{"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/weight-decay/papers/75","list_of":"/method/weight-decay","method":"Weight Decay","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":75,"pages_in_order":108,"rows_per_page":100,"rows":[7401,7500],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/weight-decay","prev":"/method/weight-decay/papers/74","next":"/method/weight-decay/papers/76","papers":[{"paper":null,"slug":"model-bias-in-nlp-application-to-hate-speech","title":"Model Bias in NLP -- Application to Hate Speech Classification using transfer learning techniques","date":"2021-09-20","arxiv_id":"2109.09725","n_code_links":0,"syntology":null},{"paper":"/paper/mirrorwic-on-eliciting-word-in-context","slug":"mirrorwic-on-eliciting-word-in-context","title":"MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models","date":"2021-09-19","arxiv_id":"2109.09237","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-zero-label-language-learning","title":"Towards Zero-Label Language Learning","date":"2021-09-19","arxiv_id":"2109.09193","n_code_links":0,"syntology":null},{"paper":null,"slug":"wav-bert-cooperative-acoustic-and-linguistic","title":"Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition","date":"2021-09-19","arxiv_id":"2109.09161","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-bert-based-language-models-learn-in","title":"What BERT Based Language Models Learn in Spoken Transcripts: An Empirical Study","date":"2021-09-19","arxiv_id":"2109.09105","n_code_links":0,"syntology":null},{"paper":"/paper/complex-temporal-question-answering-on","slug":"complex-temporal-question-answering-on","title":"Complex Temporal Question Answering on Knowledge Graphs","date":"2021-09-18","arxiv_id":"2109.08935","n_code_links":1,"syntology":null},{"paper":"/paper/dylex-incoporating-dynamic-lexicons-into-bert","slug":"dylex-incoporating-dynamic-lexicons-into-bert","title":"DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling","date":"2021-09-18","arxiv_id":"2109.08818","n_code_links":1,"syntology":null},{"paper":"/paper/text-detoxification-using-large-pre-trained","slug":"text-detoxification-using-large-pre-trained","title":"Text Detoxification using Large Pre-trained Neural Models","date":"2021-09-18","arxiv_id":"2109.08914","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["skoltech-nlp/detox"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"commonsense-knowledge-augmented-pretrained","title":"Commonsense Knowledge-Augmented Pretrained Language Models for Causal Reasoning Classification","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"context-vs-target-word-quantifying-biases","title":"Context vs Target Word: Quantifying Biases When Applying Models to Lexical Semantic Datasets","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-based-2","title":"Deep Reinforcement Learning Based Multidimensional Resource Management for Energy Harvesting Cognitive NOMA Communications","date":"2021-09-17","arxiv_id":"2109.09503","n_code_links":0,"syntology":null},{"paper":null,"slug":"defending-textual-neural-networks-against","title":"Defending Textual Neural Networks against Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"does-bert-really-agree-fine-grained-analysis","title":"Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuned-transformers-show-clusters-of","title":"Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers","date":"2021-09-17","arxiv_id":"2109.08406","n_code_links":0,"syntology":null},{"paper":"/paper/grounding-natural-language-instructions-can","slug":"grounding-natural-language-instructions-can","title":"Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?","date":"2021-09-17","arxiv_id":"2109.08634","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-neurons-in-pretrained-transformers-1","title":"Knowledge Neurons in Pretrained Transformers","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-low-frequency-patterns-with-a-pre","title":"Learning Low-frequency Patterns with A Pre-trained Document-Grounded Conversation Model","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/new-students-on-sesame-street-what-order","slug":"new-students-on-sesame-street-what-order","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","date":"2021-09-17","arxiv_id":"2109.08449","n_code_links":1,"syntology":null},{"paper":"/paper/primer-searching-for-efficient-transformers","slug":"primer-searching-for-efficient-transformers","title":"Primer: Searching for Efficient Transformers for Language Modeling","date":"2021-09-17","arxiv_id":"2109.08668","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/google-research"],"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":["listed","unlocated"]}}},{"paper":null,"slug":"relating-neural-text-degeneration-to-exposure","title":"Relating Neural Text Degeneration to Exposure Bias","date":"2021-09-17","arxiv_id":"2109.08705","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-futility-of-stilts-for-the-classification","title":"The futility of STILTs for the classification of lexical borrowings in Spanish","date":"2021-09-17","arxiv_id":"2109.08607","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-few-shot-multilingual","slug":"language-models-are-few-shot-multilingual","title":"Language Models are Few-shot Multilingual Learners","date":"2021-09-16","arxiv_id":"2109.07684","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gentaiscool/few-shot-lm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"let-the-cat-out-of-the-bag-contrastive","title":"Let the CAT out of the bag: Contrastive Attributed explanations for Text","date":"2021-09-16","arxiv_id":"2109.07983","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrievalsum-a-retrieval-enhanced-framework","title":"RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization","date":"2021-09-16","arxiv_id":"2109.07943","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-tri-training-of-dependency-parsers","slug":"revisiting-tri-training-of-dependency-parsers","title":"Revisiting Tri-training of Dependency Parsers","date":"2021-09-16","arxiv_id":"2109.08122","n_code_links":2,"syntology":null},{"paper":null,"slug":"bert-is-robust-a-case-against-synonym-based","title":"BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification","date":"2021-09-15","arxiv_id":"2109.07403","n_code_links":0,"syntology":null},{"paper":"/paper/e-fficient-bert-progressively-searching","slug":"e-fficient-bert-progressively-searching","title":"EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation","date":"2021-09-15","arxiv_id":"2109.07222","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["cheneydon/efficient-bert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"efficient-domain-adaptation-of-language","title":"Efficient Domain Adaptation of Language Models via Adaptive Tokenization","date":"2021-09-15","arxiv_id":"2109.07460","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-clinical-information-extraction","title":"Enhancing Clinical Information Extraction with Transferred Contextual Embeddings","date":"2021-09-15","arxiv_id":"2109.07243","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-text-auto-completion-with-next","title":"Improving Text Auto-Completion with Next Phrase Prediction","date":"2021-09-15","arxiv_id":"2109.07067","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-match-job-candidates-using","title":"Learning to Match Job Candidates Using Multilingual Bi-Encoder BERT","date":"2021-09-15","arxiv_id":"2109.07157","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-universality-of-deep-contextual","title":"On the Universality of Deep Contextual Language Models","date":"2021-09-15","arxiv_id":"2109.07140","n_code_links":0,"syntology":null},{"paper":"/paper/the-unreasonable-effectiveness-of-the","slug":"the-unreasonable-effectiveness-of-the","title":"The Unreasonable Effectiveness of the Baseline: Discussing SVMs in Legal Text Classification","date":"2021-09-15","arxiv_id":"2109.07234","n_code_links":0,"syntology":null},{"paper":"/paper/topic-transferable-table-question-answering","slug":"topic-transferable-table-question-answering","title":"Topic Transferable Table Question Answering","date":"2021-09-15","arxiv_id":"2109.07377","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-language-models-for-factoid","slug":"transformer-based-language-models-for-factoid","title":"Transformer-based Language Models for Factoid Question Answering at BioASQ9b","date":"2021-09-15","arxiv_id":"2109.07185","n_code_links":1,"syntology":null},{"paper":"/paper/a-temporal-variational-model-for-story","slug":"a-temporal-variational-model-for-story","title":"A Temporal Variational Model for Story Generation","date":"2021-09-14","arxiv_id":"2109.06807","n_code_links":3,"syntology":null},{"paper":null,"slug":"consultantbert-fine-tuned-siamese-sentence","title":"conSultantBERT: Fine-tuned Siamese Sentence-BERT for Matching Jobs and Job Seekers","date":"2021-09-14","arxiv_id":"2109.06501","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-based-nlp-data-pipeline-for-ehr","title":"Deep learning-based NLP Data Pipeline for EHR Scanned Document Information Extraction","date":"2021-09-14","arxiv_id":"2110.11864","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-biomedical-bert-models-for","title":"Evaluating Biomedical BERT Models for Vocabulary Alignment at Scale in the UMLS Metathesaurus","date":"2021-09-14","arxiv_id":"2109.13348","n_code_links":0,"syntology":null},{"paper":null,"slug":"explainable-identification-of-dementia-from","title":"Explainable Identification of Dementia from Transcripts using Transformer Networks","date":"2021-09-14","arxiv_id":"2109.06980","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-personality-and-online-social","title":"Exploring Personality and Online Social Engagement: An Investigation of MBTI Users on Twitter","date":"2021-09-14","arxiv_id":"2109.06402","n_code_links":0,"syntology":null},{"paper":"/paper/frequency-effects-on-syntactic-rule-learning","slug":"frequency-effects-on-syntactic-rule-learning","title":"Frequency Effects on Syntactic Rule Learning in Transformers","date":"2021-09-14","arxiv_id":"2109.07020","n_code_links":1,"syntology":null},{"paper":"/paper/learning-bill-similarity-with-annotated-and","slug":"learning-bill-similarity-with-annotated-and","title":"Learning Bill Similarity with Annotated and Augmented Corpora of Bills","date":"2021-09-14","arxiv_id":"2109.06527","n_code_links":1,"syntology":null},{"paper":null,"slug":"legal-transformer-models-may-not-always-help","title":"Legal Transformer Models May Not Always Help","date":"2021-09-14","arxiv_id":"2109.06862","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-language-specificity-of-multilingual","slug":"on-the-language-specificity-of-multilingual","title":"On the Language-specificity of Multilingual BERT and the Impact of Fine-tuning","date":"2021-09-14","arxiv_id":"2109.06935","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-answer-type-prediction-using-bert","title":"Semantic Answer Type Prediction using BERT: IAI at the ISWC SMART Task 2020","date":"2021-09-14","arxiv_id":"2109.06714","n_code_links":0,"syntology":null},{"paper":"/paper/tribrid-stance-classification-with-neural","slug":"tribrid-stance-classification-with-neural","title":"Tribrid: Stance Classification with Neural Inconsistency Detection","date":"2021-09-14","arxiv_id":"2109.06508","n_code_links":1,"syntology":null},{"paper":null,"slug":"yes-sir-optimizing-semantic-space-of","title":"YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker","date":"2021-09-14","arxiv_id":"2109.06436","n_code_links":0,"syntology":null},{"paper":null,"slug":"effectiveness-of-pre-training-for-few-shot","title":"Effectiveness of Pre-training for Few-shot Intent Classification","date":"2021-09-13","arxiv_id":"2109.05782","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-transferability-of-bert-models-on","slug":"evaluating-transferability-of-bert-models-on","title":"Evaluating Transferability of BERT Models on Uralic Languages","date":"2021-09-13","arxiv_id":"2109.06327","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-a-unified-sequence-to-sequence","slug":"exploring-a-unified-sequence-to-sequence","title":"Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media","date":"2021-09-13","arxiv_id":"2109.05815","n_code_links":1,"syntology":null},{"paper":null,"slug":"keyword-extraction-for-improved-document","title":"Keyword Extraction for Improved Document Retrieval in Conversational Search","date":"2021-09-13","arxiv_id":"2109.05979","n_code_links":0,"syntology":null},{"paper":"/paper/mitigating-language-dependent-ethnic-bias-in","slug":"mitigating-language-dependent-ethnic-bias-in","title":"Mitigating Language-Dependent Ethnic Bias in BERT","date":"2021-09-13","arxiv_id":"2109.05704","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jaimeenahn/ethnic_bias"],"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"]}}},{"paper":null,"slug":"not-all-models-localize-linguistic-knowledge","title":"Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations","date":"2021-09-13","arxiv_id":"2109.05958","n_code_links":0,"syntology":null},{"paper":"/paper/old-bert-new-tricks-artificial-language","slug":"old-bert-new-tricks-artificial-language","title":"Connecting degree and polarity: An artificial language learning study","date":"2021-09-13","arxiv_id":"2109.06333","n_code_links":1,"syntology":null},{"paper":"/paper/phrase-bert-improved-phrase-embeddings-from","slug":"phrase-bert-improved-phrase-embeddings-from","title":"Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration","date":"2021-09-13","arxiv_id":"2109.06304","n_code_links":2,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sf-wa-326/phrase-bert-topic-model"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/question-answering-over-electronic-devices-a","slug":"question-answering-over-electronic-devices-a","title":"Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework","date":"2021-09-13","arxiv_id":"2109.05897","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["abhi1nandy2/emnlp-2021-findings"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/flitext-a-faster-and-lighter-semi-supervised","slug":"flitext-a-faster-and-lighter-semi-supervised","title":"FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks","date":"2021-09-12","arxiv_id":"2110.11869","n_code_links":1,"syntology":null},{"paper":"/paper/teasel-a-transformer-based-speech-prefixed","slug":"teasel-a-transformer-based-speech-prefixed","title":"TEASEL: A Transformer-Based Speech-Prefixed Language Model","date":"2021-09-12","arxiv_id":"2109.05522","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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","official":null}},{"paper":null,"slug":"clinical-trial-information-extraction-with","title":"Clinical Trial Information Extraction with BERT","date":"2021-09-11","arxiv_id":"2110.10027","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-translation-via-grafting-pre","slug":"multilingual-translation-via-grafting-pre","title":"Multilingual Translation via Grafting Pre-trained Language Models","date":"2021-09-11","arxiv_id":"2109.05256","n_code_links":1,"syntology":null},{"paper":null,"slug":"topicrefine-joint-topic-prediction-and","title":"TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System","date":"2021-09-11","arxiv_id":"2109.05187","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-gpt-3-for-few-shot","slug":"an-empirical-study-of-gpt-3-for-few-shot","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","date":"2021-09-10","arxiv_id":"2109.05014","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":["microsoft/PICa"],"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"]}}},{"paper":"/paper/an-exploratory-study-on-long-dialogue","slug":"an-exploratory-study-on-long-dialogue","title":"An Exploratory Study on Long Dialogue Summarization: What Works and What's Next","date":"2021-09-10","arxiv_id":"2109.04609","n_code_links":1,"syntology":null},{"paper":"/paper/artificial-text-detection-via-examining-the","slug":"artificial-text-detection-via-examining-the","title":"Artificial Text Detection via Examining the Topology of Attention Maps","date":"2021-09-10","arxiv_id":"2109.04825","n_code_links":2,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 8 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["danchern97/tda4atd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/block-pruning-for-faster-transformers","slug":"block-pruning-for-faster-transformers","title":"Block Pruning For Faster Transformers","date":"2021-09-10","arxiv_id":"2109.04838","n_code_links":1,"syntology":null},{"paper":"/paper/d-rex-dialogue-relation-extraction-with","slug":"d-rex-dialogue-relation-extraction-with","title":"D-REX: Dialogue Relation Extraction with Explanations","date":"2021-09-10","arxiv_id":"2109.05126","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-self-disclosure-in-neural-dialog","title":"Enhancing Self-Disclosure In Neural Dialog Models By Candidate Re-ranking","date":"2021-09-10","arxiv_id":"2109.05090","n_code_links":0,"syntology":null},{"paper":null,"slug":"fbert-a-neural-transformer-for-identifying","title":"FBERT: A Neural Transformer for Identifying Offensive Content","date":"2021-09-10","arxiv_id":"2109.05074","n_code_links":0,"syntology":null},{"paper":"/paper/how-may-i-help-you-using-neural-text","slug":"how-may-i-help-you-using-neural-text","title":"How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks","date":"2021-09-10","arxiv_id":"2109.04604","n_code_links":1,"syntology":null},{"paper":"/paper/indobertweet-a-pretrained-language-model-for","slug":"indobertweet-a-pretrained-language-model-for","title":"IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization","date":"2021-09-10","arxiv_id":"2109.04607","n_code_links":1,"syntology":null},{"paper":"/paper/mixture-of-partitions-infusing-large","slug":"mixture-of-partitions-infusing-large","title":"Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT","date":"2021-09-10","arxiv_id":"2109.04810","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["cambridgeltl/mop"],"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"]}}},{"paper":null,"slug":"on-the-validity-of-pre-trained-transformers","title":"On the validity of pre-trained transformers for natural language processing in the software engineering domain","date":"2021-09-10","arxiv_id":"2109.04738","n_code_links":0,"syntology":null},{"paper":"/paper/ror-read-over-read-for-long-document-machine","slug":"ror-read-over-read-for-long-document-machine","title":"RoR: Read-over-Read for Long Document Machine Reading Comprehension","date":"2021-09-10","arxiv_id":"2109.04780","n_code_links":1,"syntology":null},{"paper":"/paper/what-changes-can-large-scale-language-models","slug":"what-changes-can-large-scale-language-models","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","date":"2021-09-10","arxiv_id":"2109.04650","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/all-bark-and-no-bite-rogue-dimensions-in","slug":"all-bark-and-no-bite-rogue-dimensions-in","title":"All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality","date":"2021-09-09","arxiv_id":"2109.04404","n_code_links":1,"syntology":null},{"paper":"/paper/bert-mbert-or-bibert-a-study-on","slug":"bert-mbert-or-bibert-a-study-on","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","date":"2021-09-09","arxiv_id":"2109.04588","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fe1ixxu/BiBERT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/generalised-unsupervised-domain-adaptation-of","slug":"generalised-unsupervised-domain-adaptation-of","title":"Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection","date":"2021-09-09","arxiv_id":"2109.04292","n_code_links":1,"syntology":null},{"paper":"/paper/improving-video-text-retrieval-by-multi","slug":"improving-video-text-retrieval-by-multi","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","date":"2021-09-09","arxiv_id":"2109.04290","n_code_links":2,"syntology":null},{"paper":"/paper/kelm-knowledge-enhanced-pre-trained-language","slug":"kelm-knowledge-enhanced-pre-trained-language","title":"KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs","date":"2021-09-09","arxiv_id":"2109.04223","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":1,"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","official":{"repos":["nlp-anonymous-happy/anonymous-kg-guided-nlp"],"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"]}}},{"paper":null,"slug":"medically-aware-gpt-3-as-a-data-generator-for","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","date":"2021-09-09","arxiv_id":"2110.07356","n_code_links":0,"syntology":null},{"paper":null,"slug":"mining-points-of-interest-via-address","title":"Mining Points of Interest via Address Embeddings: An Unsupervised Approach","date":"2021-09-09","arxiv_id":"2109.04467","n_code_links":0,"syntology":null},{"paper":"/paper/multi-granularity-textual-adversarial-attack","slug":"multi-granularity-textual-adversarial-attack","title":"Multi-granularity Textual Adversarial Attack with Behavior Cloning","date":"2021-09-09","arxiv_id":"2109.04367","n_code_links":1,"syntology":null},{"paper":"/paper/variational-latent-state-gpt-for-semi","slug":"variational-latent-state-gpt-for-semi","title":"Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems","date":"2021-09-09","arxiv_id":"2109.04314","n_code_links":2,"syntology":null},{"paper":"/paper/word-level-coreference-resolution","slug":"word-level-coreference-resolution","title":"Word-Level Coreference Resolution","date":"2021-09-09","arxiv_id":"2109.04127","n_code_links":1,"syntology":null},{"paper":null,"slug":"ensemble-fine-tuned-mbert-for-translation","title":"Ensemble Fine-tuned mBERT for Translation Quality Estimation","date":"2021-09-08","arxiv_id":"2109.03914","n_code_links":0,"syntology":null},{"paper":"/paper/forget-me-not-a-gentle-reminder-to-mind-the","slug":"forget-me-not-a-gentle-reminder-to-mind-the","title":"Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP","date":"2021-09-08","arxiv_id":"2109.03777","n_code_links":2,"syntology":null},{"paper":"/paper/nsp-bert-a-prompt-based-zero-shot-learner","slug":"nsp-bert-a-prompt-based-zero-shot-learner","title":"NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction","date":"2021-09-08","arxiv_id":"2109.03564","n_code_links":1,"syntology":null},{"paper":null,"slug":"sustainable-modular-debiasing-of-language","title":"Sustainable Modular Debiasing of Language Models","date":"2021-09-08","arxiv_id":"2109.03646","n_code_links":0,"syntology":null},{"paper":"/paper/truthfulqa-measuring-how-models-mimic-human","slug":"truthfulqa-measuring-how-models-mimic-human","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","date":"2021-09-08","arxiv_id":"2109.07958","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":["sylinrl/truthfulqa"],"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"]}}},{"paper":null,"slug":"bert-based-classification-system-for","title":"BERT based classification system for detecting rumours on Twitter","date":"2021-09-07","arxiv_id":"2109.02975","n_code_links":0,"syntology":null},{"paper":null,"slug":"empathetic-dialogue-generation-with-pre","title":"Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge","date":"2021-09-07","arxiv_id":"2109.03004","n_code_links":0,"syntology":null},{"paper":"/paper/fhac-at-germeval-2021-identifying-german","slug":"fhac-at-germeval-2021-identifying-german","title":"FHAC at GermEval 2021: Identifying German toxic, engaging, and fact-claiming comments with ensemble learning","date":"2021-09-07","arxiv_id":"2109.03094","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-much-pretraining-data-do-language-models","title":"How much pretraining data do language models need to learn syntax?","date":"2021-09-07","arxiv_id":"2109.03160","n_code_links":0,"syntology":null},{"paper":null,"slug":"naturalness-evaluation-of-natural-language","title":"Naturalness Evaluation of Natural Language Generation in Task-oriented Dialogues using BERT","date":"2021-09-07","arxiv_id":"2109.02938","n_code_links":0,"syntology":null},{"paper":null,"slug":"numgpt-improving-numeracy-ability-of","title":"NumGPT: Improving Numeracy Ability of Generative Pre-trained Models","date":"2021-09-07","arxiv_id":"2109.03137","n_code_links":0,"syntology":null},{"paper":"/paper/pause-positive-and-annealed-unlabeled","slug":"pause-positive-and-annealed-unlabeled","title":"PAUSE: Positive and Annealed Unlabeled Sentence Embedding","date":"2021-09-07","arxiv_id":"2109.03155","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":["eqtpartners/pause"],"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"]}}},{"paper":"/paper/refining-bert-embeddings-for-document-hashing","slug":"refining-bert-embeddings-for-document-hashing","title":"Refining BERT Embeddings for Document Hashing via Mutual Information Maximization","date":"2021-09-07","arxiv_id":"2109.02867","n_code_links":1,"syntology":null},{"paper":"/paper/text-free-prosody-aware-generative-spoken","slug":"text-free-prosody-aware-generative-spoken","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","date":"2021-09-07","arxiv_id":"2109.03264","n_code_links":1,"syntology":null},{"paper":"/paper/does-bert-learn-as-humans-perceive","slug":"does-bert-learn-as-humans-perceive","title":"Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica","date":"2021-09-06","arxiv_id":"2109.02738","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["sweetpeach/hummingbird"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"cbc63d4097f5e4159c9c7c47af4f2855fc8aee3caf70c1ad432b6a50a27e043c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}