{"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/wordpiece/papers/44","list_of":"/method/wordpiece","method":"WordPiece","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":44,"pages_in_order":71,"rows_per_page":100,"rows":[4301,4400],"of":7063,"counts":{"archive_papers_tagged":7063,"with_a_code_link":2910,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7063,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":529,"every_run_a_failure_of_syntologys_instrument":121,"listed_with_a_run_with_no_instrument_failure":529,"listed_every_run_a_failure_of_syntologys_instrument":121,"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/wordpiece","prev":"/method/wordpiece/papers/43","next":"/method/wordpiece/papers/45","papers":[{"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":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":null,"slug":"wine-is-not-v-i-n-on-the-compatibility-of","title":"Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages","date":"2021-09-13","arxiv_id":"2109.05772","n_code_links":0,"syntology":null},{"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-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":"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/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":"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/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":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":"/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/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"]}}},{"paper":"/paper/enhancing-language-models-with-plug-and-play","slug":"enhancing-language-models-with-plug-and-play","title":"Enhancing Natural Language Representation with Large-Scale Out-of-Domain Commonsense","date":"2021-09-06","arxiv_id":"2109.02572","n_code_links":1,"syntology":null},{"paper":null,"slug":"ss-bert-mitigating-identity-terms-bias-in","title":"SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of \"Subjectivity\" and \"Identity Terms\"","date":"2021-09-06","arxiv_id":"2109.02691","n_code_links":0,"syntology":null},{"paper":null,"slug":"error-detection-in-large-scale-natural","title":"Error Detection in Large-Scale Natural Language Understanding Systems Using Transformer Models","date":"2021-09-04","arxiv_id":"2109.01754","n_code_links":0,"syntology":null},{"paper":"/paper/uncovering-the-limits-of-text-based-emotion","slug":"uncovering-the-limits-of-text-based-emotion","title":"Uncovering the Limits of Text-based Emotion Detection","date":"2021-09-04","arxiv_id":"2109.01900","n_code_links":2,"syntology":null},{"paper":"/paper/a-context-aware-hierarchical-bert-fusion","slug":"a-context-aware-hierarchical-bert-fusion","title":"A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection","date":"2021-09-03","arxiv_id":"2109.01267","n_code_links":1,"syntology":null},{"paper":"/paper/codet5-identifier-aware-unified-pre-trained","slug":"codet5-identifier-aware-unified-pre-trained","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","date":"2021-09-02","arxiv_id":"2109.00859","n_code_links":5,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":0,"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) · 5 unverified","official":{"repos":["salesforce/codet5"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"conqx-semantic-expansion-of-spoken-queries","title":"ConQX: Semantic Expansion of Spoken Queries for Intent Detection based on Conditioned Text Generation","date":"2021-09-02","arxiv_id":"2109.00729","n_code_links":0,"syntology":null},{"paper":null,"slug":"legalmfit-efficient-short-legal-text","title":"LegaLMFiT: Efficient Short Legal Text Classification with LSTM Language Model Pre-Training","date":"2021-09-02","arxiv_id":"2109.00993","n_code_links":0,"syntology":null},{"paper":null,"slug":"so-cloze-yet-so-far-n400-amplitude-is-better","title":"So Cloze yet so Far: N400 Amplitude is Better Predicted by Distributional Information than Human Predictability Judgements","date":"2021-09-02","arxiv_id":"2109.01226","n_code_links":0,"syntology":null},{"paper":null,"slug":"travelbert-pre-training-language-model","title":"Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation","date":"2021-09-02","arxiv_id":"2109.01048","n_code_links":0,"syntology":null},{"paper":"/paper/dilbert-customized-pre-training-for-domain","slug":"dilbert-customized-pre-training-for-domain","title":"DILBERT: Customized Pre-Training for Domain Adaptation withCategory Shift, with an Application to Aspect Extraction","date":"2021-09-01","arxiv_id":"2109.00571","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-deep-learning-methods-for","slug":"exploring-deep-learning-methods-for","title":"Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts","date":"2021-09-01","arxiv_id":"2109.00343","n_code_links":2,"syntology":null},{"paper":null,"slug":"fight-fire-with-fire-fine-tuning-hate","title":"Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech","date":"2021-09-01","arxiv_id":"2109.00591","n_code_links":0,"syntology":null},{"paper":"/paper/optagan-entropy-based-finetuning-on-text-vae","slug":"optagan-entropy-based-finetuning-on-text-vae","title":"OptAGAN: Entropy-based finetuning on text VAE-GAN","date":"2021-09-01","arxiv_id":"2109.00239","n_code_links":1,"syntology":null},{"paper":"/paper/towards-improving-adversarial-training-of-nlp","slug":"towards-improving-adversarial-training-of-nlp","title":"Towards Improving Adversarial Training of NLP Models","date":"2021-09-01","arxiv_id":"2109.00544","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["QData/TextAttack-A2T"],"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"]}}},{"paper":null,"slug":"effectiveness-of-deep-networks-in-nlp-using","title":"Effectiveness of Deep Networks in NLP using BiDAF as an example architecture","date":"2021-08-31","arxiv_id":"2109.00074","n_code_links":0,"syntology":null},{"paper":"/paper/enjoy-the-salience-towards-better-transformer","slug":"enjoy-the-salience-towards-better-transformer","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","date":"2021-08-31","arxiv_id":"2108.13759","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-does-adversarial-fine-tuning-benefit-bert","title":"How Does Adversarial Fine-Tuning Benefit BERT?","date":"2021-08-31","arxiv_id":"2108.13602","n_code_links":0,"syntology":null},{"paper":null,"slug":"monolingual-versus-multilingual-bertology-for","title":"Monolingual versus Multilingual BERTology for Vietnamese Extractive Multi-Document Summarization","date":"2021-08-31","arxiv_id":"2108.13741","n_code_links":0,"syntology":null},{"paper":null,"slug":"sense-representations-for-portuguese","title":"Sense representations for Portuguese: experiments with sense embeddings and deep neural language models","date":"2021-08-31","arxiv_id":"2109.00025","n_code_links":0,"syntology":null},{"paper":"/paper/improving-query-representations-for-dense","slug":"improving-query-representations-for-dense","title":"Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback","date":"2021-08-30","arxiv_id":"2108.13454","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["yuhongqian/ance-prf"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/knowledge-base-completion-meets-transfer","slug":"knowledge-base-completion-meets-transfer","title":"Knowledge Base Completion Meets Transfer Learning","date":"2021-08-30","arxiv_id":"2108.13073","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vid-koci/kbctransferlearning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"shatter-an-efficient-transformer-encoder-with","title":"Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning","date":"2021-08-30","arxiv_id":"2108.13032","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-and-mitigating-interference-in","title":"Analyzing and Mitigating Interference in Neural Architecture Search","date":"2021-08-29","arxiv_id":"2108.12821","n_code_links":0,"syntology":null},{"paper":null,"slug":"noier-an-approach-for-training-more-reliable","title":"NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models","date":"2021-08-29","arxiv_id":"2110.02054","n_code_links":0,"syntology":null},{"paper":null,"slug":"dkm-differentiable-k-means-clustering-layer","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","date":"2021-08-28","arxiv_id":"2108.12659","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-text-evaluation-through-the-lens-of","slug":"automatic-text-evaluation-through-the-lens-of","title":"Automatic Text Evaluation through the Lens of Wasserstein Barycenters","date":"2021-08-27","arxiv_id":"2108.12463","n_code_links":2,"syntology":null},{"paper":"/paper/dealing-with-typos-for-bert-based-passage","slug":"dealing-with-typos-for-bert-based-passage","title":"Dealing with Typos for BERT-based Passage Retrieval and Ranking","date":"2021-08-27","arxiv_id":"2108.12139","n_code_links":2,"syntology":null},{"paper":"/paper/evaluating-the-robustness-of-neural-language","slug":"evaluating-the-robustness-of-neural-language","title":"Evaluating the Robustness of Neural Language Models to Input Perturbations","date":"2021-08-27","arxiv_id":"2108.12237","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mmoradi-iut/nlp-perturbation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/query-focused-extractive-summarisation-for","slug":"query-focused-extractive-summarisation-for","title":"Query-Focused Extractive Summarisation for Finding Ideal Answers to Biomedical and COVID-19 Questions","date":"2021-08-27","arxiv_id":"2108.12189","n_code_links":1,"syntology":null},{"paper":"/paper/a-computational-approach-to-measure-empathy","slug":"a-computational-approach-to-measure-empathy","title":"A Computational Approach to Measure Empathy and Theory-of-Mind from Written Texts","date":"2021-08-26","arxiv_id":"2108.11810","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-new-sentence-ordering-method-using-bert","title":"A New Sentence Ordering Method Using BERT Pretrained Model","date":"2021-08-26","arxiv_id":"2108.11994","n_code_links":0,"syntology":null},{"paper":"/paper/emoberta-speaker-aware-emotion-recognition-in","slug":"emoberta-speaker-aware-emotion-recognition-in","title":"EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa","date":"2021-08-26","arxiv_id":"2108.12009","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-why-intermediate-task-fine-tuning","slug":"rethinking-why-intermediate-task-fine-tuning","title":"Rethinking Why Intermediate-Task Fine-Tuning Works","date":"2021-08-26","arxiv_id":"2108.11696","n_code_links":1,"syntology":null},{"paper":"/paper/slim-explicit-slot-intent-mapping-with-bert","slug":"slim-explicit-slot-intent-mapping-with-bert","title":"SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling","date":"2021-08-26","arxiv_id":"2108.11711","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-attention-in-machine-reading","slug":"understanding-attention-in-machine-reading","title":"Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models","date":"2021-08-26","arxiv_id":"2108.11574","n_code_links":1,"syntology":null},{"paper":"/paper/models-in-a-spelling-bee-language-models","slug":"models-in-a-spelling-bee-language-models","title":"Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens","date":"2021-08-25","arxiv_id":"2108.11193","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["itay1itzhak/spellingbee"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-approximate-nearest-neighbour-selection","slug":"on-approximate-nearest-neighbour-selection","title":"On Approximate Nearest Neighbour Selection for Multi-Stage Dense Retrieval","date":"2021-08-25","arxiv_id":"2108.11480","n_code_links":1,"syntology":null},{"paper":null,"slug":"ontology-enhanced-slot-filling","title":"Ontology-Enhanced Slot Filling","date":"2021-08-25","arxiv_id":"2108.11275","n_code_links":0,"syntology":null},{"paper":"/paper/what-do-pre-trained-code-models-know-about","slug":"what-do-pre-trained-code-models-know-about","title":"What do pre-trained code models know about code?","date":"2021-08-25","arxiv_id":"2108.11308","n_code_links":1,"syntology":null},{"paper":"/paper/sigmoidf1-a-smooth-f1-score-surrogate-loss","slug":"sigmoidf1-a-smooth-f1-score-surrogate-loss","title":"sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification","date":"2021-08-24","arxiv_id":"2108.10566","n_code_links":1,"syntology":null}],"record_sha256":"3cfa60c706201763b50302d9eb0055b5e28adb082d9bafb36051d28cd9f91b1f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}