{"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/67","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":67,"pages_in_order":177,"rows_per_page":100,"rows":[6601,6700],"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/66","next":"/task/language-modelling/papers/68","papers":[{"url":"/paper/revisiting-challenges-in-data-to-text-1","slug":"revisiting-challenges-in-data-to-text-1","title":"Revisiting Challenges in Data-to-Text Generation with Fact Grounding","date":"2020-01-12","arxiv_id":"2001.03830","repositories_listed":1,"syntology":null},{"url":"/paper/improving-transformer-optimization-through","slug":"improving-transformer-optimization-through","title":"Improving Transformer Optimization Through Better Initialization","date":"2020-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-transformer-optimization-through-1","slug":"improving-transformer-optimization-through-1","title":"Improving Transformer Optimization Through Better Initialization","date":"2020-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pseudo-masked-language-models-for-unified","slug":"pseudo-masked-language-models-for-unified","title":"Pseudo-Masked Language Models for Unified Language Model Pre-Training","date":"2020-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/encoding-word-order-in-complex-embeddings-1","slug":"encoding-word-order-in-complex-embeddings-1","title":"Encoding word order in complex embeddings","date":"2019-12-27","arxiv_id":"1912.12333","repositories_listed":1,"syntology":null},{"url":"/paper/is-attention-all-what-you-need-an-empirical","slug":"is-attention-all-what-you-need-an-empirical","title":"Is Attention All What You Need? -- An Empirical Investigation on Convolution-Based Active Memory and Self-Attention","date":"2019-12-27","arxiv_id":"1912.11959","repositories_listed":1,"syntology":null},{"url":"/paper/falcon-20-an-entity-and-relation-linking","slug":"falcon-20-an-entity-and-relation-linking","title":"Falcon 2.0: An Entity and Relation Linking Tool over Wikidata","date":"2019-12-24","arxiv_id":"1912.11270","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-hierarchical-topic-guided-neural-1","slug":"recurrent-hierarchical-topic-guided-neural-1","title":"Recurrent Hierarchical Topic-Guided RNN for Language Generation","date":"2019-12-21","arxiv_id":"1912.10337","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-named-entity-recognition-and-1","slug":"end-to-end-named-entity-recognition-and-1","title":"End-to-end Named Entity Recognition and Relation Extraction using Pre-trained Language Models","date":"2019-12-20","arxiv_id":"1912.13415","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-character-embeddings-learning","slug":"hierarchical-character-embeddings-learning","title":"Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin using Recursive Neural Networks","date":"2019-12-20","arxiv_id":"1912.09913","repositories_listed":1,"syntology":null},{"url":"/paper/generating-synthetic-audio-data-for-attention","slug":"generating-synthetic-audio-data-for-attention","title":"Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems","date":"2019-12-19","arxiv_id":"1912.09257","repositories_listed":1,"syntology":null},{"url":"/paper/domain-independent-dominance-of-adaptive-1","slug":"domain-independent-dominance-of-adaptive-1","title":"Domain-independent Dominance of Adaptive Methods","date":"2019-12-04","arxiv_id":"1912.01823","repositories_listed":1,"syntology":null},{"url":"/paper/long-distance-relationships-without-time","slug":"long-distance-relationships-without-time","title":"Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence Modeling","date":"2019-12-02","arxiv_id":"1912.01116","repositories_listed":1,"syntology":null},{"url":"/paper/neural-academic-paper-generation","slug":"neural-academic-paper-generation","title":"Neural Academic Paper Generation","date":"2019-12-02","arxiv_id":"1912.01982","repositories_listed":1,"syntology":null},{"url":"/paper/data-differentiable-architecture","slug":"data-differentiable-architecture","title":"DATA: Differentiable ArchiTecture Approximation","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/memory-efficient-adaptive-optimization","slug":"memory-efficient-adaptive-optimization","title":"Memory Efficient Adaptive Optimization","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-shuffle-exchange-networks-sequence-1","slug":"neural-shuffle-exchange-networks-sequence-1","title":"Neural Shuffle-Exchange Networks - Sequence Processing in O(n log n) Time","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pythia-ai-assisted-code-completion-system","slug":"pythia-ai-assisted-code-completion-system","title":"Pythia: AI-assisted Code Completion System","date":"2019-11-29","arxiv_id":"1912.00742","repositories_listed":1,"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/pythia-ai-assisted-code-completion-system#ran","syntology_url":"https://syntology.ai/paper/1912.00742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00742"}},"official":{"repos":["Microsoft/PTVS"],"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/evaluating-commonsense-in-pre-trained","slug":"evaluating-commonsense-in-pre-trained","title":"Evaluating Commonsense in Pre-trained Language Models","date":"2019-11-27","arxiv_id":"1911.11931","repositories_listed":1,"syntology":null},{"url":"/paper/autoencoding-undirected-molecular-graphs-with","slug":"autoencoding-undirected-molecular-graphs-with","title":"Autoencoding Undirected Molecular Graphs With Neural Networks","date":"2019-11-26","arxiv_id":"2001.03517","repositories_listed":1,"syntology":null},{"url":"/paper/emotional-neural-language-generation-grounded","slug":"emotional-neural-language-generation-grounded","title":"Emotional Neural Language Generation Grounded in Situational Contexts","date":"2019-11-25","arxiv_id":"1911.11161","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-learn-words-from-narrated-video","slug":"learning-to-learn-words-from-narrated-video","title":"Learning to Learn Words from Visual Scenes","date":"2019-11-25","arxiv_id":"1911.11237","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-of-deep-bidirectional-protein","slug":"pre-training-of-deep-bidirectional-protein","title":"Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information","date":"2019-11-25","arxiv_id":"1912.05625","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-the-amount-of-verbatim-copying-in","slug":"controlling-the-amount-of-verbatim-copying-in","title":"Controlling the Amount of Verbatim Copying in Abstractive Summarization","date":"2019-11-23","arxiv_id":"1911.10390","repositories_listed":1,"syntology":null},{"url":"/paper/continual-adaptation-for-efficient-machine","slug":"continual-adaptation-for-efficient-machine","title":"Continual adaptation for efficient machine communication","date":"2019-11-22","arxiv_id":"1911.09896","repositories_listed":1,"syntology":null},{"url":"/paper/red-dragon-ai-at-textgraphs-2019-shared-task-1","slug":"red-dragon-ai-at-textgraphs-2019-shared-task-1","title":"Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation","date":"2019-11-20","arxiv_id":"1911.08976","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-asr-from-supervised-to-semi","slug":"end-to-end-asr-from-supervised-to-semi","title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","date":"2019-11-19","arxiv_id":"1911.08460","repositories_listed":1,"syntology":null},{"url":"/paper/seq-u-net-a-one-dimensional-causal-u-net-for","slug":"seq-u-net-a-one-dimensional-causal-u-net-for","title":"Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling","date":"2019-11-14","arxiv_id":"1911.06393","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/seq-u-net-a-one-dimensional-causal-u-net-for#ran","syntology_url":"https://syntology.ai/paper/1911.06393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06393"}},"official":{"repos":["f90/Seq-U-Net"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/kepler-a-unified-model-for-knowledge","slug":"kepler-a-unified-model-for-knowledge","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","date":"2019-11-13","arxiv_id":"1911.06136","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/kepler-a-unified-model-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/1911.06136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06136"}},"official":{"repos":["THU-KEG/KEPLER"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/smiles-transformer-pre-trained-molecular","slug":"smiles-transformer-pre-trained-molecular","title":"SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery","date":"2019-11-12","arxiv_id":"1911.04738","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/smiles-transformer-pre-trained-molecular#ran","syntology_url":"https://syntology.ai/paper/1911.04738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04738"}},"official":{"repos":["DSPsleeporg/smiles-transformer"],"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/conditionally-learn-to-pay-attention-for","slug":"conditionally-learn-to-pay-attention-for","title":"Conditionally Learn to Pay Attention for Sequential Visual Task","date":"2019-11-11","arxiv_id":"1911.04365","repositories_listed":1,"syntology":null},{"url":"/paper/searching-for-legal-clauses-by-analogy-few","slug":"searching-for-legal-clauses-by-analogy-few","title":"Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines","date":"2019-11-10","arxiv_id":"1911.03911","repositories_listed":1,"syntology":null},{"url":"/paper/bert-is-not-a-knowledge-base-yet-factual","slug":"bert-is-not-a-knowledge-base-yet-factual","title":"E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT","date":"2019-11-09","arxiv_id":"1911.03681","repositories_listed":1,"syntology":null},{"url":"/paper/how-decoding-strategies-affect-the","slug":"how-decoding-strategies-affect-the","title":"How Decoding Strategies Affect the Verifiability of Generated Text","date":"2019-11-09","arxiv_id":"1911.03587","repositories_listed":1,"syntology":null},{"url":"/paper/on-architectures-for-including-visual","slug":"on-architectures-for-including-visual","title":"On Architectures for Including Visual Information in Neural Language Models for Image Description","date":"2019-11-09","arxiv_id":"1911.03738","repositories_listed":1,"syntology":null},{"url":"/paper/not-enough-data-deep-learning-to-the-rescue","slug":"not-enough-data-deep-learning-to-the-rescue","title":"Not Enough Data? Deep Learning to the Rescue!","date":"2019-11-08","arxiv_id":"1911.03118","repositories_listed":1,"syntology":null},{"url":"/paper/blockwise-self-attention-for-long-document","slug":"blockwise-self-attention-for-long-document","title":"Blockwise Self-Attention for Long Document Understanding","date":"2019-11-07","arxiv_id":"1911.02972","repositories_listed":1,"syntology":null},{"url":"/paper/improving-grammatical-error-correction-with","slug":"improving-grammatical-error-correction-with","title":"Improving Grammatical Error Correction with Machine Translation Pairs","date":"2019-11-07","arxiv_id":"1911.02825","repositories_listed":1,"syntology":null},{"url":"/paper/a-programmable-approach-to-model-compression","slug":"a-programmable-approach-to-model-compression","title":"A Programmable Approach to Neural Network Compression","date":"2019-11-06","arxiv_id":"1911.02497","repositories_listed":1,"syntology":null},{"url":"/paper/sentilr-linguistic-knowledge-enhanced","slug":"sentilr-linguistic-knowledge-enhanced","title":"SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge","date":"2019-11-06","arxiv_id":"1911.02493","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-grounding-of-natural-language","slug":"contextual-grounding-of-natural-language","title":"Contextual Grounding of Natural Language Entities in Images","date":"2019-11-05","arxiv_id":"1911.02133","repositories_listed":1,"syntology":null},{"url":"/paper/a-recurrent-bert-based-model-for-question","slug":"a-recurrent-bert-based-model-for-question","title":"A Recurrent BERT-based Model for Question Generation","date":"2019-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/faspell-a-fast-adaptable-simple-powerful","slug":"faspell-a-fast-adaptable-simple-powerful","title":"FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm","date":"2019-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improved-differentiable-architecture-search","slug":"improved-differentiable-architecture-search","title":"Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition","date":"2019-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-customize-language-model-for","slug":"learning-to-customize-language-model-for","title":"Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks","date":"2019-10-31","arxiv_id":"1910.14326","repositories_listed":1,"syntology":null},{"url":"/paper/learning-deterministic-weighted-automata-with","slug":"learning-deterministic-weighted-automata-with","title":"Learning Deterministic Weighted Automata with Queries and Counterexamples","date":"2019-10-30","arxiv_id":"1910.13895","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":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/learning-deterministic-weighted-automata-with#ran","syntology_url":"https://syntology.ai/paper/1910.13895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13895"}},"official":{"repos":["tech-srl/weighted_lstar"],"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/inducing-brain-relevant-bias-in-natural","slug":"inducing-brain-relevant-bias-in-natural","title":"Inducing brain-relevant bias in natural language processing models","date":"2019-10-29","arxiv_id":"1911.03268","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/inducing-brain-relevant-bias-in-natural#ran","syntology_url":"https://syntology.ai/paper/1911.03268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03268"}},"official":{"repos":["danrsc/bert_brain_neurips_2019"],"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/extreme-classification-in-log-memory-using","slug":"extreme-classification-in-log-memory-using","title":"Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products","date":"2019-10-28","arxiv_id":"1910.13830","repositories_listed":1,"syntology":null},{"url":"/paper/thieves-on-sesame-street-model-extraction-of","slug":"thieves-on-sesame-street-model-extraction-of","title":"Thieves on Sesame Street! Model Extraction of BERT-based APIs","date":"2019-10-27","arxiv_id":"1910.12366","repositories_listed":1,"syntology":null},{"url":"/paper/hubert-untangles-bert-to-improve-transfer-1","slug":"hubert-untangles-bert-to-improve-transfer-1","title":"HUBERT Untangles BERT to Improve Transfer across NLP Tasks","date":"2019-10-25","arxiv_id":"1910.12647","repositories_listed":1,"syntology":null},{"url":"/paper/low-resource-sequence-labeling-via","slug":"low-resource-sequence-labeling-via","title":"Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations","date":"2019-10-24","arxiv_id":"1910.10893","repositories_listed":1,"syntology":null},{"url":"/paper/federated-evaluation-of-on-device","slug":"federated-evaluation-of-on-device","title":"Federated Evaluation of On-device Personalization","date":"2019-10-22","arxiv_id":"1910.10252","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-gating-mechanism-of-recurrent-1","slug":"improving-the-gating-mechanism-of-recurrent-1","title":"Improving the Gating Mechanism of Recurrent Neural Networks","date":"2019-10-22","arxiv_id":"1910.09890","repositories_listed":1,"syntology":null},{"url":"/paper/localization-of-fake-news-detection-via","slug":"localization-of-fake-news-detection-via","title":"Localization of Fake News Detection via Multitask Transfer Learning","date":"2019-10-21","arxiv_id":"1910.09295","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-recurrent-neural-networks-with","slug":"enhancing-recurrent-neural-networks-with","title":"Improving Sequence Modeling Ability of Recurrent Neural Networks via Sememes","date":"2019-10-20","arxiv_id":"1910.08910","repositories_listed":1,"syntology":null},{"url":"/paper/follow-alice-into-the-rabbit-hole-giving","slug":"follow-alice-into-the-rabbit-hole-giving","title":"ALOHA: Artificial Learning of Human Attributes for Dialogue Agents","date":"2019-10-18","arxiv_id":"1910.08293","repositories_listed":1,"syntology":null},{"url":"/paper/bertram-improved-word-embeddings-have-big","slug":"bertram-improved-word-embeddings-have-big","title":"BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance","date":"2019-10-16","arxiv_id":"1910.07181","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bertram-improved-word-embeddings-have-big#ran","syntology_url":"https://syntology.ai/paper/1910.07181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07181"}},"official":{"repos":["timoschick/bertram"],"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/deep-independently-recurrent-neural-network","slug":"deep-independently-recurrent-neural-network","title":"Deep Independently Recurrent Neural Network (IndRNN)","date":"2019-10-11","arxiv_id":"1910.06251","repositories_listed":1,"syntology":null},{"url":"/paper/exbert-a-visual-analysis-tool-to-explore","slug":"exbert-a-visual-analysis-tool-to-explore","title":"exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models","date":"2019-10-11","arxiv_id":"1910.05276","repositories_listed":1,"syntology":null},{"url":"/paper/alternating-recurrent-dialog-model-with-large","slug":"alternating-recurrent-dialog-model-with-large","title":"Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models","date":"2019-10-09","arxiv_id":"1910.03756","repositories_listed":1,"syntology":null},{"url":"/paper/is-multilingual-bert-fluent-in-language","slug":"is-multilingual-bert-fluent-in-language","title":"Is Multilingual BERT Fluent in Language Generation?","date":"2019-10-09","arxiv_id":"1910.03806","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-adequacy-of-untuned-warmup-for","slug":"on-the-adequacy-of-untuned-warmup-for","title":"On the adequacy of untuned warmup for adaptive optimization","date":"2019-10-09","arxiv_id":"1910.04209","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/on-the-adequacy-of-untuned-warmup-for#ran","syntology_url":"https://syntology.ai/paper/1910.04209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04209"}},"official":null}},{"url":"/paper/exploiting-structural-and-semantic-context","slug":"exploiting-structural-and-semantic-context","title":"Commonsense Knowledge Base Completion with Structural and Semantic Context","date":"2019-10-07","arxiv_id":"1910.02915","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/exploiting-structural-and-semantic-context#ran","syntology_url":"https://syntology.ai/paper/1910.02915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.02915"}},"official":null}},{"url":"/paper/towards-understanding-of-medical-randomized","slug":"towards-understanding-of-medical-randomized","title":"Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation","date":"2019-10-03","arxiv_id":"1910.01462","repositories_listed":1,"syntology":null},{"url":"/paper/identifying-nuances-in-fake-news-vs-satire","slug":"identifying-nuances-in-fake-news-vs-satire","title":"Identifying Nuances in Fake News vs. Satire: Using Semantic and Linguistic Cues","date":"2019-10-02","arxiv_id":"1910.01160","repositories_listed":1,"syntology":null},{"url":"/paper/190909656","slug":"190909656","title":"Understanding and Robustifying Differentiable Architecture Search","date":"2019-09-20","arxiv_id":"1909.09656","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/190909656#ran","syntology_url":"https://syntology.ai/paper/1909.09656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.09656"}},"official":{"repos":["automl/RobustDARTS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-critical-analysis-of-biased-parsers-in","slug":"a-critical-analysis-of-biased-parsers-in","title":"A Critical Analysis of Biased Parsers in Unsupervised Parsing","date":"2019-09-20","arxiv_id":"1909.09428","repositories_listed":1,"syntology":null},{"url":"/paper/creative-gans-for-generating-poems-lyrics-and","slug":"creative-gans-for-generating-poems-lyrics-and","title":"Creative GANs for generating poems, lyrics, and metaphors","date":"2019-09-20","arxiv_id":"1909.09534","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-architectures-learnt-by-cell","slug":"understanding-architectures-learnt-by-cell","title":"Understanding Architectures Learnt by Cell-based Neural Architecture Search","date":"2019-09-20","arxiv_id":"1909.09569","repositories_listed":1,"syntology":null},{"url":"/paper/allennlp-interpret-a-framework-for-explaining","slug":"allennlp-interpret-a-framework-for-explaining","title":"AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models","date":"2019-09-19","arxiv_id":"1909.09251","repositories_listed":1,"syntology":null},{"url":"/paper/alleviating-sequence-information-loss-with","slug":"alleviating-sequence-information-loss-with","title":"Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes","date":"2019-09-18","arxiv_id":"1909.08700","repositories_listed":1,"syntology":null},{"url":"/paper/enriching-bert-with-knowledge-graph","slug":"enriching-bert-with-knowledge-graph","title":"Enriching BERT with Knowledge Graph Embeddings for Document Classification","date":"2019-09-18","arxiv_id":"1909.08402","repositories_listed":1,"syntology":null},{"url":"/paper/espresso-a-fast-end-to-end-neural-speech","slug":"espresso-a-fast-end-to-end-neural-speech","title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","date":"2019-09-18","arxiv_id":"1909.08723","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":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/espresso-a-fast-end-to-end-neural-speech#ran","syntology_url":"https://syntology.ai/paper/1909.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08723"}},"official":{"repos":["freewym/espresso"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/extracting-evidence-of-supplement-drug","slug":"extracting-evidence-of-supplement-drug","title":"SUPP.AI: Finding Evidence for Supplement-Drug Interactions","date":"2019-09-17","arxiv_id":"1909.08135","repositories_listed":1,"syntology":null},{"url":"/paper/pointer-based-fusion-of-bilingual-lexicons","slug":"pointer-based-fusion-of-bilingual-lexicons","title":"Pointer-based Fusion of Bilingual Lexicons into Neural Machine Translation","date":"2019-09-17","arxiv_id":"1909.07907","repositories_listed":1,"syntology":null},{"url":"/paper/fast-transcription-of-speech-in-low-resource","slug":"fast-transcription-of-speech-in-low-resource","title":"Fast transcription of speech in low-resource languages","date":"2019-09-16","arxiv_id":"1909.07285","repositories_listed":1,"syntology":null},{"url":"/paper/global-autoregressive-models-for-data","slug":"global-autoregressive-models-for-data","title":"Global Autoregressive Models for Data-Efficient Sequence Learning","date":"2019-09-16","arxiv_id":"1909.07063","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-bert-transformation-for-zero","slug":"cross-lingual-bert-transformation-for-zero","title":"Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing","date":"2019-09-15","arxiv_id":"1909.06775","repositories_listed":1,"syntology":null},{"url":"/paper/ouroboros-on-accelerating-training-of","slug":"ouroboros-on-accelerating-training-of","title":"Ouroboros: On Accelerating Training of Transformer-Based Language Models","date":"2019-09-14","arxiv_id":"1909.06695","repositories_listed":1,"syntology":null},{"url":"/paper/learning-dynamic-author-representations-with","slug":"learning-dynamic-author-representations-with","title":"Learning Dynamic Author Representations with Temporal Language Models","date":"2019-09-11","arxiv_id":"1909.04985","repositories_listed":1,"syntology":null},{"url":"/paper/an-evalutation-of-programming-language-models","slug":"an-evalutation-of-programming-language-models","title":"An Evalutation of Programming Language Models' performance on Software Defect Detection","date":"2019-09-10","arxiv_id":"1909.10309","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-embeddings-from-language-models","slug":"multimodal-embeddings-from-language-models","title":"Multimodal Embeddings from Language Models","date":"2019-09-10","arxiv_id":"1909.04302","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-enhanced-contextual-word","slug":"knowledge-enhanced-contextual-word","title":"Knowledge Enhanced Contextual Word Representations","date":"2019-09-09","arxiv_id":"1909.04164","repositories_listed":1,"syntology":null},{"url":"/paper/span-selection-pre-training-for-question","slug":"span-selection-pre-training-for-question","title":"Span Selection Pre-training for Question Answering","date":"2019-09-09","arxiv_id":"1909.04120","repositories_listed":1,"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":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/span-selection-pre-training-for-question#ran","syntology_url":"https://syntology.ai/paper/1909.04120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04120"}},"official":{"repos":["IBM/span-selection-pretraining"],"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/lamal-language-modeling-is-all-you-need-for","slug":"lamal-language-modeling-is-all-you-need-for","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","date":"2019-09-07","arxiv_id":"1909.03329","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lamal-language-modeling-is-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/1909.03329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03329"}},"official":{"repos":["jojotenya/LAMOL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-extractive-and-abstractive-neural-document","slug":"on-extractive-and-abstractive-neural-document","title":"On Extractive and Abstractive Neural Document Summarization with Transformer Language Models","date":"2019-09-07","arxiv_id":"1909.03186","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/on-extractive-and-abstractive-neural-document#ran","syntology_url":"https://syntology.ai/paper/1909.03186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03186"}},"official":null}},{"url":"/paper/improved-patient-classification-with-language","slug":"improved-patient-classification-with-language","title":"Improved Hierarchical Patient Classification with Language Model Pretraining over Clinical Notes","date":"2019-09-06","arxiv_id":"1909.03039","repositories_listed":1,"syntology":null},{"url":"/paper/informing-unsupervised-pretraining-with","slug":"informing-unsupervised-pretraining-with","title":"Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity","date":"2019-09-05","arxiv_id":"1909.02339","repositories_listed":1,"syntology":null},{"url":"/paper/semantics-aware-bert-for-language","slug":"semantics-aware-bert-for-language","title":"Semantics-aware BERT for Language Understanding","date":"2019-09-05","arxiv_id":"1909.02209","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/semantics-aware-bert-for-language#ran","syntology_url":"https://syntology.ai/paper/1909.02209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02209"}},"official":{"repos":["cooelf/SemBERT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/tabfact-a-large-scale-dataset-for-table-based","slug":"tabfact-a-large-scale-dataset-for-table-based","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","date":"2019-09-05","arxiv_id":"1909.02164","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tabfact-a-large-scale-dataset-for-table-based#ran","syntology_url":"https://syntology.ai/paper/1909.02164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02164"}},"official":{"repos":["wenhuchen/Table-Fact-Checking"],"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","unlocated"]}}},{"url":"/paper/distributionally-robust-language-modeling","slug":"distributionally-robust-language-modeling","title":"Distributionally Robust Language Modeling","date":"2019-09-04","arxiv_id":"1909.02060","repositories_listed":1,"syntology":null},{"url":"/paper/palm-a-hybrid-parser-and-language-model","slug":"palm-a-hybrid-parser-and-language-model","title":"PaLM: A Hybrid Parser and Language Model","date":"2019-09-04","arxiv_id":"1909.02134","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-as-knowledge-bases","slug":"language-models-as-knowledge-bases","title":"Language Models as Knowledge Bases?","date":"2019-09-03","arxiv_id":"1909.01066","repositories_listed":1,"syntology":null},{"url":"/paper/neural-linguistic-steganography","slug":"neural-linguistic-steganography","title":"Neural Linguistic Steganography","date":"2019-09-03","arxiv_id":"1909.01496","repositories_listed":1,"syntology":null},{"url":"/paper/the-woman-worked-as-a-babysitter-on-biases-in","slug":"the-woman-worked-as-a-babysitter-on-biases-in","title":"The Woman Worked as a Babysitter: On Biases in Language Generation","date":"2019-09-03","arxiv_id":"1909.01326","repositories_listed":1,"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":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/the-woman-worked-as-a-babysitter-on-biases-in#ran","syntology_url":"https://syntology.ai/paper/1909.01326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01326"}},"official":{"repos":["ewsheng/nlg-bias"],"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/a-surprisingly-effective-fix-for-deep-latent","slug":"a-surprisingly-effective-fix-for-deep-latent","title":"A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text","date":"2019-09-02","arxiv_id":"1909.00868","repositories_listed":1,"syntology":null},{"url":"/paper/commonsense-knowledge-mining-from-pretrained","slug":"commonsense-knowledge-mining-from-pretrained","title":"Commonsense Knowledge Mining from Pretrained Models","date":"2019-09-02","arxiv_id":"1909.00505","repositories_listed":1,"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":3,"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/commonsense-knowledge-mining-from-pretrained#ran","syntology_url":"https://syntology.ai/paper/1909.00505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.00505"}},"official":null}},{"url":"/paper/subword-language-model-for-query-auto","slug":"subword-language-model-for-query-auto","title":"Subword Language Model for Query Auto-Completion","date":"2019-09-02","arxiv_id":"1909.00599","repositories_listed":1,"syntology":null},{"url":"/paper/language-modeling-with-syntactic-and-semantic","slug":"language-modeling-with-syntactic-and-semantic","title":"Language Modeling with Syntactic and Semantic Representation for Sentence Acceptability Predictions","date":"2019-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-of-deep-contextualized","slug":"pre-training-of-deep-contextualized","title":"Global Entity Disambiguation with BERT","date":"2019-09-01","arxiv_id":"1909.00426","repositories_listed":1,"syntology":null}],"record_sha256":"ba3421ffb4059e79e7fd8f655862c838b4698531b94f8142e36ebee483bd3fda","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}