{"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/65","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":65,"pages_in_order":177,"rows_per_page":100,"rows":[6401,6500],"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/64","next":"/task/language-modelling/papers/66","papers":[{"url":"/paper/contrastive-distillation-on-intermediate","slug":"contrastive-distillation-on-intermediate","title":"Contrastive Distillation on Intermediate Representations for Language Model Compression","date":"2020-09-29","arxiv_id":"2009.14167","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/contrastive-distillation-on-intermediate#ran","syntology_url":"https://syntology.ai/paper/2009.14167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14167"}},"official":{"repos":["intersun/CoDIR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/grappa-grammar-augmented-pre-training-for","slug":"grappa-grammar-augmented-pre-training-for","title":"GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing","date":"2020-09-29","arxiv_id":"2009.13845","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 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; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/grappa-grammar-augmented-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2009.13845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13845"}},"official":null}},{"url":"/paper/improving-low-compute-language-modeling-with","slug":"improving-low-compute-language-modeling-with","title":"Improving Low Compute Language Modeling with In-Domain Embedding Initialisation","date":"2020-09-29","arxiv_id":"2009.14109","repositories_listed":1,"syntology":null},{"url":"/paper/deep-transformers-with-latent-depth","slug":"deep-transformers-with-latent-depth","title":"Deep Transformers with Latent Depth","date":"2020-09-28","arxiv_id":"2009.13102","repositories_listed":1,"syntology":null},{"url":"/paper/hetseq-distributed-gpu-training-on","slug":"hetseq-distributed-gpu-training-on","title":"HetSeq: Distributed GPU Training on Heterogeneous Infrastructure","date":"2020-09-25","arxiv_id":"2009.14783","repositories_listed":1,"syntology":null},{"url":"/paper/visually-grounded-compound-pcfgs","slug":"visually-grounded-compound-pcfgs","title":"Visually Grounded Compound PCFGs","date":"2020-09-25","arxiv_id":"2009.12404","repositories_listed":1,"syntology":null},{"url":"/paper/anchibert-a-pre-trained-model-for-ancient","slug":"anchibert-a-pre-trained-model-for-ancient","title":"AnchiBERT: A Pre-Trained Model for Ancient ChineseLanguage Understanding and Generation","date":"2020-09-24","arxiv_id":"2009.11473","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-compositional-outputs-for-adaptive","slug":"grounded-compositional-outputs-for-adaptive","title":"Grounded Compositional Outputs for Adaptive Language Modeling","date":"2020-09-24","arxiv_id":"2009.11523","repositories_listed":1,"syntology":null},{"url":"/paper/toward-a-thermodynamics-of-meaning","slug":"toward-a-thermodynamics-of-meaning","title":"Toward a Thermodynamics of Meaning","date":"2020-09-24","arxiv_id":"2009.11963","repositories_listed":1,"syntology":null},{"url":"/paper/content-planning-for-neural-story-generation","slug":"content-planning-for-neural-story-generation","title":"Content Planning for Neural Story Generation with Aristotelian Rescoring","date":"2020-09-21","arxiv_id":"2009.09870","repositories_listed":1,"syntology":null},{"url":"/paper/latin-bert-a-contextual-language-model-for","slug":"latin-bert-a-contextual-language-model-for","title":"Latin BERT: A Contextual Language Model for Classical Philology","date":"2020-09-21","arxiv_id":"2009.10053","repositories_listed":1,"syntology":null},{"url":"/paper/dual-path-cnn-with-max-gated-block-for-text","slug":"dual-path-cnn-with-max-gated-block-for-text","title":"Dual-path CNN with Max Gated block for Text-Based Person Re-identification","date":"2020-09-20","arxiv_id":"2009.09343","repositories_listed":1,"syntology":null},{"url":"/paper/inductive-learning-on-commonsense-knowledge","slug":"inductive-learning-on-commonsense-knowledge","title":"Inductive Learning on Commonsense Knowledge Graph Completion","date":"2020-09-19","arxiv_id":"2009.09263","repositories_listed":1,"syntology":null},{"url":"/paper/comet-a-neural-framework-for-mt-evaluation","slug":"comet-a-neural-framework-for-mt-evaluation","title":"COMET: A Neural Framework for MT Evaluation","date":"2020-09-18","arxiv_id":"2009.09025","repositories_listed":1,"syntology":null},{"url":"/paper/the-birth-of-romanian-bert","slug":"the-birth-of-romanian-bert","title":"The birth of Romanian BERT","date":"2020-09-18","arxiv_id":"2009.08712","repositories_listed":1,"syntology":null},{"url":"/paper/dsc-iit-ism-at-semeval-2020-task-6-boosting","slug":"dsc-iit-ism-at-semeval-2020-task-6-boosting","title":"DSC IIT-ISM at SemEval-2020 Task 6: Boosting BERT with Dependencies for Definition Extraction","date":"2020-09-17","arxiv_id":"2009.08180","repositories_listed":1,"syntology":null},{"url":"/paper/generating-label-cohesive-and-well-formed","slug":"generating-label-cohesive-and-well-formed","title":"Generating Label Cohesive and Well-Formed Adversarial Claims","date":"2020-09-17","arxiv_id":"2009.08205","repositories_listed":1,"syntology":null},{"url":"/paper/graphcodebert-pre-training-code","slug":"graphcodebert-pre-training-code","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","date":"2020-09-17","arxiv_id":"2009.08366","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-meta-learning-for-few-shot","slug":"self-supervised-meta-learning-for-few-shot","title":"Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks","date":"2020-09-17","arxiv_id":"2009.08445","repositories_listed":1,"syntology":null},{"url":"/paper/automated-source-code-generation-and-auto","slug":"automated-source-code-generation-and-auto","title":"Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches","date":"2020-09-16","arxiv_id":"2009.07740","repositories_listed":1,"syntology":null},{"url":"/paper/contextualized-perturbation-for-textual","slug":"contextualized-perturbation-for-textual","title":"Contextualized Perturbation for Textual Adversarial Attack","date":"2020-09-16","arxiv_id":"2009.07502","repositories_listed":1,"syntology":null},{"url":"/paper/reusing-a-pretrained-language-model-on","slug":"reusing-a-pretrained-language-model-on","title":"Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT","date":"2020-09-16","arxiv_id":"2009.07610","repositories_listed":1,"syntology":null},{"url":"/paper/improving-indonesian-text-classification","slug":"improving-indonesian-text-classification","title":"Improving Indonesian Text Classification Using Multilingual Language Model","date":"2020-09-12","arxiv_id":"2009.05713","repositories_listed":1,"syntology":null},{"url":"/paper/task-specific-objectives-of-pre-trained","slug":"task-specific-objectives-of-pre-trained","title":"Dialogue-adaptive Language Model Pre-training From Quality Estimation","date":"2020-09-10","arxiv_id":"2009.04984","repositories_listed":1,"syntology":null},{"url":"/paper/walk-extraction-strategies-for-node","slug":"walk-extraction-strategies-for-node","title":"Walk Extraction Strategies for Node Embeddings with RDF2Vec in Knowledge Graphs","date":"2020-09-09","arxiv_id":"2009.04404","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-lstm-networks-for-semi-supervised-1","slug":"revisiting-lstm-networks-for-semi-supervised-1","title":"Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function","date":"2020-09-08","arxiv_id":"2009.04007","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":3,"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/revisiting-lstm-networks-for-semi-supervised-1#ran","syntology_url":"https://syntology.ai/paper/2009.04007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.04007"}},"official":null}},{"url":"/paper/improving-language-generation-with-sentence","slug":"improving-language-generation-with-sentence","title":"Improving Language Generation with Sentence Coherence Objective","date":"2020-09-07","arxiv_id":"2009.06358","repositories_listed":1,"syntology":null},{"url":"/paper/biological-structure-and-function-emerge-from","slug":"biological-structure-and-function-emerge-from","title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","date":"2020-08-31","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/data-augmentation-using-prosody-and-false","slug":"data-augmentation-using-prosody-and-false","title":"Data augmentation using prosody and false starts to recognize non-native children's speech","date":"2020-08-29","arxiv_id":"2008.12914","repositories_listed":1,"syntology":null},{"url":"/paper/ethan-at-semeval-2020-task-5-modelling-causal","slug":"ethan-at-semeval-2020-task-5-modelling-causal","title":"ETHAN at SemEval-2020 Task 5: Modelling Causal Reasoning inLanguage using neuro-symbolic cloud computing","date":"2020-08-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/greek-bert-the-greeks-visiting-sesame-street","slug":"greek-bert-the-greeks-visiting-sesame-street","title":"GREEK-BERT: The Greeks visiting Sesame Street","date":"2020-08-27","arxiv_id":"2008.12014","repositories_listed":1,"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":1,"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/greek-bert-the-greeks-visiting-sesame-street#ran","syntology_url":"https://syntology.ai/paper/2008.12014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.12014"}},"official":{"repos":["nlpaueb/greek-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/language-models-and-word-sense-disambiguation","slug":"language-models-and-word-sense-disambiguation","title":"Analysis and Evaluation of Language Models for Word Sense Disambiguation","date":"2020-08-26","arxiv_id":"2008.11608","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-evaluate-your-dialogue-system-probe","slug":"how-to-evaluate-your-dialogue-system-probe","title":"How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics","date":"2020-08-24","arxiv_id":"2008.10427","repositories_listed":1,"syntology":null},{"url":"/paper/kr-bert-a-small-scale-korean-specific","slug":"kr-bert-a-small-scale-korean-specific","title":"KR-BERT: A Small-Scale Korean-Specific Language Model","date":"2020-08-10","arxiv_id":"2008.03979","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-the-knowledge-of-bert-for-sequence","slug":"distilling-the-knowledge-of-bert-for-sequence","title":"Distilling the Knowledge of BERT for Sequence-to-Sequence ASR","date":"2020-08-09","arxiv_id":"2008.03822","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-generate-grounded-visual-captions","slug":"learning-to-generate-grounded-visual-captions","title":"Learning to Generate Grounded Visual Captions without Localization Supervision","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-ner-s-performance-with-massive","slug":"improving-ner-s-performance-with-massive","title":"Improving NER's Performance with Massive financial corpus","date":"2020-07-31","arxiv_id":"2007.15871","repositories_listed":1,"syntology":null},{"url":"/paper/language-modelling-for-source-code-with","slug":"language-modelling-for-source-code-with","title":"Language Modelling for Source Code with Transformer-XL","date":"2020-07-31","arxiv_id":"2007.15813","repositories_listed":1,"syntology":null},{"url":"/paper/tweepfake-about-detecting-deepfake-tweets","slug":"tweepfake-about-detecting-deepfake-tweets","title":"TweepFake: about Detecting Deepfake Tweets","date":"2020-07-31","arxiv_id":"2008.00036","repositories_listed":1,"syntology":null},{"url":"/paper/neuralqa-a-usable-library-for-question","slug":"neuralqa-a-usable-library-for-question","title":"NeuralQA: A Usable Library for Question Answering (Contextual Query Expansion + BERT) on Large Datasets","date":"2020-07-30","arxiv_id":"2007.15211","repositories_listed":1,"syntology":null},{"url":"/paper/what-does-bert-know-about-books-movies-and","slug":"what-does-bert-know-about-books-movies-and","title":"What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation","date":"2020-07-30","arxiv_id":"2007.15356","repositories_listed":1,"syntology":null},{"url":"/paper/composer-style-classification-of-piano-sheet","slug":"composer-style-classification-of-piano-sheet","title":"Composer Style Classification of Piano Sheet Music Images Using Language Model Pretraining","date":"2020-07-29","arxiv_id":"2007.14587","repositories_listed":1,"syntology":null},{"url":"/paper/text-based-classification-of-interviews-for","slug":"text-based-classification-of-interviews-for","title":"Text-based classification of interviews for mental health -- juxtaposing the state of the art","date":"2020-07-29","arxiv_id":"2008.01543","repositories_listed":1,"syntology":null},{"url":"/paper/public-sentiment-toward-solar-energy-opinion","slug":"public-sentiment-toward-solar-energy-opinion","title":"Public Sentiment Toward Solar Energy: Opinion Mining of Twitter Using a Transformer-Based Language Model","date":"2020-07-27","arxiv_id":"2007.13306","repositories_listed":1,"syntology":null},{"url":"/paper/fissa-at-semeval-2020-task-9-fine-tuned-for","slug":"fissa-at-semeval-2020-task-9-fine-tuned-for","title":"FiSSA at SemEval-2020 Task 9: Fine-tuned For Feelings","date":"2020-07-24","arxiv_id":"2007.12544","repositories_listed":1,"syntology":null},{"url":"/paper/ir-bert-leveraging-bert-for-semantic-search","slug":"ir-bert-leveraging-bert-for-semantic-search","title":"IR-BERT: Leveraging BERT for Semantic Search in Background Linking for News Articles","date":"2020-07-24","arxiv_id":"2007.12603","repositories_listed":1,"syntology":null},{"url":"/paper/online-spatio-temporal-learning-in-deep","slug":"online-spatio-temporal-learning-in-deep","title":"Online Spatio-Temporal Learning in Deep Neural Networks","date":"2020-07-24","arxiv_id":"2007.12723","repositories_listed":1,"syntology":null},{"url":"/paper/newssweeper-at-semeval-2020-task-11-context","slug":"newssweeper-at-semeval-2020-task-11-context","title":"newsSweeper at SemEval-2020 Task 11: Context-Aware Rich Feature Representations For Propaganda Classification","date":"2020-07-21","arxiv_id":"2007.10827","repositories_listed":1,"syntology":null},{"url":"/paper/mono-vs-multilingual-transformer-based-models","slug":"mono-vs-multilingual-transformer-based-models","title":"Mono vs Multilingual Transformer-based Models: a Comparison across Several Language Tasks","date":"2020-07-19","arxiv_id":"2007.09757","repositories_listed":1,"syntology":null},{"url":"/paper/one-shot-learning-for-language-modelling","slug":"one-shot-learning-for-language-modelling","title":"One-Shot Learning for Language Modelling","date":"2020-07-19","arxiv_id":"2007.09679","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-generalization-in-semantic","slug":"compositional-generalization-in-semantic","title":"Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures","date":"2020-07-17","arxiv_id":"2007.08970","repositories_listed":1,"syntology":null},{"url":"/paper/do-you-have-the-right-scissors-tailoring-pre-1","slug":"do-you-have-the-right-scissors-tailoring-pre-1","title":"Do You Have the Right Scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods","date":"2020-07-13","arxiv_id":"2007.06162","repositories_listed":1,"syntology":null},{"url":"/paper/generative-graph-perturbations-for-scene","slug":"generative-graph-perturbations-for-scene","title":"Generative Compositional Augmentations for Scene Graph Prediction","date":"2020-07-11","arxiv_id":"2007.05756","repositories_listed":1,"syntology":null},{"url":"/paper/multi-dialect-arabic-bert-for-country-level","slug":"multi-dialect-arabic-bert-for-country-level","title":"Multi-Dialect Arabic BERT for Country-Level Dialect Identification","date":"2020-07-10","arxiv_id":"2007.05612","repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-word-embeddings-for-goal","slug":"pre-trained-word-embeddings-for-goal","title":"Pre-trained Word Embeddings for Goal-conditional Transfer Learning in Reinforcement Learning","date":"2020-07-10","arxiv_id":"2007.05196","repositories_listed":1,"syntology":null},{"url":"/paper/do-transformers-need-deep-long-range-memory-1","slug":"do-transformers-need-deep-long-range-memory-1","title":"Do Transformers Need Deep Long-Range Memory","date":"2020-07-07","arxiv_id":"2007.03356","repositories_listed":1,"syntology":null},{"url":"/paper/emotiongif-yankee-a-sentiment-classifier-with","slug":"emotiongif-yankee-a-sentiment-classifier-with","title":"EmotionGIF-Yankee: A Sentiment Classifier with Robust Model Based Ensemble Methods","date":"2020-07-05","arxiv_id":"2007.02259","repositories_listed":1,"syntology":null},{"url":"/paper/data-movement-is-all-you-need-a-case-study-of","slug":"data-movement-is-all-you-need-a-case-study-of","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","date":"2020-06-30","arxiv_id":"2007.00072","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/data-movement-is-all-you-need-a-case-study-of#ran","syntology_url":"https://syntology.ai/paper/2007.00072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00072"}},"official":{"repos":["spcl/substation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-combine-top-down-and-bottom-up","slug":"learning-to-combine-top-down-and-bottom-up","title":"Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules","date":"2020-06-30","arxiv_id":"2006.16981","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/learning-to-combine-top-down-and-bottom-up#ran","syntology_url":"https://syntology.ai/paper/2006.16981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16981"}},"official":{"repos":["sarthmit/BRIMs"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-sparse-prototypes-for-text","slug":"learning-sparse-prototypes-for-text","title":"Learning Sparse Prototypes for Text Generation","date":"2020-06-29","arxiv_id":"2006.16336","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":3,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-sparse-prototypes-for-text#ran","syntology_url":"https://syntology.ai/paper/2006.16336","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16336"}},"official":{"repos":["jxhe/sparse-text-prototype"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":3,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bond-bert-assisted-open-domain-named-entity","slug":"bond-bert-assisted-open-domain-named-entity","title":"BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision","date":"2020-06-28","arxiv_id":"2006.15509","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/bond-bert-assisted-open-domain-named-entity#ran","syntology_url":"https://syntology.ai/paper/2006.15509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.15509"}},"official":{"repos":["cliang1453/BOND"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-handwritten-chinese-text-recognition","slug":"offline-handwritten-chinese-text-recognition","title":"Offline Handwritten Chinese Text Recognition with Convolutional Neural Networks","date":"2020-06-28","arxiv_id":"2006.15619","repositories_listed":1,"syntology":null},{"url":"/paper/lsbert-a-simple-framework-for-lexical","slug":"lsbert-a-simple-framework-for-lexical","title":"LSBert: A Simple Framework for Lexical Simplification","date":"2020-06-25","arxiv_id":"2006.14939","repositories_listed":1,"syntology":null},{"url":"/paper/lipschitz-recurrent-neural-networks","slug":"lipschitz-recurrent-neural-networks","title":"Lipschitz Recurrent Neural Networks","date":"2020-06-22","arxiv_id":"2006.12070","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/lipschitz-recurrent-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2006.12070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12070"}},"official":{"repos":["erichson/LipschitzRNN"],"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/memory-transformer","slug":"memory-transformer","title":"Memory Transformer","date":"2020-06-20","arxiv_id":"2006.11527","repositories_listed":1,"syntology":null},{"url":"/paper/a-qualitative-evaluation-of-language-models","slug":"a-qualitative-evaluation-of-language-models","title":"A Qualitative Evaluation of Language Models on Automatic Question-Answering for COVID-19","date":"2020-06-19","arxiv_id":"2006.10964","repositories_listed":1,"syntology":null},{"url":"/paper/differentiable-language-model-adversarial","slug":"differentiable-language-model-adversarial","title":"Differentiable Language Model Adversarial Attacks on Categorical Sequence Classifiers","date":"2020-06-19","arxiv_id":"2006.11078","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-and-discourse-topic-aware-neural","slug":"explainable-and-discourse-topic-aware-neural","title":"Explainable and Discourse Topic-aware Neural Language Understanding","date":"2020-06-18","arxiv_id":"2006.10632","repositories_listed":1,"syntology":null},{"url":"/paper/i-bert-inductive-generalization-of","slug":"i-bert-inductive-generalization-of","title":"I-BERT: Inductive Generalization of Transformer to Arbitrary Context Lengths","date":"2020-06-18","arxiv_id":"2006.10220","repositories_listed":1,"syntology":null},{"url":"/paper/video-moment-localization-using-object","slug":"video-moment-localization-using-object","title":"Video Moment Localization using Object Evidence and Reverse Captioning","date":"2020-06-18","arxiv_id":"2006.10260","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-for-weakly-supervised","slug":"contrastive-learning-for-weakly-supervised","title":"Contrastive Learning for Weakly Supervised Phrase Grounding","date":"2020-06-17","arxiv_id":"2006.09920","repositories_listed":1,"syntology":null},{"url":"/paper/tagging-and-parsing-of-multidomain","slug":"tagging-and-parsing-of-multidomain","title":"Tagging and parsing of multidomain collections","date":"2020-06-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/algebranets","slug":"algebranets","title":"AlgebraNets","date":"2020-06-12","arxiv_id":"2006.07360","repositories_listed":1,"syntology":null},{"url":"/paper/memesem-a-multi-modal-framework-for","slug":"memesem-a-multi-modal-framework-for","title":"MemeSem:A Multi-modal Framework for Sentimental Analysis of Meme via Transfer Learning","date":"2020-06-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nas-bench-nlp-neural-architecture-search","slug":"nas-bench-nlp-neural-architecture-search","title":"NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing","date":"2020-06-12","arxiv_id":"2006.07116","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/nas-bench-nlp-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/2006.07116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07116"}},"official":{"repos":["fmsnew/nas-bench-nlp-release"],"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/demystifying-self-supervised-learning-an","slug":"demystifying-self-supervised-learning-an","title":"Self-supervised Learning from a Multi-view Perspective","date":"2020-06-10","arxiv_id":"2006.05576","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"11 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/demystifying-self-supervised-learning-an#ran","syntology_url":"https://syntology.ai/paper/2006.05576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.05576"}},"official":{"repos":["yaohungt/Demystifying_Self_Supervised_Learning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mc-bert-efficient-language-pre-training-via-a","slug":"mc-bert-efficient-language-pre-training-via-a","title":"MC-BERT: Efficient Language Pre-Training via a Meta Controller","date":"2020-06-10","arxiv_id":"2006.05744","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/mc-bert-efficient-language-pre-training-via-a#ran","syntology_url":"https://syntology.ai/paper/2006.05744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.05744"}},"official":{"repos":["MC-BERT/MC-BERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/misinformation-has-high-perplexity","slug":"misinformation-has-high-perplexity","title":"Misinformation Has High Perplexity","date":"2020-06-08","arxiv_id":"2006.04666","repositories_listed":1,"syntology":null},{"url":"/paper/bert-loses-patience-fast-and-robust-inference","slug":"bert-loses-patience-fast-and-robust-inference","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","date":"2020-06-07","arxiv_id":"2006.04152","repositories_listed":1,"syntology":null},{"url":"/paper/gmat-global-memory-augmentation-for","slug":"gmat-global-memory-augmentation-for","title":"GMAT: Global Memory Augmentation for Transformers","date":"2020-06-05","arxiv_id":"2006.03274","repositories_listed":1,"syntology":null},{"url":"/paper/masked-language-modeling-for-proteins-via","slug":"masked-language-modeling-for-proteins-via","title":"Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers","date":"2020-06-05","arxiv_id":"2006.03555","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-cross-translated-diversification","slug":"multi-agent-cross-translated-diversification","title":"Cross-model Back-translated Distillation for Unsupervised Machine Translation","date":"2020-06-03","arxiv_id":"2006.02163","repositories_listed":1,"syntology":null},{"url":"/paper/flaubert-des-mod-eles-de-langue-contextualis","slug":"flaubert-des-mod-eles-de-langue-contextualis","title":"FlauBERT : des mod\\`eles de langue contextualis\\'es pr\\'e-entra\\^\\in\\'es pour le fran\\ccais (FlauBERT : Unsupervised Language Model Pre-training for French)","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-segmentation-for-technical-support","slug":"improving-segmentation-for-technical-support","title":"Improving Segmentation for Technical Support Problems","date":"2020-05-22","arxiv_id":"2005.11055","repositories_listed":1,"syntology":null},{"url":"/paper/l2r2-leveraging-ranking-for-abductive","slug":"l2r2-leveraging-ranking-for-abductive","title":"L2R2: Leveraging Ranking for Abductive Reasoning","date":"2020-05-22","arxiv_id":"2005.11223","repositories_listed":1,"syntology":null},{"url":"/paper/living-machines-a-study-of-atypical-animacy","slug":"living-machines-a-study-of-atypical-animacy","title":"Living Machines: A study of atypical animacy","date":"2020-05-22","arxiv_id":"2005.11140","repositories_listed":1,"syntology":null},{"url":"/paper/comparing-transformers-and-rnns-on-predicting","slug":"comparing-transformers-and-rnns-on-predicting","title":"Human Sentence Processing: Recurrence or Attention?","date":"2020-05-19","arxiv_id":"2005.09471","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-pseudo-labeling-for-speech","slug":"iterative-pseudo-labeling-for-speech","title":"Iterative Pseudo-Labeling for Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09267","repositories_listed":1,"syntology":null},{"url":"/paper/table-search-using-a-deep-contextualized","slug":"table-search-using-a-deep-contextualized","title":"Table Search Using a Deep Contextualized Language Model","date":"2020-05-19","arxiv_id":"2005.09207","repositories_listed":1,"syntology":null},{"url":"/paper/gpt-too-a-language-model-first-approach-for","slug":"gpt-too-a-language-model-first-approach-for","title":"GPT-too: A language-model-first approach for AMR-to-text generation","date":"2020-05-18","arxiv_id":"2005.09123","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-too-a-language-model-first-approach-for#ran","syntology_url":"https://syntology.ai/paper/2005.09123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.09123"}},"official":{"repos":["IBM/GPT-too-AMR2text"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-much-complexity-does-an-rnn-architecture","slug":"how-much-complexity-does-an-rnn-architecture","title":"How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?","date":"2020-05-17","arxiv_id":"2005.08199","repositories_listed":1,"syntology":null},{"url":"/paper/micronet-for-efficient-language-modeling","slug":"micronet-for-efficient-language-modeling","title":"MicroNet for Efficient Language Modeling","date":"2020-05-16","arxiv_id":"2005.07877","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":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) · 2 unverified","sample_list":"/paper/micronet-for-efficient-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2005.07877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.07877"}},"official":{"repos":["mit-han-lab/neurips-micronet"],"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/challenges-in-emotion-style-transfer-an","slug":"challenges-in-emotion-style-transfer-an","title":"Challenges in Emotion Style Transfer: An Exploration with a Lexical Substitution Pipeline","date":"2020-05-15","arxiv_id":"2005.07617","repositories_listed":1,"syntology":null},{"url":"/paper/document-level-event-role-filler-extraction","slug":"document-level-event-role-filler-extraction","title":"Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding","date":"2020-05-13","arxiv_id":"2005.06579","repositories_listed":1,"syntology":null},{"url":"/paper/towards-hate-speech-detection-at-large-via","slug":"towards-hate-speech-detection-at-large-via","title":"Towards Hate Speech Detection at Large via Deep Generative Modeling","date":"2020-05-13","arxiv_id":"2005.06370","repositories_listed":1,"syntology":null},{"url":"/paper/attviz-online-exploration-of-self-attention","slug":"attviz-online-exploration-of-self-attention","title":"AttViz: Online exploration of self-attention for transparent neural language modeling","date":"2020-05-12","arxiv_id":"2005.05716","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-syntactic-structure-for-better","slug":"exploiting-syntactic-structure-for-better","title":"Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach","date":"2020-05-12","arxiv_id":"2005.05864","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/exploiting-syntactic-structure-for-better#ran","syntology_url":"https://syntology.ai/paper/2005.05864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05864"}},"official":{"repos":["wenyudu/SDLM"],"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/soloist-few-shot-task-oriented-dialog-with-a","slug":"soloist-few-shot-task-oriented-dialog-with-a","title":"SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching","date":"2020-05-11","arxiv_id":"2005.05298","repositories_listed":1,"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":0,"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/soloist-few-shot-task-oriented-dialog-with-a#ran","syntology_url":"https://syntology.ai/paper/2005.05298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05298"}},"official":null}},{"url":"/paper/toward-better-storylines-with-sentence-level","slug":"toward-better-storylines-with-sentence-level","title":"Toward Better Storylines with Sentence-Level Language Models","date":"2020-05-11","arxiv_id":"2005.05255","repositories_listed":1,"syntology":null},{"url":"/paper/finding-universal-grammatical-relations-in","slug":"finding-universal-grammatical-relations-in","title":"Finding Universal Grammatical Relations in Multilingual BERT","date":"2020-05-09","arxiv_id":"2005.04511","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/finding-universal-grammatical-relations-in#ran","syntology_url":"https://syntology.ai/paper/2005.04511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.04511"}},"official":{"repos":["ethanachi/multilingual-probing-visualization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"23831ccd6f8cb4bc6ce557cccda571f622e2a872ec527b3ecfffc42d199dd9fc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}