{"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":"/method/bert/papers/68","list_of":"/method/bert","method":"BERT","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":68,"pages_in_order":70,"rows_per_page":100,"rows":[6701,6800],"of":6938,"counts":{"archive_papers_tagged":6938,"with_a_code_link":2862,"where_syntology_ran_a_sample":640,"not_listed_spam_title":0,"listed":6938,"listed_where_code_ran":640,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":520,"every_run_a_failure_of_syntologys_instrument":120,"listed_with_a_run_with_no_instrument_failure":520,"listed_every_run_a_failure_of_syntologys_instrument":120,"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":"/method/bert","prev":"/method/bert/papers/67","next":"/method/bert/papers/69","papers":[{"paper":"/paper/m-bert-injecting-multimodal-information-in","slug":"m-bert-injecting-multimodal-information-in","title":"Integrating Multimodal Information in Large Pretrained Transformers","date":"2019-08-15","arxiv_id":"1908.05787","n_code_links":1,"syntology":null},{"paper":"/paper/towards-making-the-most-of-bert-in-neural","slug":"towards-making-the-most-of-bert-in-neural","title":"Towards Making the Most of BERT in Neural Machine Translation","date":"2019-08-15","arxiv_id":"1908.05672","n_code_links":2,"syntology":null},{"paper":null,"slug":"visualizing-and-understanding-the","title":"Visualizing and Understanding the Effectiveness of BERT","date":"2019-08-15","arxiv_id":"1908.05620","n_code_links":0,"syntology":null},{"paper":"/paper/establishing-strong-baselines-for-the-new","slug":"establishing-strong-baselines-for-the-new","title":"Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT","date":"2019-08-14","arxiv_id":"1908.04943","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-robustness-of-projection-neural","title":"On-Device Text Representations Robust To Misspellings via Projections","date":"2019-08-14","arxiv_id":"1908.05763","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-attentive-sentence-pair-modeling-via","slug":"scalable-attentive-sentence-pair-modeling-via","title":"Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding","date":"2019-08-14","arxiv_id":"1908.05161","n_code_links":1,"syntology":null},{"paper":"/paper/sg-net-syntax-guided-machine-reading","slug":"sg-net-syntax-guided-machine-reading","title":"SG-Net: Syntax-Guided Machine Reading Comprehension","date":"2019-08-14","arxiv_id":"1908.05147","n_code_links":1,"syntology":null},{"paper":"/paper/bioflair-pretrained-pooled-contextualized","slug":"bioflair-pretrained-pooled-contextualized","title":"BioFLAIR: Pretrained Pooled Contextualized Embeddings for Biomedical Sequence Labeling Tasks","date":"2019-08-13","arxiv_id":"1908.05760","n_code_links":1,"syntology":null},{"paper":"/paper/domain-adaptive-training-bert-for-response","slug":"domain-adaptive-training-bert-for-response","title":"An Effective Domain Adaptive Post-Training Method for BERT in Response Selection","date":"2019-08-13","arxiv_id":"1908.04812","n_code_links":1,"syntology":null},{"paper":"/paper/generative-question-refinement-with-deep","slug":"generative-question-refinement-with-deep","title":"Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System","date":"2019-08-13","arxiv_id":"1908.05604","n_code_links":1,"syntology":null},{"paper":"/paper/structbert-incorporating-language-structures","slug":"structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","date":"2019-08-13","arxiv_id":"1908.04577","n_code_links":0,"syntology":null},{"paper":"/paper/taper-time-aware-patient-ehr-representation","slug":"taper-time-aware-patient-ehr-representation","title":"TAPER: Time-Aware Patient EHR Representation","date":"2019-08-11","arxiv_id":"1908.03971","n_code_links":2,"syntology":{"ran":10,"of":12,"n_ran_checked":9,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"10 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["sajaddarabi/TAPER","sajaddarabi/TAPER-EHR"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-modality-latent-interaction-network-for","title":"Multi-modality Latent Interaction Network for Visual Question Answering","date":"2019-08-10","arxiv_id":"1908.04289","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-ranking-for-biomedical-entity","title":"BERT-based Ranking for Biomedical Entity Normalization","date":"2019-08-09","arxiv_id":"1908.03548","n_code_links":0,"syntology":null},{"paper":null,"slug":"tinysearch-semantics-based-search-engine","title":"TinySearch -- Semantics based Search Engine using Bert Embeddings","date":"2019-08-07","arxiv_id":"1908.02451","n_code_links":0,"syntology":null},{"paper":"/paper/clustering-of-deep-contextualized","slug":"clustering-of-deep-contextualized","title":"Clustering of Deep Contextualized Representations for Summarization of Biomedical Texts","date":"2019-08-06","arxiv_id":"1908.02286","n_code_links":1,"syntology":null},{"paper":"/paper/predicting-prosodic-prominence-from-text-with","slug":"predicting-prosodic-prominence-from-text-with","title":"Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations","date":"2019-08-06","arxiv_id":"1908.02262","n_code_links":1,"syntology":null},{"paper":"/paper/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","n_code_links":11,"syntology":{"ran":10,"of":34,"n_ran_checked":8,"n_instrument":2,"unverified":24,"pointer_only":34,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 24 unverified","official":null}},{"paper":"/paper/beyond-english-only-reading-comprehension","slug":"beyond-english-only-reading-comprehension","title":"Beyond English-Only Reading Comprehension: Experiments in Zero-Shot Multilingual Transfer for Bulgarian","date":"2019-08-05","arxiv_id":"1908.01519","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-neural-net-augmentation-to-bert-for","title":"Exploring Neural Net Augmentation to BERT for Question Answering on SQUAD 2.0","date":"2019-08-04","arxiv_id":"1908.01767","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-masked-language-modeling-for-co","title":"BERT Masked Language Modeling for Co-reference Resolution","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bsnlp2019-shared-task-submission-multisource","title":"BSNLP2019 Shared Task Submission: Multisource Neural NER Transfer","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-lemmatization-and-morphology","slug":"cross-lingual-lemmatization-and-morphology","title":"Cross-Lingual Lemmatization and Morphology Tagging with Two-Stage Multilingual BERT Fine-Tuning","date":"2019-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fill-the-gap-exploiting-bert-for-pronoun","slug":"fill-the-gap-exploiting-bert-for-pronoun","title":"Fill the GAP: Exploiting BERT for Pronoun Resolution","date":"2019-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"filtering-pseudo-references-by-paraphrasing","title":"Filtering Pseudo-References by Paraphrasing for Automatic Evaluation of Machine Translation","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gendered-ambiguous-pronoun-gap-shared-task-at","title":"Gendered Ambiguous Pronoun (GAP) Shared Task at the Gender Bias in NLP Workshop 2019","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hulmona-the-universal-language-model-in","slug":"hulmona-the-universal-language-model-in","title":"hULMonA: The Universal Language Model in Arabic","date":"2019-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"kfu-nlp-team-at-smm4h-2019-tasks-want-to","title":"KFU NLP Team at SMM4H 2019 Tasks: Want to Extract Adverse Drugs Reactions from Tweets? BERT to The Rescue","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ku_ai-at-mediqa-2019-domain-specific-pre","title":"KU\\_ai at MEDIQA 2019: Domain-specific Pre-training and Transfer Learning for Medical NLI","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mipt-system-for-world-level-quality","title":"MIPT System for World-Level Quality Estimation","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/msnet-a-bert-based-network-for-gendered-1","slug":"msnet-a-bert-based-network-for-gendered-1","title":"MSnet: A BERT-based Network for Gendered Pronoun Resolution","date":"2019-08-01","arxiv_id":"1908.00308","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-headed-architecture-based-on-bert-for","title":"Multi-headed Architecture Based on BERT for Grammatical Errors Correction","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ncuee-at-mediqa-2019-medical-text-inference","title":"NCUEE at MEDIQA 2019: Medical Text Inference Using Ensemble BERT-BiLSTM-Attention Model","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"no-army-no-navy-bert-semi-supervised-learning","title":"No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"noisy-channel-for-low-resource-grammatical","title":"Noisy Channel for Low Resource Grammatical Error Correction","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-gap-coreference-resolution-shared-task","title":"On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"panlp-at-mediqa-2019-pre-trained-language","title":"PANLP at MEDIQA 2019: Pre-trained Language Models, Transfer Learning and Knowledge Distillation","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"qe-bert-bilingual-bert-using-multi-task","title":"QE BERT: Bilingual BERT Using Multi-task Learning for Neural Quality Estimation","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"quality-estimation-and-translation-metrics","title":"Quality Estimation and Translation Metrics via Pre-trained Word and Sentence Embeddings","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/saama-research-at-mediqa-2019-pre-trained","slug":"saama-research-at-mediqa-2019-pre-trained","title":"Saama Research at MEDIQA 2019: Pre-trained BioBERT with Attention Visualisation for Medical Natural Language Inference","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-role-of-protected-class-word-lists-in","title":"The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tmu-transformer-system-using-bert-for-re","title":"TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted Track","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-from-pre-trained-bert-for","title":"Transfer Learning from Pre-trained BERT for Pronoun Resolution","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tuning-multilingual-transformers-for-language","slug":"tuning-multilingual-transformers-for-language","title":"Tuning Multilingual Transformers for Language-Specific Named Entity Recognition","date":"2019-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"uu_tails-at-mediqa-2019-learning-textual","title":"UU\\_TAILS at MEDIQA 2019: Learning Textual Entailment in the Medical Domain","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/what-bert-is-not-lessons-from-a-new-suite-of","slug":"what-bert-is-not-lessons-from-a-new-suite-of","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","date":"2019-07-31","arxiv_id":"1907.13528","n_code_links":2,"syntology":{"ran":5,"of":10,"n_ran_checked":0,"n_instrument":5,"unverified":5,"pointer_only":1,"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) · 5 unverified","official":{"repos":["aetting/lm-diagnostics"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/ernie-20-a-continual-pre-training-framework","slug":"ernie-20-a-continual-pre-training-framework","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","date":"2019-07-29","arxiv_id":"1907.12412","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["PaddlePaddle/ERNIE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/leveraging-pre-trained-checkpoints-for","slug":"leveraging-pre-trained-checkpoints-for","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","date":"2019-07-29","arxiv_id":"1907.12461","n_code_links":7,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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","official":null}},{"paper":null,"slug":"machine-translation-evaluation-with-bert","title":"Machine Translation Evaluation with BERT Regressor","date":"2019-07-29","arxiv_id":"1907.12679","n_code_links":0,"syntology":null},{"paper":"/paper/neural-mention-detection","slug":"neural-mention-detection","title":"Neural Mention Detection","date":"2019-07-29","arxiv_id":"1907.12524","n_code_links":1,"syntology":null},{"paper":"/paper/is-bert-really-robust-natural-language-attack","slug":"is-bert-really-robust-natural-language-attack","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","date":"2019-07-27","arxiv_id":"1907.11932","n_code_links":7,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":{"repos":["jind11/TextFooler"],"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"]}}},{"paper":"/paper/investigating-self-attention-network-for","slug":"investigating-self-attention-network-for","title":"Investigating Self-Attention Network for Chinese Word Segmentation","date":"2019-07-26","arxiv_id":"1907.11512","n_code_links":2,"syntology":null},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","n_code_links":67,"syntology":{"ran":37,"of":48,"n_ran_checked":36,"n_instrument":1,"unverified":11,"pointer_only":24,"phrase":"37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 0 honoured, 0 violated, 36 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/spanbert-improving-pre-training-by","slug":"spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","arxiv_id":"1907.10529","n_code_links":6,"syntology":{"ran":9,"of":15,"n_ran_checked":6,"n_instrument":3,"unverified":6,"pointer_only":6,"phrase":"9 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; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["facebookresearch/SpanBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"unbabels-participation-in-the-wmt19","title":"Unbabel's Participation in the WMT19 Translation Quality Estimation Shared Task","date":"2019-07-24","arxiv_id":"1907.10352","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotionx-hsu-adopting-pre-trained-bert-for","title":"EmotionX-HSU: Adopting Pre-trained BERT for Emotion Classification","date":"2019-07-23","arxiv_id":"1907.09669","n_code_links":0,"syntology":null},{"paper":"/paper/gear-graph-based-evidence-aggregating-and-1","slug":"gear-graph-based-evidence-aggregating-and-1","title":"GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification","date":"2019-07-22","arxiv_id":"1908.01843","n_code_links":2,"syntology":null},{"paper":null,"slug":"generating-sentiment-preserving-fake-online","title":"Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection","date":"2019-07-22","arxiv_id":"1907.09177","n_code_links":0,"syntology":null},{"paper":"/paper/fake-news-detection-as-natural-language","slug":"fake-news-detection-as-natural-language","title":"Fake News Detection as Natural Language Inference","date":"2019-07-17","arxiv_id":"1907.07347","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-shot-classification-a-comparison-of","title":"Low-Shot Classification: A Comparison of Classical and Deep Transfer Machine Learning Approaches","date":"2019-07-17","arxiv_id":"1907.07543","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-sentiment-analysis-using-deep","title":"Multi-modal Sentiment Analysis using Deep Canonical Correlation Analysis","date":"2019-07-15","arxiv_id":"1907.08696","n_code_links":0,"syntology":null},{"paper":null,"slug":"myers-briggs-personality-classification-and","title":"Myers-Briggs Personality Classification and Personality-Specific Language Generation Using Pre-trained Language Models","date":"2019-07-15","arxiv_id":"1907.06333","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-bert-based-approach-for-lexical","slug":"a-simple-bert-based-approach-for-lexical","title":"Lexical Simplification with Pretrained Encoders","date":"2019-07-14","arxiv_id":"1907.06226","n_code_links":3,"syntology":null},{"paper":"/paper/tweetqa-a-social-media-focused-question","slug":"tweetqa-a-social-media-focused-question","title":"TWEETQA: A Social Media Focused Question Answering Dataset","date":"2019-07-14","arxiv_id":"1907.06292","n_code_links":0,"syntology":null},{"paper":"/paper/bam-born-again-multi-task-networks-for","slug":"bam-born-again-multi-task-networks-for","title":"BAM! Born-Again Multi-Task Networks for Natural Language Understanding","date":"2019-07-10","arxiv_id":"1907.04829","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-unconditional-language-models-recover","title":"Can Unconditional Language Models Recover Arbitrary Sentences?","date":"2019-07-10","arxiv_id":"1907.04944","n_code_links":0,"syntology":null},{"paper":null,"slug":"lets-measure-run-time-extending-the-ir","title":"Let's measure run time! Extending the IR replicability infrastructure to include performance aspects","date":"2019-07-10","arxiv_id":"1907.04614","n_code_links":0,"syntology":null},{"paper":"/paper/to-tune-or-not-to-tune-how-about-the-best-of","slug":"to-tune-or-not-to-tune-how-about-the-best-of","title":"To Tune or Not To Tune? How About the Best of Both Worlds?","date":"2019-07-09","arxiv_id":"1907.05338","n_code_links":2,"syntology":null},{"paper":null,"slug":"incorporating-query-term-independence","title":"Incorporating Query Term Independence Assumption for Efficient Retrieval and Ranking using Deep Neural Networks","date":"2019-07-08","arxiv_id":"1907.03693","n_code_links":0,"syntology":null},{"paper":"/paper/short-text-conversation-based-on-deep-neural","slug":"short-text-conversation-based-on-deep-neural","title":"Short Text Conversation Based on Deep Neural Network and Analysis on Evaluation Measures","date":"2019-07-06","arxiv_id":"1907.03070","n_code_links":1,"syntology":null},{"paper":"/paper/bert-dst-scalable-end-to-end-dialogue-state","slug":"bert-dst-scalable-end-to-end-dialogue-state","title":"BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer","date":"2019-07-05","arxiv_id":"1907.03040","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-and-effective-approach-to-automatic-1","slug":"a-simple-and-effective-approach-to-automatic-1","title":"A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-surprisingly-robust-trick-for-the-winograd","title":"A Surprisingly Robust Trick for the Winograd Schema Challenge","date":"2019-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/bert-based-lexical-substitution","slug":"bert-based-lexical-substitution","title":"BERT-based Lexical Substitution","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/coreference-resolution-with-entity","slug":"coreference-resolution-with-entity","title":"Coreference Resolution with Entity Equalization","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/dissent-learning-sentence-representations","slug":"dissent-learning-sentence-representations","title":"DisSent: Learning Sentence Representations from Explicit Discourse Relations","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-pre-trained-language","slug":"enhancing-pre-trained-language","title":"Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/literary-event-detection","slug":"literary-event-detection","title":"Literary Event Detection","date":"2019-07-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"pentagon-at-mediqa-2019-multi-task-learning","title":"Pentagon at MEDIQA 2019: Multi-task Learning for Filtering and Re-ranking Answers using Language Inference and Question Entailment","date":"2019-07-01","arxiv_id":"1907.01643","n_code_links":0,"syntology":null},{"paper":"/paper/using-database-rule-for-weak-supervised-text","slug":"using-database-rule-for-weak-supervised-text","title":"Using Database Rule for Weak Supervised Text-to-SQL Generation","date":"2019-07-01","arxiv_id":"1907.00620","n_code_links":2,"syntology":null},{"paper":"/paper/what-does-bert-learn-about-the-structure-of","slug":"what-does-bert-learn-about-the-structure-of","title":"What Does BERT Learn about the Structure of Language?","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/xqa-a-cross-lingual-open-domain-question","slug":"xqa-a-cross-lingual-open-domain-question","title":"XQA: A Cross-lingual Open-domain Question Answering Dataset","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-language-model-finetuning","slug":"evaluating-language-model-finetuning","title":"Evaluating Language Model Finetuning Techniques for Low-resource Languages","date":"2019-06-30","arxiv_id":"1907.00409","n_code_links":2,"syntology":null},{"paper":"/paper/compositional-semantic-parsing-across","slug":"compositional-semantic-parsing-across","title":"Compositional Semantic Parsing Across Graphbanks","date":"2019-06-27","arxiv_id":"1906.11746","n_code_links":1,"syntology":null},{"paper":null,"slug":"inducing-syntactic-trees-from-bert","title":"Inducing Syntactic Trees from BERT Representations","date":"2019-06-27","arxiv_id":"1906.11511","n_code_links":0,"syntology":null},{"paper":"/paper/relating-simple-sentence-representations-in","slug":"relating-simple-sentence-representations-in","title":"Relating Simple Sentence Representations in Deep Neural Networks and the Brain","date":"2019-06-27","arxiv_id":"1906.11861","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-named-entity-recognition-using-1","slug":"multilingual-named-entity-recognition-using-1","title":"Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF","date":"2019-06-21","arxiv_id":"1906.09978","n_code_links":2,"syntology":null},{"paper":"/paper/pre-training-with-whole-word-masking-for","slug":"pre-training-with-whole-word-masking-for","title":"Pre-Training with Whole Word Masking for Chinese BERT","date":"2019-06-19","arxiv_id":"1906.08101","n_code_links":2,"syntology":null},{"paper":"/paper/measuring-bias-in-contextualized-word","slug":"measuring-bias-in-contextualized-word","title":"Measuring Bias in Contextualized Word Representations","date":"2019-06-18","arxiv_id":"1906.07337","n_code_links":1,"syntology":null},{"paper":"/paper/transfer-learning-for-causal-sentence","slug":"transfer-learning-for-causal-sentence","title":"Transfer Learning for Causal Sentence Detection","date":"2019-06-18","arxiv_id":"1906.07544","n_code_links":2,"syntology":null},{"paper":"/paper/zero-shot-entity-linking-by-reading-entity","slug":"zero-shot-entity-linking-by-reading-entity","title":"Zero-Shot Entity Linking by Reading Entity Descriptions","date":"2019-06-18","arxiv_id":"1906.07348","n_code_links":3,"syntology":null},{"paper":null,"slug":"exploiting-unsupervised-pre-training-and","title":"Exploiting Unsupervised Pre-training and Automated Feature Engineering for Low-resource Hate Speech Detection in Polish","date":"2019-06-17","arxiv_id":"1906.09325","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-transfer-learning-for-end-to-end","title":"Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models","date":"2019-06-17","arxiv_id":"1906.07307","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-epoch-is-all-you-need","title":"One Epoch Is All You Need","date":"2019-06-16","arxiv_id":"1906.06669","n_code_links":0,"syntology":null},{"paper":"/paper/context-is-key-grammatical-error-detection","slug":"context-is-key-grammatical-error-detection","title":"Context is Key: Grammatical Error Detection with Contextual Word Representations","date":"2019-06-15","arxiv_id":"1906.06593","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-and-effective-approach-to-automatic","slug":"a-simple-and-effective-approach-to-automatic","title":"A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning","date":"2019-06-14","arxiv_id":"1906.06253","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["deep-spin/OpenNMT-APE"],"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"]}}},{"paper":null,"slug":"contrastive-bidirectional-transformer-for","title":"Learning Video Representations using Contrastive Bidirectional Transformer","date":"2019-06-13","arxiv_id":"1906.05743","n_code_links":0,"syntology":null},{"paper":null,"slug":"telephonetic-making-neural-language-models","title":"Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise","date":"2019-06-13","arxiv_id":"1906.05678","n_code_links":0,"syntology":null},{"paper":"/paper/a-multiscale-visualization-of-attention-in","slug":"a-multiscale-visualization-of-attention-in","title":"A Multiscale Visualization of Attention in the Transformer Model","date":"2019-06-12","arxiv_id":"1906.05714","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["jessevig/bertviz"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/neural-arabic-question-answering","slug":"neural-arabic-question-answering","title":"Neural Arabic Question Answering","date":"2019-06-12","arxiv_id":"1906.05394","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["husseinmozannar/SOQAL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"202fabdc407c354a5dc0ad534b656c25a1ecfa7eced72c6adb7056f1f9d6a90c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}