alephbert-a-hebrew-large-pre-trained-language","title":"AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With","date":"2021-04-08","arxiv_id":"2104.04052","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":2,"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/alephbert-a-hebrew-large-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2104.04052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.04052"}},"official":{"repos":["OnlpLab/Hebrew-Sentiment-Data"],"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/nutribullets-hybrid-multi-document-health","slug":"nutribullets-hybrid-multi-document-health","title":"Nutribullets Hybrid: Multi-document Health Summarization","date":"2021-04-08","arxiv_id":"2104.03465","repositories_listed":2,"syntology":null},{"url":"/paper/librispeech-transducer-model-with-internal","slug":"librispeech-transducer-model-with-internal","title":"Librispeech Transducer Model with Internal Language Model Prior Correction","date":"2021-04-07","arxiv_id":"2104.03006","repositories_listed":2,"syntology":null},{"url":"/paper/finetuning-pretrained-transformers-into-rnns","slug":"finetuning-pretrained-transformers-into-rnns","title":"Finetuning Pretrained Transformers into RNNs","date":"2021-03-24","arxiv_id":"2103.13076","repositories_listed":2,"syntology":{"n":8,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/finetuning-pretrained-transformers-into-rnns#ran","syntology_url":"https://syntology.ai/paper/2103.13076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13076"}},"official":null}},{"url":"/paper/learning-chess-blindfolded-evaluating","slug":"learning-chess-blindfolded-evaluating","title":"Chess as a Testbed for Language Model State Tracking","date":"2021-02-26","arxiv_id":"2102.13249","repositories_listed":2,"syntology":null},{"url":"/paper/roberta-wwm-ext-fine-tuning-for-chinese-text","slug":"roberta-wwm-ext-fine-tuning-for-chinese-text","title":"RoBERTa-wwm-ext Fine-Tuning for Chinese Text Classification","date":"2021-02-24","arxiv_id":"2103.00492","repositories_listed":2,"syntology":null},{"url":"/paper/coco-lm-correcting-and-contrasting-text","slug":"coco-lm-correcting-and-contrasting-text","title":"COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining","date":"2021-02-16","arxiv_id":"2102.08473","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coco-lm-correcting-and-contrasting-text#ran","syntology_url":"https://syntology.ai/paper/2102.08473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.08473"}},"official":{"repos":["microsoft/coco-lm"],"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/gradinit-learning-to-initialize-neural","slug":"gradinit-learning-to-initialize-neural","title":"GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training","date":"2021-02-16","arxiv_id":"2102.08098","repositories_listed":2,"syntology":{"n":13,"n_ran":7,"n_constructed":4,"n_ran_checked":4,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":12,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/gradinit-learning-to-initialize-neural#ran","syntology_url":"https://syntology.ai/paper/2102.08098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.08098"}},"official":{"repos":["zhuchen03/gradinit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dobf-a-deobfuscation-pre-training-objective","slug":"dobf-a-deobfuscation-pre-training-objective","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","date":"2021-02-15","arxiv_id":"2102.07492","repositories_listed":2,"syntology":null},{"url":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","repositories_listed":2,"syntology":{"n":12,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 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) · 10 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}},"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-spoken-language-modeling-from-raw","slug":"generative-spoken-language-modeling-from-raw","title":"Generative Spoken Language Modeling from Raw Audio","date":"2021-02-01","arxiv_id":"2102.01192","repositories_listed":2,"syntology":null},{"url":"/paper/muppet-massive-multi-task-representations","slug":"muppet-massive-multi-task-representations","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","date":"2021-01-26","arxiv_id":"2101.11038","repositories_listed":2,"syntology":null},{"url":"/paper/wangchanberta-pretraining-transformer-based","slug":"wangchanberta-pretraining-transformer-based","title":"WangchanBERTa: Pretraining transformer-based Thai Language Models","date":"2021-01-24","arxiv_id":"2101.09635","repositories_listed":2,"syntology":null},{"url":"/paper/cross-document-language-modeling","slug":"cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","date":"2021-01-02","arxiv_id":"2101.00406","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-doc-the-retrospective-long-document","slug":"ernie-doc-the-retrospective-long-document","title":"ERNIE-Doc: A Retrospective Long-Document Modeling Transformer","date":"2020-12-31","arxiv_id":"2012.15688","repositories_listed":2,"syntology":null},{"url":"/paper/deer-a-data-efficient-language-model-for","slug":"deer-a-data-efficient-language-model-for","title":"ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning","date":"2020-12-30","arxiv_id":"2012.15283","repositories_listed":2,"syntology":null},{"url":"/paper/intrinsic-dimensionality-explains-the","slug":"intrinsic-dimensionality-explains-the","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","date":"2020-12-22","arxiv_id":"2012.13255","repositories_listed":2,"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/intrinsic-dimensionality-explains-the#ran","syntology_url":"https://syntology.ai/paper/2012.13255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.13255"}},"official":{"repos":["rabeehk/compacter"],"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/fusing-context-into-knowledge-graph-for","slug":"fusing-context-into-knowledge-graph-for","title":"Fusing Context Into Knowledge Graph for Commonsense Question Answering","date":"2020-12-09","arxiv_id":"2012.04808","repositories_listed":2,"syntology":null},{"url":"/paper/pgl-at-textgraphs-2020-shared-task","slug":"pgl-at-textgraphs-2020-shared-task","title":"PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods","date":"2020-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/structformer-joint-unsupervised-induction-of-1","slug":"structformer-joint-unsupervised-induction-of-1","title":"StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling","date":"2020-12-01","arxiv_id":"2012.00857","repositories_listed":2,"syntology":null},{"url":"/paper/understanding-how-bert-learns-to-identify","slug":"understanding-how-bert-learns-to-identify","title":"An Investigation of Language Model Interpretability via Sentence Editing","date":"2020-11-28","arxiv_id":"2011.14039","repositories_listed":2,"syntology":null},{"url":"/paper/the-zero-resource-speech-benchmark-2021","slug":"the-zero-resource-speech-benchmark-2021","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","date":"2020-11-23","arxiv_id":"2011.11588","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/the-zero-resource-speech-benchmark-2021#ran","syntology_url":"https://syntology.ai/paper/2011.11588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.11588"}},"official":{"repos":["bootphon/zerospeech2021_baseline"],"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/data-informed-global-sparseness-in-attention","slug":"data-informed-global-sparseness-in-attention","title":"Data-Informed Global Sparseness in Attention Mechanisms for Deep Neural Networks","date":"2020-11-20","arxiv_id":"2012.02030","repositories_listed":2,"syntology":null},{"url":"/paper/character-level-representations-improve-drs","slug":"character-level-representations-improve-drs","title":"Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT","date":"2020-11-09","arxiv_id":"2011.04308","repositories_listed":2,"syntology":null},{"url":"/paper/abnirml-analyzing-the-behavior-of-neural-ir","slug":"abnirml-analyzing-the-behavior-of-neural-ir","title":"ABNIRML: Analyzing the Behavior of Neural IR Models","date":"2020-11-02","arxiv_id":"2011.00696","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/abnirml-analyzing-the-behavior-of-neural-ir#ran","syntology_url":"https://syntology.ai/paper/2011.00696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.00696"}},"official":{"repos":["allenai/abnirml"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-pre-trained-bert-for-aspect","slug":"understanding-pre-trained-bert-for-aspect","title":"Understanding Pre-trained BERT for Aspect-based Sentiment Analysis","date":"2020-10-31","arxiv_id":"2011.00169","repositories_listed":2,"syntology":null},{"url":"/paper/automatically-identifying-words-that-can","slug":"automatically-identifying-words-that-can","title":"Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification","date":"2020-10-26","arxiv_id":"2010.13641","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-gram-pre-training-with-explicitly-n","slug":"ernie-gram-pre-training-with-explicitly-n","title":"ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding","date":"2020-10-23","arxiv_id":"2010.12148","repositories_listed":2,"syntology":null},{"url":"/paper/tweeteval-unified-benchmark-and-comparative","slug":"tweeteval-unified-benchmark-and-comparative","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","date":"2020-10-23","arxiv_id":"2010.12421","repositories_listed":2,"syntology":null},{"url":"/paper/multi-task-learning-of-negation-and","slug":"multi-task-learning-of-negation-and","title":"Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification","date":"2020-10-16","arxiv_id":"2010.08318","repositories_listed":2,"syntology":null},{"url":"/paper/text-classification-using-label-names-only-a","slug":"text-classification-using-label-names-only-a","title":"Text Classification Using Label Names Only: A Language Model Self-Training Approach","date":"2020-10-14","arxiv_id":"2010.07245","repositories_listed":2,"syntology":null},{"url":"/paper/pagsusuri-ng-rnn-based-transfer-learning","slug":"pagsusuri-ng-rnn-based-transfer-learning","title":"Pagsusuri ng RNN-based Transfer Learning Technique sa Low-Resource Language","date":"2020-10-13","arxiv_id":"2010.06447","repositories_listed":2,"syntology":null},{"url":"/paper/inductive-entity-representations-from-text","slug":"inductive-entity-representations-from-text","title":"Inductive Entity Representations from Text via Link Prediction","date":"2020-10-07","arxiv_id":"2010.03496","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/inductive-entity-representations-from-text#ran","syntology_url":"https://syntology.ai/paper/2010.03496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03496"}},"official":{"repos":["dfdazac/blp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/converting-the-point-of-view-of-messages","slug":"converting-the-point-of-view-of-messages","title":"Converting the Point of View of Messages Spoken to Virtual Assistants","date":"2020-10-06","arxiv_id":"2010.02600","repositories_listed":2,"syntology":null},{"url":"/paper/genaug-data-augmentation-for-finetuning-text","slug":"genaug-data-augmentation-for-finetuning-text","title":"GenAug: Data Augmentation for Finetuning Text Generators","date":"2020-10-05","arxiv_id":"2010.01794","repositories_listed":2,"syntology":null},{"url":"/paper/semi-supervised-speech-language-joint-pre-1","slug":"semi-supervised-speech-language-joint-pre-1","title":"SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding","date":"2020-10-05","arxiv_id":"2010.02295","repositories_listed":2,"syntology":null},{"url":"/paper/owl2vec-embedding-of-owl-ontologies","slug":"owl2vec-embedding-of-owl-ontologies","title":"OWL2Vec*: Embedding of OWL Ontologies","date":"2020-09-30","arxiv_id":"2009.14654","repositories_listed":2,"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/owl2vec-embedding-of-owl-ontologies#ran","syntology_url":"https://syntology.ai/paper/2009.14654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14654"}},"official":{"repos":["KRR-Oxford/OWL2Vec-Star"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/pay-attention-when-required","slug":"pay-attention-when-required","title":"Pay Attention when Required","date":"2020-09-09","arxiv_id":"2009.04534","repositories_listed":2,"syntology":null},{"url":"/paper/sentimental-liar-extended-corpus-and-deep","slug":"sentimental-liar-extended-corpus-and-deep","title":"Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification","date":"2020-09-01","arxiv_id":"2009.01047","repositories_listed":2,"syntology":null},{"url":"/paper/intermediate-training-of-bert-for-product","slug":"intermediate-training-of-bert-for-product","title":"Intermediate Training of BERT for Product Matching","date":"2020-08-31","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/glancing-transformer-for-non-autoregressive","slug":"glancing-transformer-for-non-autoregressive","title":"Glancing Transformer for Non-Autoregressive Neural Machine Translation","date":"2020-08-18","arxiv_id":"2008.07905","repositories_listed":2,"syntology":null},{"url":"/paper/hybrid-ranking-network-for-text-to-sql","slug":"hybrid-ranking-network-for-text-to-sql","title":"Hybrid Ranking Network for Text-to-SQL","date":"2020-08-11","arxiv_id":"2008.04759","repositories_listed":2,"syntology":null},{"url":"/paper/ae-textspotter-learning-visual-and-linguistic","slug":"ae-textspotter-learning-visual-and-linguistic","title":"AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting","date":"2020-08-03","arxiv_id":"2008.00714","repositories_listed":2,"syntology":null},{"url":"/paper/delight-very-deep-and-light-weight","slug":"delight-very-deep-and-light-weight","title":"DeLighT: Deep and Light-weight Transformer","date":"2020-08-03","arxiv_id":"2008.00623","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 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) · 0 unverified","sample_list":"/paper/delight-very-deep-and-light-weight#ran","syntology_url":"https://syntology.ai/paper/2008.00623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.00623"}},"official":{"repos":["sacmehta/delight"],"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/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","repositories_listed":2,"syntology":null},{"url":"/paper/mirostat-a-perplexity-controlled-neural-text","slug":"mirostat-a-perplexity-controlled-neural-text","title":"Mirostat: A Neural Text Decoding Algorithm that Directly Controls Perplexity","date":"2020-07-29","arxiv_id":"2007.14966","repositories_listed":2,"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":0,"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/mirostat-a-perplexity-controlled-neural-text#ran","syntology_url":"https://syntology.ai/paper/2007.14966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14966"}},"official":{"repos":["basusourya/mirostat"],"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/the-lottery-ticket-hypothesis-for-pre-trained","slug":"the-lottery-ticket-hypothesis-for-pre-trained","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","date":"2020-07-23","arxiv_id":"2007.12223","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-lottery-ticket-hypothesis-for-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2007.12223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.12223"}},"official":{"repos":["TAMU-VITA/BERT-Tickets","VITA-Group/BERT-Tickets"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-spoken-language-representations-with-1","slug":"learning-spoken-language-representations-with-1","title":"Learning Spoken Language Representations with Neural Lattice Language Modeling","date":"2020-07-06","arxiv_id":"2007.02629","repositories_listed":2,"syntology":null},{"url":"/paper/processing-south-asian-languages-written-in-1","slug":"processing-south-asian-languages-written-in-1","title":"Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset","date":"2020-07-02","arxiv_id":"2007.01176","repositories_listed":2,"syntology":null},{"url":"/paper/pre-training-via-paraphrasing","slug":"pre-training-via-paraphrasing","title":"Pre-training via Paraphrasing","date":"2020-06-26","arxiv_id":"2006.15020","repositories_listed":2,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":3,"n_honours":3,"n_violates":2,"n_no_contract":7,"n_pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 2 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pre-training-via-paraphrasing#ran","syntology_url":"https://syntology.ai/paper/2006.15020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15020"}},"official":null}},{"url":"/paper/senwave-monitoring-the-global-sentiments","slug":"senwave-monitoring-the-global-sentiments","title":"SenWave: Monitoring the Global Sentiments under the COVID-19 Pandemic","date":"2020-06-18","arxiv_id":"2006.10842","repositories_listed":2,"syntology":null},{"url":"/paper/finbert-a-pretrained-language-model-for","slug":"finbert-a-pretrained-language-model-for","title":"FinBERT: A Pretrained Language Model for Financial Communications","date":"2020-06-15","arxiv_id":"2006.08097","repositories_listed":2,"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/finbert-a-pretrained-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2006.08097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08097"}},"official":{"repos":["yya518/FinBERT"],"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/massive-choice-ample-tasks-machamp-a-toolkit","slug":"massive-choice-ample-tasks-machamp-a-toolkit","title":"Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP","date":"2020-05-29","arxiv_id":"2005.14672","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/massive-choice-ample-tasks-machamp-a-toolkit#ran","syntology_url":"https://syntology.ai/paper/2005.14672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14672"}},"official":{"repos":["machamp-nlp/machamp"],"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/text-to-text-pre-training-for-data-to-text","slug":"text-to-text-pre-training-for-data-to-text","title":"Text-to-Text Pre-Training for Data-to-Text Tasks","date":"2020-05-21","arxiv_id":"2005.10433","repositories_listed":2,"syntology":null}],"record_sha256":"51a36e195f138fbe53e77edfd3fd4c052cfd6c53939291d71af8f055c87f1534","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}