{"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/multi-head-attention/papers/232","list_of":"/method/multi-head-attention","method":"Multi-Head Attention","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":232,"pages_in_order":249,"rows_per_page":100,"rows":[23101,23200],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"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/multi-head-attention","prev":"/method/multi-head-attention/papers/231","next":"/method/multi-head-attention/papers/233","papers":[{"paper":null,"slug":"automated-essay-scoring-system-for-nonnative","title":"Automated Essay Scoring System for Nonnative Japanese Learners","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/bagging-bert-models-for-robust-aggression","slug":"bagging-bert-models-for-robust-aggression","title":"Bagging BERT Models for Robust Aggression Identification","date":"2020-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"building-a-task-oriented-dialog-system-for","title":"Building a Task-oriented Dialog System for Languages with no Training Data: the Case for Basque","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"chinese-discourse-parsing-model-and","title":"Chinese Discourse Parsing: Model and Evaluation","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/clinical-reading-comprehension-a-thorough","slug":"clinical-reading-comprehension-a-thorough","title":"Clinical Reading Comprehension: A Thorough Analysis of the emrQA Dataset","date":"2020-05-01","arxiv_id":"2005.00574","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xiangyue9607/CliniRC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/contextualized-embeddings-based-transformer","slug":"contextualized-embeddings-based-transformer","title":"Contextualized Embeddings based Transformer Encoder for Sentence Similarity Modeling in Answer Selection Task","date":"2020-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"corpora-for-document-level-neural-machine","title":"Corpora for Document-Level Neural Machine Translation","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-and-cross-domain-evaluation-of","title":"Cross-lingual and Cross-domain Evaluation of Machine Reading Comprehension with Squad and CALOR-Quest Corpora","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-zero-pronoun-resolution","title":"Cross-lingual Zero Pronoun Resolution","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cross-linguistic-syntactic-evaluation-of-word","slug":"cross-linguistic-syntactic-evaluation-of-word","title":"Cross-Linguistic Syntactic Evaluation of Word Prediction Models","date":"2020-05-01","arxiv_id":"2005.00187","n_code_links":2,"syntology":null},{"paper":"/paper/dane-a-named-entity-resource-for-danish","slug":"dane-a-named-entity-resource-for-danish","title":"DaNE: A Named Entity Resource for Danish","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"decop-a-multilingual-and-multi-domain-corpus","title":"DecOp: A Multilingual and Multi-domain Corpus For Detecting Deception In Typed Text","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-direct-speech-in-multilingual","title":"Detecting Direct Speech in Multilingual Collection of 19th-century Novels","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"development-and-validation-of-a-corpus-for","title":"Development and Validation of a Corpus for Machine Humor Comprehension","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-metrics-for-headline-generation","title":"Evaluation Metrics for Headline Generation Using Deep Pre-Trained Embeddings","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-dataset-selection-for-pre","title":"Evaluation of Dataset Selection for Pre-Training and Fine-Tuning Transformer Language Models for Clinical Question Answering","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"event-clustering-within-news-articles","title":"Event Clustering within News Articles","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/exploring-transformer-text-generation-for","slug":"exploring-transformer-text-generation-for","title":"Exploring Transformer Text Generation for Medical Dataset Augmentation","date":"2020-05-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"framenet-annotations-alignment-using","title":"FrameNet Annotations Alignment using Attention-based Machine Translation","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"from-web-crawl-to-clean-register-annotated","title":"From Web Crawl to Clean Register-Annotated Corpora","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/global-relational-models-of-source-code","slug":"global-relational-models-of-source-code","title":"Global Relational Models of Source Code","date":"2020-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","n_code_links":3,"syntology":{"ran":10,"of":13,"n_ran_checked":9,"n_instrument":1,"unverified":3,"pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["linjieli222/HERO"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/hiporank-incorporating-hierarchical-and","slug":"hiporank-incorporating-hierarchical-and","title":"Discourse-Aware Unsupervised Summarization of Long Scientific Documents","date":"2020-05-01","arxiv_id":"2005.00513","n_code_links":1,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-12-offensive","title":"Hitachi at SemEval-2020 Task 12: Offensive Language Identification with Noisy Labels using Statistical Sampling and Post-Processing","date":"2020-05-01","arxiv_id":"2005.00295","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-necessary-elements-for-bert-s","slug":"identifying-necessary-elements-for-bert-s","title":"Identifying Necessary Elements for BERT's Multilinguality","date":"2020-05-01","arxiv_id":"2005.00396","n_code_links":1,"syntology":null},{"paper":null,"slug":"implementation-of-supervised-training","title":"Implementation of Supervised Training Approaches for Monolingual Word Sense Alignment: ACDH-CH System Description for the MWSA Shared Task at GlobaLex 2020","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-neural-language-generation-with","title":"Improving Neural Language Generation with Spectrum Control","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/information-seeking-in-the-spirit-of-learning","slug":"information-seeking-in-the-spirit-of-learning","title":"Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity","date":"2020-05-01","arxiv_id":"2005.00172","n_code_links":1,"syntology":null},{"paper":null,"slug":"intermediate-task-transfer-learning-with","title":"Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?","date":"2020-05-01","arxiv_id":"2005.00628","n_code_links":0,"syntology":null},{"paper":null,"slug":"introducing-a-large-scale-dataset-for","title":"Introducing a Large-Scale Dataset for Vietnamese POS Tagging on Conversational Texts","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"irit-at-trac-2020","title":"IRIT at TRAC 2020","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"is-language-modeling-enough-evaluating","title":"Is Language Modeling Enough? Evaluating Effective Embedding Combinations","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/joint-learning-of-syntactic-features-helps","slug":"joint-learning-of-syntactic-features-helps","title":"Joint Learning of Syntactic Features Helps Discourse Segmentation","date":"2020-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/klej-comprehensive-benchmark-for-polish","slug":"klej-comprehensive-benchmark-for-polish","title":"KLEJ: Comprehensive Benchmark for Polish Language Understanding","date":"2020-05-01","arxiv_id":"2005.00630","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["allegro/klejbenchmark-baselines"],"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":"linguistically-informed-hindi-english-neural","title":"Linguistically Informed Hindi-English Neural Machine Translation","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/logic-and-the-2-simplicial-transformer-1","slug":"logic-and-the-2-simplicial-transformer-1","title":"Logic and the 2-Simplicial Transformer","date":"2020-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"massive-vs-curated-embeddings-for-low","title":"Massive vs. Curated Embeddings for Low-Resourced Languages: the Case of Yor\\`ub\\'a and Twi","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"minority-positive-sampling-for-switching","title":"Minority Positive Sampling for Switching Points - an Anecdote for the Code-Mixing Language Modeling","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"much-ado-about-nothing-identification-of-zero","title":"Much Ado About Nothing -- Identification of Zero Copulas in Hungarian Using an NMT Model","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-transformer-language-models","title":"Multi-scale Transformer Language Models","date":"2020-05-01","arxiv_id":"2005.00581","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-corpus-creation-for-multilingual","title":"Multilingual Corpus Creation for Multilingual Semantic Similarity Task","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-joint-fine-tuning-of-transformer","slug":"multilingual-joint-fine-tuning-of-transformer","title":"Multilingual Joint Fine-tuning of Transformer models for identifying Trolling, Aggression and Cyberbullying at TRAC 2020","date":"2020-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/neural-symbolic-reader-scalable-integration","slug":"neural-symbolic-reader-scalable-integration","title":"Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-influence-of-coreference-resolution-on","title":"On the Influence of Coreference Resolution on Word Embeddings in Lexical-semantic Evaluation Tasks","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"one-classifier-for-all-ambiguous-words","title":"One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"paraphrase-generation-and-evaluation-on","title":"Paraphrase Generation and Evaluation on Colloquial-Style Sentences","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"parlvote-a-corpus-for-sentiment-analysis-of","title":"ParlVote: A Corpus for Sentiment Analysis of Political Debates","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"parsing-as-tagging","title":"Parsing as Tagging","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/pointer-constrained-text-generation-via","slug":"pointer-constrained-text-generation-via","title":"POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training","date":"2020-05-01","arxiv_id":"2005.00558","n_code_links":1,"syntology":{"ran":11,"of":18,"n_ran_checked":6,"n_instrument":5,"unverified":7,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","official":{"repos":["dreasysnail/POINTER"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"probing-text-models-for-common-ground-with","title":"Probing Contextual Language Models for Common Ground with Visual Representations","date":"2020-05-01","arxiv_id":"2005.00619","n_code_links":0,"syntology":null},{"paper":null,"slug":"region-based-self-triggered-control-for","title":"Region-Based Self-Triggered Control for Perturbed and Uncertain Nonlinear Systems","date":"2020-05-01","arxiv_id":"2005.00473","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-language-data-import-export-with-a","title":"Scaling Language Data Import/Export with a Data Transformer Interface","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/scirex-a-challenge-dataset-for-document-level","slug":"scirex-a-challenge-dataset-for-document-level","title":"SciREX: A Challenge Dataset for Document-Level Information Extraction","date":"2020-05-01","arxiv_id":"2005.00512","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":["allenai/SciREX"],"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":"scmhl5-at-trac-2-shared-task-on-aggression","title":"Scmhl5 at TRAC-2 Shared Task on Aggression Identification: Bert Based Ensemble Learning Approach","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"seq2seqpy-a-lightweight-and-customizable","title":"Seq2SeqPy: A Lightweight and Customizable Toolkit for Neural Sequence-to-Sequence Modeling","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/sibert-enhanced-chinese-pre-trained-language","slug":"sibert-enhanced-chinese-pre-trained-language","title":"SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion","date":"2020-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"sign-language-recognition-with-transformer","title":"Sign Language Recognition with Transformer Networks","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"termeval-2020-taln-ls2n-system-for-automatic","title":"TermEval 2020: TALN-LS2N System for Automatic Term Extraction","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"text-categorization-for-conflict-event","title":"Text Categorization for Conflict Event Annotation","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tf-idf-character-n-grams-versus-word","title":"TF-IDF Character N-grams versus Word Embedding-based Models for Fine-grained Event Classification: A Preliminary Study","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-ava-kinetics-localized-human-actions","title":"The AVA-Kinetics Localized Human Actions Video Dataset","date":"2020-05-01","arxiv_id":"2005.00214","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-applied-to-text","title":"Transfer learning applied to text classification in Spanish radiological reports","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-user-utterances-in-a-dialog","title":"Understanding User Utterances in a Dialog System for Caregiving","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"when-bert-plays-the-lottery-all-tickets-are","title":"When BERT Plays the Lottery, All Tickets Are Winning","date":"2020-05-01","arxiv_id":"2005.00561","n_code_links":0,"syntology":null},{"paper":"/paper/a-focused-study-to-compare-arabic-pre","slug":"a-focused-study-to-compare-arabic-pre","title":"An Empirical Study of Pre-trained Transformers for Arabic Information Extraction","date":"2020-04-30","arxiv_id":"2004.14519","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-matter-of-framing-the-impact-of-linguistic","title":"A Matter of Framing: The Impact of Linguistic Formalism on Probing Results","date":"2020-04-30","arxiv_id":"2004.14999","n_code_links":0,"syntology":null},{"paper":"/paper/accurate-word-alignment-induction-from-neural","slug":"accurate-word-alignment-induction-from-neural","title":"Accurate Word Alignment Induction from Neural Machine Translation","date":"2020-04-30","arxiv_id":"2004.14837","n_code_links":1,"syntology":null},{"paper":null,"slug":"addressing-zero-resource-domains-using","title":"Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation","date":"2020-04-30","arxiv_id":"2004.14927","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-global-barriers-in-parallel","title":"Breaking (Global) Barriers in Parallel Stochastic Optimization with Wait-Avoiding Group Averaging","date":"2020-04-30","arxiv_id":"2005.00124","n_code_links":0,"syntology":null},{"paper":null,"slug":"capsule-transformer-for-neural-machine","title":"Capsule-Transformer for Neural Machine Translation","date":"2020-04-30","arxiv_id":"2004.14649","n_code_links":0,"syntology":null},{"paper":null,"slug":"character-level-translation-with-self","title":"Character-Level Translation with Self-attention","date":"2020-04-30","arxiv_id":"2004.14788","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-neural-word-alignment-outperforms","title":"End-to-End Neural Word Alignment Outperforms GIZA++","date":"2020-04-30","arxiv_id":"2004.14675","n_code_links":0,"syntology":null},{"paper":null,"slug":"enriched-pre-trained-transformers-for-joint","title":"Enriched Pre-trained Transformers for Joint Slot Filling and Intent Detection","date":"2020-04-30","arxiv_id":"2004.14848","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-contextualized-neural-language","slug":"exploring-contextualized-neural-language","title":"Exploring Contextualized Neural Language Models for Temporal Dependency Parsing","date":"2020-04-30","arxiv_id":"2004.14577","n_code_links":1,"syntology":null},{"paper":"/paper/few-shot-learning-for-abstractive-multi","slug":"few-shot-learning-for-abstractive-multi","title":"Few-Shot Learning for Opinion Summarization","date":"2020-04-30","arxiv_id":"2004.14884","n_code_links":1,"syntology":null},{"paper":"/paper/how-do-decisions-emerge-across-layers-in","slug":"how-do-decisions-emerge-across-layers-in","title":"How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking","date":"2020-04-30","arxiv_id":"2004.14992","n_code_links":2,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 4 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) · 4 unverified","official":{"repos":["nicola-decao/diffmask"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"interpretable-entity-representations-through","title":"Interpretable Entity Representations through Large-Scale Typing","date":"2020-04-30","arxiv_id":"2005.00147","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-transferability-in-pretrained","slug":"investigating-transferability-in-pretrained","title":"Investigating Transferability in Pretrained Language Models","date":"2020-04-30","arxiv_id":"2004.14975","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":["dgiova/bert-lm-transferability"],"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":["found_in_text"]}}},{"paper":"/paper/look-at-the-first-sentence-position-bias-in","slug":"look-at-the-first-sentence-position-bias-in","title":"Look at the First Sentence: Position Bias in Question Answering","date":"2020-04-30","arxiv_id":"2004.14602","n_code_links":1,"syntology":null},{"paper":"/paper/mad-x-an-adapter-based-framework-for-multi","slug":"mad-x-an-adapter-based-framework-for-multi","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","date":"2020-04-30","arxiv_id":"2005.00052","n_code_links":3,"syntology":null},{"paper":"/paper/modular-representation-underlies-systematic","slug":"modular-representation-underlies-systematic","title":"Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation","date":"2020-04-30","arxiv_id":"2004.14623","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-evaluation-of-contextual-embeddings","title":"Don't Use English Dev: On the Zero-Shot Cross-Lingual Evaluation of Contextual Embeddings","date":"2020-04-30","arxiv_id":"2004.15001","n_code_links":0,"syntology":null},{"paper":"/paper/perturbed-masking-parameter-free-probing-for","slug":"perturbed-masking-parameter-free-probing-for","title":"Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT","date":"2020-04-30","arxiv_id":"2004.14786","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":["LividWo/Perturbed-Masking"],"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":"/paper/plotmachines-outline-conditioned-generation","slug":"plotmachines-outline-conditioned-generation","title":"PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking","date":"2020-04-30","arxiv_id":"2004.14967","n_code_links":2,"syntology":{"ran":5,"of":11,"n_ran_checked":5,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["hrashkin/plotmachines"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/progressive-transformers-for-end-to-end-sign","slug":"progressive-transformers-for-end-to-end-sign","title":"Progressive Transformers for End-to-End Sign Language Production","date":"2020-04-30","arxiv_id":"2004.14874","n_code_links":1,"syntology":null},{"paper":null,"slug":"recipes-for-adapting-pre-trained-monolingual","title":"Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation","date":"2020-04-30","arxiv_id":"2004.14911","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-question-answering-through-sub-part","title":"Robust Question Answering Through Sub-part Alignment","date":"2020-04-30","arxiv_id":"2004.14648","n_code_links":0,"syntology":null},{"paper":"/paper/segabert-pre-training-of-segment-aware-bert","slug":"segabert-pre-training-of-segment-aware-bert","title":"Segatron: Segment-Aware Transformer for Language Modeling and Understanding","date":"2020-04-30","arxiv_id":"2004.14996","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-and-controlled-multi-document","title":"Self-Supervised and Controlled Multi-Document Opinion Summarization","date":"2020-04-30","arxiv_id":"2004.14754","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-triple-encoder-for-fast-open-set","slug":"semantic-triple-encoder-for-fast-open-set","title":"Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion","date":"2020-04-30","arxiv_id":"2004.14781","n_code_links":1,"syntology":null},{"paper":"/paper/textat-adversarial-training-for-natural","slug":"textat-adversarial-training-for-natural","title":"TAVAT: Token-Aware Virtual Adversarial Training for Language Understanding","date":"2020-04-30","arxiv_id":"2004.14543","n_code_links":1,"syntology":null},{"paper":"/paper/universal-dependencies-according-to-bert-both","slug":"universal-dependencies-according-to-bert-both","title":"Universal Dependencies according to BERT: both more specific and more general","date":"2020-04-30","arxiv_id":"2004.14620","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["Tom556/BERTHeadEnsembles"],"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/wic-tsv-an-evaluation-benchmark-for-target","slug":"wic-tsv-an-evaluation-benchmark-for-target","title":"WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context","date":"2020-04-30","arxiv_id":"2004.15016","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-supervised-word-alignment-method-based-on","title":"A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT","date":"2020-04-29","arxiv_id":"2004.14516","n_code_links":0,"syntology":null},{"paper":"/paper/analysing-lexical-semantic-change-with","slug":"analysing-lexical-semantic-change-with","title":"Analysing Lexical Semantic Change with Contextualised Word Representations","date":"2020-04-29","arxiv_id":"2004.14118","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["glnmario/cwr4lsc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"asking-without-telling-exploring-latent","title":"Asking without Telling: Exploring Latent Ontologies in Contextual Representations","date":"2020-04-29","arxiv_id":"2004.14513","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilingual-text-extraction-as-reading","title":"Bilingual Text Extraction as Reading Comprehension","date":"2020-04-29","arxiv_id":"2004.14517","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-perceived-emotions-in-hurricane","slug":"detecting-perceived-emotions-in-hurricane","title":"Detecting Perceived Emotions in Hurricane Disasters","date":"2020-04-29","arxiv_id":"2004.14299","n_code_links":1,"syntology":null},{"paper":"/paper/distantly-supervised-neural-relation","slug":"distantly-supervised-neural-relation","title":"Distantly-Supervised Neural Relation Extraction with Side Information using BERT","date":"2020-04-29","arxiv_id":"2004.14443","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-neural-language-models-show-preferences","title":"Do Neural Language Models Show Preferences for Syntactic Formalisms?","date":"2020-04-29","arxiv_id":"2004.14096","n_code_links":0,"syntology":null}],"record_sha256":"14be27cc9f31bc711c458881b0f542ea22e3686d4a73c048d3c2154e41ce371f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}