{"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/47","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":47,"pages_in_order":142,"rows_per_page":100,"rows":[4601,4700],"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/46","next":"/task/language-modeling/papers/48","papers":[{"url":"/paper/impact-of-representation-matching-with-neural","slug":"impact-of-representation-matching-with-neural","title":"Impact of representation matching with neural machine translation","date":"2022-01-26","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-grapheme-to-phoneme-conversion-with","slug":"neural-grapheme-to-phoneme-conversion-with","title":"Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Models","date":"2022-01-26","arxiv_id":"2201.10716","repositories_listed":1,"syntology":null},{"url":"/paper/bertha-video-captioning-evaluation-via","slug":"bertha-video-captioning-evaluation-via","title":"BERTHA: Video Captioning Evaluation Via Transfer-Learned Human Assessment","date":"2022-01-25","arxiv_id":"2201.10243","repositories_listed":1,"syntology":null},{"url":"/paper/two-heads-are-better-than-one-enhancing","slug":"two-heads-are-better-than-one-enhancing","title":"Multimodal data matters: language model pre-training over structured and unstructured electronic health records","date":"2022-01-25","arxiv_id":"2201.10113","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-study-on-language-models-for-1","slug":"a-comparative-study-on-language-models-for-1","title":"A Comparative Study on Language Models for Task-Oriented Dialogue Systems","date":"2022-01-21","arxiv_id":"2201.08687","repositories_listed":1,"syntology":null},{"url":"/paper/coauthor-designing-a-human-ai-collaborative","slug":"coauthor-designing-a-human-ai-collaborative","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","date":"2022-01-18","arxiv_id":"2201.06796","repositories_listed":1,"syntology":null},{"url":"/paper/korean-specific-dataset-for-table-question","slug":"korean-specific-dataset-for-table-question","title":"Korean-Specific Dataset for Table Question Answering","date":"2022-01-17","arxiv_id":"2201.06223","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-based-paired-variational","slug":"language-model-based-paired-variational","title":"Language Model-Based Paired Variational Autoencoders for Robotic Language Learning","date":"2022-01-17","arxiv_id":"2201.06317","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-programming-in-rank-space-scaling","slug":"dynamic-programming-in-rank-space-scaling","title":"Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs","date":"2022-01-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/valcat-generating-variable-length","slug":"valcat-generating-variable-length","title":"ValCAT: Generating Variable-Length Contextualized Adversarial Transformations using Encoder-Decoder","date":"2022-01-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/eliciting-knowledge-from-pretrained-language","slug":"eliciting-knowledge-from-pretrained-language","title":"Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer","date":"2022-01-14","arxiv_id":"2201.05411","repositories_listed":1,"syntology":null},{"url":"/paper/datasheet-for-the-pile","slug":"datasheet-for-the-pile","title":"Datasheet for the Pile","date":"2022-01-13","arxiv_id":"2201.07311","repositories_listed":1,"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/datasheet-for-the-pile#ran","syntology_url":"https://syntology.ai/paper/2201.07311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.07311"}},"official":{"repos":["EleutherAI/The-Pile"],"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/lp-bert-multi-task-pre-training-knowledge","slug":"lp-bert-multi-task-pre-training-knowledge","title":"Multi-task Pre-training Language Model for Semantic Network Completion","date":"2022-01-13","arxiv_id":"2201.04843","repositories_listed":1,"syntology":null},{"url":"/paper/an-ensemble-approach-to-acronym-extraction","slug":"an-ensemble-approach-to-acronym-extraction","title":"An Ensemble Approach to Acronym Extraction using Transformers","date":"2022-01-09","arxiv_id":"2201.03026","repositories_listed":1,"syntology":null},{"url":"/paper/low-rank-constraints-for-fast-inference-in-1","slug":"low-rank-constraints-for-fast-inference-in-1","title":"Low-Rank Constraints for Fast Inference in Structured Models","date":"2022-01-08","arxiv_id":"2201.02715","repositories_listed":1,"syntology":null},{"url":"/paper/improving-mandarin-end-to-end-speech","slug":"improving-mandarin-end-to-end-speech","title":"Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Model","date":"2022-01-06","arxiv_id":"2201.01995","repositories_listed":1,"syntology":null},{"url":"/paper/event-based-clinical-findings-extraction-from","slug":"event-based-clinical-findings-extraction-from","title":"Event-based clinical findings extraction from radiology reports with pre-trained language model","date":"2021-12-27","arxiv_id":"2112.13512","repositories_listed":1,"syntology":null},{"url":"/paper/visual-semantics-allow-for-textual-reasoning-1","slug":"visual-semantics-allow-for-textual-reasoning-1","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","date":"2021-12-24","arxiv_id":"2112.12916","repositories_listed":1,"syntology":null},{"url":"/paper/atm-an-uncertainty-aware-active-self-training","slug":"atm-an-uncertainty-aware-active-self-training","title":"AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models","date":"2021-12-16","arxiv_id":"2112.08787","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-hierarchical-domain-adaptation-for","slug":"efficient-hierarchical-domain-adaptation-for","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","date":"2021-12-16","arxiv_id":"2112.08786","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-learning-for-speech-1","slug":"self-supervised-learning-for-speech-1","title":"Self-Supervised Learning for speech recognition with Intermediate layer supervision","date":"2021-12-16","arxiv_id":"2112.08778","repositories_listed":1,"syntology":null},{"url":"/paper/unirex-a-unified-learning-framework-for","slug":"unirex-a-unified-learning-framework-for","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","date":"2021-12-16","arxiv_id":"2112.08802","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unirex-a-unified-learning-framework-for#ran","syntology_url":"https://syntology.ai/paper/2112.08802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08802"}},"official":{"repos":["facebookresearch/unirex"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-conversational-recommendation-1","slug":"improving-conversational-recommendation-1","title":"Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta Information","date":"2021-12-15","arxiv_id":"2112.08140","repositories_listed":1,"syntology":null},{"url":"/paper/oracle-linguistic-graphs-complement-a","slug":"oracle-linguistic-graphs-complement-a","title":"Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling","date":"2021-12-15","arxiv_id":"2112.07874","repositories_listed":1,"syntology":null},{"url":"/paper/value-retrieval-with-arbitrary-queries-for","slug":"value-retrieval-with-arbitrary-queries-for","title":"Value Retrieval with Arbitrary Queries for Form-like Documents","date":"2021-12-15","arxiv_id":"2112.07820","repositories_listed":1,"syntology":null},{"url":"/paper/deciphering-antibody-affinity-maturation-with","slug":"deciphering-antibody-affinity-maturation-with","title":"Deciphering antibody affinity maturation with language models and weakly supervised learning","date":"2021-12-14","arxiv_id":"2112.07782","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"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 1 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/deciphering-antibody-affinity-maturation-with#ran","syntology_url":"https://syntology.ai/paper/2112.07782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07782"}},"official":null}},{"url":"/paper/step-unrolled-denoising-autoencoders-for-text-1","slug":"step-unrolled-denoising-autoencoders-for-text-1","title":"Step-unrolled Denoising Autoencoders for Text Generation","date":"2021-12-13","arxiv_id":"2112.06749","repositories_listed":1,"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/step-unrolled-denoising-autoencoders-for-text-1#ran","syntology_url":"https://syntology.ai/paper/2112.06749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.06749"}},"official":null}},{"url":"/paper/magma-multimodal-augmentation-of-generative","slug":"magma-multimodal-augmentation-of-generative","title":"MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning","date":"2021-12-09","arxiv_id":"2112.05253","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/magma-multimodal-augmentation-of-generative#ran","syntology_url":"https://syntology.ai/paper/2112.05253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05253"}},"official":{"repos":["Aleph-Alpha/magma"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/jaber-junior-arabic-bert","slug":"jaber-junior-arabic-bert","title":"JABER and SABER: Junior and Senior Arabic BERt","date":"2021-12-08","arxiv_id":"2112.04329","repositories_listed":1,"syntology":null},{"url":"/paper/mlp-architectures-for-vision-and-language","slug":"mlp-architectures-for-vision-and-language","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","date":"2021-12-08","arxiv_id":"2112.04453","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-recommendation-as-language-modeling","slug":"zero-shot-recommendation-as-language-modeling","title":"Zero-Shot Recommendation as Language Modeling","date":"2021-12-08","arxiv_id":"2112.04184","repositories_listed":1,"syntology":null},{"url":"/paper/achieving-forgetting-prevention-and-knowledge-1","slug":"achieving-forgetting-prevention-and-knowledge-1","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","date":"2021-12-05","arxiv_id":"2112.02706","repositories_listed":1,"syntology":null},{"url":"/paper/causal-distillation-for-language-models","slug":"causal-distillation-for-language-models","title":"Causal Distillation for Language Models","date":"2021-12-05","arxiv_id":"2112.02505","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/causal-distillation-for-language-models#ran","syntology_url":"https://syntology.ai/paper/2112.02505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02505"}},"official":{"repos":["frankaging/Causal-Distill"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dibert-dependency-injected-bidirectional","slug":"dibert-dependency-injected-bidirectional","title":"DIBERT: Dependency Injected Bidirectional Encoder Representations from Transformers","date":"2021-12-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/probing-linguistic-information-for-logical","slug":"probing-linguistic-information-for-logical","title":"Probing Linguistic Information For Logical Inference In Pre-trained Language Models","date":"2021-12-03","arxiv_id":"2112.01753","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/probing-linguistic-information-for-logical#ran","syntology_url":"https://syntology.ai/paper/2112.01753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01753"}},"official":{"repos":["eric11eca/inference-information-probing"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/siamese-bert-based-model-for-web-search","slug":"siamese-bert-based-model-for-web-search","title":"Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset","date":"2021-12-03","arxiv_id":"2112.01810","repositories_listed":1,"syntology":null},{"url":"/paper/dkplm-decomposable-knowledge-enhanced-pre","slug":"dkplm-decomposable-knowledge-enhanced-pre","title":"DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding","date":"2021-12-02","arxiv_id":"2112.01047","repositories_listed":1,"syntology":null},{"url":"/paper/infolm-a-new-metric-to-evaluate-summarization","slug":"infolm-a-new-metric-to-evaluate-summarization","title":"InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation","date":"2021-12-02","arxiv_id":"2112.01589","repositories_listed":1,"syntology":null},{"url":"/paper/pixelated-butterfly-simple-and-efficient-1","slug":"pixelated-butterfly-simple-and-efficient-1","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","date":"2021-11-30","arxiv_id":"2112.00029","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 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; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/pixelated-butterfly-simple-and-efficient-1#ran","syntology_url":"https://syntology.ai/paper/2112.00029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00029"}},"official":{"repos":["HazyResearch/pixelfly"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/a-simple-long-tailed-recognition-baseline-via","slug":"a-simple-long-tailed-recognition-baseline-via","title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","date":"2021-11-29","arxiv_id":"2111.14745","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-image-to-text-generation-for-visual","slug":"zero-shot-image-to-text-generation-for-visual","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","date":"2021-11-29","arxiv_id":"2111.14447","repositories_listed":1,"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/zero-shot-image-to-text-generation-for-visual#ran","syntology_url":"https://syntology.ai/paper/2111.14447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14447"}},"official":{"repos":["yoadtew/zero-shot-image-to-text"],"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/fasttrees-parallel-latent-tree-induction-for","slug":"fasttrees-parallel-latent-tree-induction-for","title":"FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding","date":"2021-11-28","arxiv_id":"2111.14031","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-cross-lingual-transfer-in-legal","slug":"zero-shot-cross-lingual-transfer-in-legal","title":"Zero-Shot Cross-Lingual Transfer in Legal Domain Using Transformer Models","date":"2021-11-28","arxiv_id":"2111.14192","repositories_listed":1,"syntology":null},{"url":"/paper/predict-prevent-and-evaluate-disentangled","slug":"predict-prevent-and-evaluate-disentangled","title":"Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model","date":"2021-11-26","arxiv_id":"2111.13333","repositories_listed":1,"syntology":null},{"url":"/paper/crossing-the-format-boundary-of-text-and","slug":"crossing-the-format-boundary-of-text-and","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","date":"2021-11-23","arxiv_id":"2111.12085","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":5,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/crossing-the-format-boundary-of-text-and#ran","syntology_url":"https://syntology.ai/paper/2111.12085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12085"}},"official":{"repos":["microsoft/UniTAB"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/using-language-model-to-bootstrap-human","slug":"using-language-model-to-bootstrap-human","title":"Using Language Model to Bootstrap Human Activity Recognition Ambient Sensors Based in Smart Homes","date":"2021-11-23","arxiv_id":"2111.12158","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-based-multilingual-language-model-1","slug":"knowledge-based-multilingual-language-model-1","title":"Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples","date":"2021-11-22","arxiv_id":"2111.10962","repositories_listed":1,"syntology":null},{"url":"/paper/robertuito-a-pre-trained-language-model-for","slug":"robertuito-a-pre-trained-language-model-for","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","date":"2021-11-18","arxiv_id":"2111.09453","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/robertuito-a-pre-trained-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2111.09453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09453"}},"official":{"repos":["pysentimiento/robertuito"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/integrated-semantic-and-phonetic-post-1","slug":"integrated-semantic-and-phonetic-post-1","title":"Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition","date":"2021-11-16","arxiv_id":"2111.08400","repositories_listed":1,"syntology":null},{"url":"/paper/meeting-summarization-with-pre-training-and","slug":"meeting-summarization-with-pre-training-and","title":"Meeting Summarization with Pre-training and Clustering Methods","date":"2021-11-16","arxiv_id":"2111.08210","repositories_listed":1,"syntology":null},{"url":"/paper/xlm-e-cross-lingual-language-model-pre-1","slug":"xlm-e-cross-lingual-language-model-pre-1","title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA","date":"2021-11-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/automated-audio-captioning-by-fine-tuning","slug":"automated-audio-captioning-by-fine-tuning","title":"AUTOMATED AUDIO CAPTIONING BY FINE-TUNING BART WITH AUDIOSET TAGS","date":"2021-11-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/machine-in-the-loop-rewriting-for-creative","slug":"machine-in-the-loop-rewriting-for-creative","title":"Machine-in-the-Loop Rewriting for Creative Image Captioning","date":"2021-11-07","arxiv_id":"2111.04193","repositories_listed":1,"syntology":null},{"url":"/paper/nlp-from-scratch-without-large-scale","slug":"nlp-from-scratch-without-large-scale","title":"NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework","date":"2021-11-07","arxiv_id":"2111.04130","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/nlp-from-scratch-without-large-scale#ran","syntology_url":"https://syntology.ai/paper/2111.04130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.04130"}},"official":{"repos":["yaoxingcheng/TLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tip-adapter-training-free-clip-adapter-for","slug":"tip-adapter-training-free-clip-adapter-for","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","date":"2021-11-06","arxiv_id":"2111.03930","repositories_listed":1,"syntology":null},{"url":"/paper/a-model-of-cross-lingual-knowledge-grounded","slug":"a-model-of-cross-lingual-knowledge-grounded","title":"A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systems","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-pilot-study-for-bert-language-modelling-and","slug":"a-pilot-study-for-bert-language-modelling-and","title":"A Pilot Study for BERT Language Modelling and Morphological Analysis for Ancient and Medieval Greek","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/aesop-paraphrase-generation-with-adaptive","slug":"aesop-paraphrase-generation-with-adaptive","title":"AESOP: Paraphrase Generation with Adaptive Syntactic Control","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/arabictransformer-efficient-large-arabic","slug":"arabictransformer-efficient-large-arabic","title":"ArabicTransformer: Efficient Large Arabic Language Model with Funnel Transformer and ELECTRA Objective","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/attentionrank-unsupervised-keyphrase","slug":"attentionrank-unsupervised-keyphrase","title":"AttentionRank: Unsupervised Keyphrase Extraction using Self and Cross Attentions","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/casting-the-same-sentiment-classification","slug":"casting-the-same-sentiment-classification","title":"Casting the Same Sentiment Classification Problem","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/distilling-relation-embeddings-from","slug":"distilling-relation-embeddings-from","title":"Distilling Relation Embeddings from Pretrained Language Models","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/distilling-word-meaning-in-context-from-pre","slug":"distilling-word-meaning-in-context-from-pre","title":"Distilling Word Meaning in Context from Pre-trained Language Models","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/effective-use-of-graph-convolution-network-1","slug":"effective-use-of-graph-convolution-network-1","title":"Effective Use of Graph Convolution Network and Contextual Sub-Tree for Commodity News Event Extraction","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-multitask-learning-for-low-resource-1","slug":"exploring-multitask-learning-for-low-resource-1","title":"Exploring Multitask Learning for Low-Resource Abstractive Summarization","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hyperparameter-power-impact-in-transformer","slug":"hyperparameter-power-impact-in-transformer","title":"Hyperparameter Power Impact in Transformer Language Model Training","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/it-doesnt-look-good-for-a-date-transforming","slug":"it-doesnt-look-good-for-a-date-transforming","title":"“It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/klmo-knowledge-graph-enhanced-pretrained","slug":"klmo-knowledge-graph-enhanced-pretrained","title":"KLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationships","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-pretrain-a-strong-siamese","slug":"less-is-more-pretrain-a-strong-siamese","title":"Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/prosper-probing-human-and-neural-network","slug":"prosper-probing-human-and-neural-network","title":"ProSPer: Probing Human and Neural Network Language Model Understanding of Spatial Perspective","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/scaffolded-input-promotes-atomic-organization","slug":"scaffolded-input-promotes-atomic-organization","title":"Scaffolded input promotes atomic organization in the recurrent neural network language model","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/small-data-no-problem-exploring-the-viability","slug":"small-data-no-problem-exploring-the-viability","title":"Small Data? No Problem! Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stacked-amr-parsing-with-silver-data","slug":"stacked-amr-parsing-with-silver-data","title":"Stacked AMR Parsing with Silver Data","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-world-of-an-octopus-how-reporting-bias-1","slug":"the-world-of-an-octopus-how-reporting-bias-1","title":"The World of an Octopus: How Reporting Bias Influences a Language Model’s Perception of Color","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-with-shallow-decoders-bsc","slug":"transfer-learning-with-shallow-decoders-bsc","title":"Transfer Learning with Shallow Decoders: BSC at WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tsdae-using-transformer-based-sequential-1","slug":"tsdae-using-transformer-based-sequential-1","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/whos-on-first-probing-the-learning-and","slug":"whos-on-first-probing-the-learning-and","title":"Who’s on First?: Probing the Learning and Representation Capabilities of Language Models on Deterministic Closed Domains","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/with-a-little-help-from-my-temporal-context","slug":"with-a-little-help-from-my-temporal-context","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","date":"2021-11-01","arxiv_id":"2111.01024","repositories_listed":1,"syntology":null},{"url":"/paper/top1-solution-of-qq-browser-2021-ai-algorithm","slug":"top1-solution-of-qq-browser-2021-ai-algorithm","title":"Top1 Solution of QQ Browser 2021 Ai Algorithm Competition Track 1 : Multimodal Video Similarity","date":"2021-10-30","arxiv_id":"2111.01677","repositories_listed":1,"syntology":null},{"url":"/paper/scatterbrain-unifying-sparse-and-low-rank","slug":"scatterbrain-unifying-sparse-and-low-rank","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","date":"2021-10-28","arxiv_id":"2110.15343","repositories_listed":1,"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/scatterbrain-unifying-sparse-and-low-rank#ran","syntology_url":"https://syntology.ai/paper/2110.15343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15343"}},"official":{"repos":["hazyresearch/scatterbrain"],"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/semi-siamese-bi-encoder-neural-ranking-model","slug":"semi-siamese-bi-encoder-neural-ranking-model","title":"Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning","date":"2021-10-28","arxiv_id":"2110.14943","repositories_listed":1,"syntology":null},{"url":"/paper/ufal-at-multilexnorm-2021-improving","slug":"ufal-at-multilexnorm-2021-improving","title":"ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5","date":"2021-10-28","arxiv_id":"2110.15248","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-non-monotonic-autoregressive","slug":"discovering-non-monotonic-autoregressive","title":"Discovering Non-monotonic Autoregressive Orderings with Variational Inference","date":"2021-10-27","arxiv_id":"2110.15797","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/discovering-non-monotonic-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2110.15797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15797"}},"official":{"repos":["xuanlinli17/autoregressive_inference"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/mutformer-a-context-dependent-transformer","slug":"mutformer-a-context-dependent-transformer","title":"Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins","date":"2021-10-27","arxiv_id":"2110.14746","repositories_listed":1,"syntology":null},{"url":"/paper/avocado-strategy-for-adapting-vocabulary-to","slug":"avocado-strategy-for-adapting-vocabulary-to","title":"AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain","date":"2021-10-26","arxiv_id":"2110.13434","repositories_listed":1,"syntology":null},{"url":"/paper/spanish-legalese-language-model-and-corpora","slug":"spanish-legalese-language-model-and-corpora","title":"Spanish Legalese Language Model and Corpora","date":"2021-10-23","arxiv_id":"2110.12201","repositories_listed":1,"syntology":null},{"url":"/paper/climatebert-a-pretrained-language-model-for","slug":"climatebert-a-pretrained-language-model-for","title":"ClimateBert: A Pretrained Language Model for Climate-Related Text","date":"2021-10-22","arxiv_id":"2110.12010","repositories_listed":1,"syntology":null},{"url":"/paper/text-counterfactuals-via-latent-optimization","slug":"text-counterfactuals-via-latent-optimization","title":"Text Counterfactuals via Latent Optimization and Shapley-Guided Search","date":"2021-10-22","arxiv_id":"2110.11589","repositories_listed":1,"syntology":null},{"url":"/paper/improved-multilingual-language-model","slug":"improved-multilingual-language-model","title":"Improved Multilingual Language Model Pretraining for Social Media Text via Translation Pair Prediction","date":"2021-10-20","arxiv_id":"2110.10318","repositories_listed":1,"syntology":null},{"url":"/paper/javabert-training-a-transformer-based-model","slug":"javabert-training-a-transformer-based-model","title":"JavaBERT: Training a transformer-based model for the Java programming language","date":"2021-10-20","arxiv_id":"2110.10404","repositories_listed":1,"syntology":null},{"url":"/paper/lmsoc-an-approach-for-socially-sensitive","slug":"lmsoc-an-approach-for-socially-sensitive","title":"LMSOC: An Approach for Socially Sensitive Pretraining","date":"2021-10-20","arxiv_id":"2110.10319","repositories_listed":1,"syntology":null},{"url":"/paper/normformer-improved-transformer-pretraining-1","slug":"normformer-improved-transformer-pretraining-1","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","date":"2021-10-18","arxiv_id":"2110.09456","repositories_listed":1,"syntology":null},{"url":"/paper/training-deep-neural-networks-with-adaptive","slug":"training-deep-neural-networks-with-adaptive","title":"Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization","date":"2021-10-18","arxiv_id":"2110.09057","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":3,"n_no_contract":3,"n_pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 3 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/training-deep-neural-networks-with-adaptive#ran","syntology_url":"https://syntology.ai/paper/2110.09057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09057"}},"official":{"repos":["kentaroy47/vision-transformers-cifar10"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/gnn-lm-language-modeling-based-on-global-1","slug":"gnn-lm-language-modeling-based-on-global-1","title":"GNN-LM: Language Modeling based on Global Contexts via GNN","date":"2021-10-17","arxiv_id":"2110.08743","repositories_listed":1,"syntology":null},{"url":"/paper/a-good-prompt-is-worth-millions-of-parameters","slug":"a-good-prompt-is-worth-millions-of-parameters","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","date":"2021-10-16","arxiv_id":"2110.08484","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-metric-for-evaluating-semantics-1","slug":"a-novel-metric-for-evaluating-semantics-1","title":"A Novel Metric for Evaluating Semantics Preservation","date":"2021-10-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hrkd-hierarchical-relational-knowledge","slug":"hrkd-hierarchical-relational-knowledge","title":"HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression","date":"2021-10-16","arxiv_id":"2110.08551","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/hrkd-hierarchical-relational-knowledge#ran","syntology_url":"https://syntology.ai/paper/2110.08551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08551"}},"official":{"repos":["cheneydon/hrkd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hydra-a-system-for-large-multi-model-deep","slug":"hydra-a-system-for-large-multi-model-deep","title":"Hydra: A System for Large Multi-Model Deep Learning","date":"2021-10-16","arxiv_id":"2110.08633","repositories_listed":1,"syntology":null},{"url":"/paper/invariant-language-modeling","slug":"invariant-language-modeling","title":"Invariant Language Modeling","date":"2021-10-16","arxiv_id":"2110.08413","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-unsupervised-sequence","slug":"multilingual-unsupervised-sequence","title":"Multilingual unsupervised sequence segmentation transfers to extremely low-resource languages","date":"2021-10-16","arxiv_id":"2110.08415","repositories_listed":1,"syntology":null}],"record_sha256":"956e072e13dd2d812b33e8e10a4800a542047401134aadfb7f2dcab94284a2fe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}