{"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/attention-dropout/papers/97","list_of":"/method/attention-dropout","method":"Attention Dropout","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":97,"pages_in_order":109,"rows_per_page":100,"rows":[9601,9700],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"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/attention-dropout","prev":"/method/attention-dropout/papers/96","next":"/method/attention-dropout/papers/98","papers":[{"paper":"/paper/query-focused-multi-document-summarisation-of-1","slug":"query-focused-multi-document-summarisation-of-1","title":"Query Focused Multi-document Summarisation of Biomedical Texts: Macquarie Universiy and the Australian National University at BioASQ8b","date":"2020-08-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"apmsqueeze-a-communication-efficient-adam","title":"APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD Algorithm","date":"2020-08-26","arxiv_id":"2008.11343","n_code_links":0,"syntology":null},{"paper":null,"slug":"discrete-word-embedding-for-logical-natural","title":"Discrete Word Embedding for Logical Natural Language Understanding","date":"2020-08-26","arxiv_id":"2008.11649","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-and-word-sense-disambiguation","slug":"language-models-and-word-sense-disambiguation","title":"Analysis and Evaluation of Language Models for Word Sense Disambiguation","date":"2020-08-26","arxiv_id":"2008.11608","n_code_links":1,"syntology":null},{"paper":null,"slug":"conceptualized-representation-learning-for","title":"Conceptualized Representation Learning for Chinese Biomedical Text Mining","date":"2020-08-25","arxiv_id":"2008.10813","n_code_links":0,"syntology":null},{"paper":"/paper/etc-nlg-end-to-end-topic-conditioned-natural","slug":"etc-nlg-end-to-end-topic-conditioned-natural","title":"ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation","date":"2020-08-25","arxiv_id":"2008.10875","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamics-of-feed-forward-induced-interference","title":"Dynamics of feed forward induced interference training","date":"2020-08-24","arxiv_id":"2008.11111","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-empowered-representation-learning","slug":"knowledge-empowered-representation-learning","title":"Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources","date":"2020-08-24","arxiv_id":"2008.10327","n_code_links":1,"syntology":null},{"paper":null,"slug":"prediction-of-icd-codes-with-clinical-bert","title":"Prediction of ICD Codes with Clinical BERT Embeddings and Text Augmentation with Label Balancing using MIMIC-III","date":"2020-08-24","arxiv_id":"2008.10492","n_code_links":0,"syntology":null},{"paper":null,"slug":"syrapropa-at-semeval-2020-task-11-bert-based","title":"syrapropa at SemEval-2020 Task 11: BERT-based Models Design For Propagandistic Technique and Span Detection","date":"2020-08-24","arxiv_id":"2008.10163","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-stages-approach-for-tweet-engagement","title":"Two Stages Approach for Tweet Engagement Prediction","date":"2020-08-24","arxiv_id":"2008.10419","n_code_links":0,"syntology":null},{"paper":"/paper/ynu-hpcc-at-semeval-2020-task-11-lstm-network","slug":"ynu-hpcc-at-semeval-2020-task-11-lstm-network","title":"YNU-HPCC at SemEval-2020 Task 11: LSTM Network for Detection of Propaganda Techniques in News Articles","date":"2020-08-24","arxiv_id":"2008.10166","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["daojiaxu/semeval_11"],"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":["official"]}}},{"paper":null,"slug":"applications-of-bert-based-sequence-tagging","title":"Applications of BERT Based Sequence Tagging Models on Chinese Medical Text Attributes Extraction","date":"2020-08-22","arxiv_id":"2008.09740","n_code_links":0,"syntology":null},{"paper":"/paper/cyberwalle-at-semeval-2020-task-11-an","slug":"cyberwalle-at-semeval-2020-task-11-an","title":"CyberWallE at SemEval-2020 Task 11: An Analysis of Feature Engineering for Ensemble Models for Propaganda Detection","date":"2020-08-22","arxiv_id":"2008.09859","n_code_links":1,"syntology":null},{"paper":"/paper/duth-at-semeval-2020-task-11-bert-with-entity","slug":"duth-at-semeval-2020-task-11-bert-with-entity","title":"DUTH at SemEval-2020 Task 11: BERT with Entity Mapping for Propaganda Classification","date":"2020-08-22","arxiv_id":"2008.09894","n_code_links":1,"syntology":null},{"paper":"/paper/fat-albert-finding-answers-in-large-texts","slug":"fat-albert-finding-answers-in-large-texts","title":"FAT ALBERT: Finding Answers in Large Texts using Semantic Similarity Attention Layer based on BERT","date":"2020-08-22","arxiv_id":"2009.01004","n_code_links":1,"syntology":null},{"paper":"/paper/hinglishnlp-fine-tuned-language-models-for","slug":"hinglishnlp-fine-tuned-language-models-for","title":"HinglishNLP: Fine-tuned Language Models for Hinglish Sentiment Detection","date":"2020-08-22","arxiv_id":"2008.09820","n_code_links":2,"syntology":null},{"paper":"/paper/abstractive-summarization-of-spoken","slug":"abstractive-summarization-of-spoken","title":"Abstractive Summarization of Spoken andWritten Instructions with BERT","date":"2020-08-21","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"adapting-event-extractors-to-medical-data","title":"Adapting Event Extractors to Medical Data: Bridging the Covariate Shift","date":"2020-08-21","arxiv_id":"2008.09266","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-experimental-study-of-deep-neural-network","title":"An Experimental Study of Deep Neural Network Models for Vietnamese Multiple-Choice Reading Comprehension","date":"2020-08-20","arxiv_id":"2008.08810","n_code_links":0,"syntology":null},{"paper":"/paper/lite-training-strategies-for-portuguese","slug":"lite-training-strategies-for-portuguese","title":"Lite Training Strategies for Portuguese-English and English-Portuguese Translation","date":"2020-08-20","arxiv_id":"2008.08769","n_code_links":1,"syntology":null},{"paper":"/paper/parade-passage-representation-aggregation-for","slug":"parade-passage-representation-aggregation-for","title":"PARADE: Passage Representation Aggregation for Document Reranking","date":"2020-08-20","arxiv_id":"2008.09093","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["canjiali/PARADE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/ptt5-pretraining-and-validating-the-t5-model","slug":"ptt5-pretraining-and-validating-the-t5-model","title":"PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data","date":"2020-08-20","arxiv_id":"2008.09144","n_code_links":3,"syntology":null},{"paper":"/paper/top2vec-distributed-representations-of-topics","slug":"top2vec-distributed-representations-of-topics","title":"Top2Vec: Distributed Representations of Topics","date":"2020-08-19","arxiv_id":"2008.09470","n_code_links":2,"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":["ddangelov/Top2Vec"],"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":"uob-at-semeval-2020-task-12-boosting-bert","title":"UoB at SemEval-2020 Task 12: Boosting BERT with Corpus Level Information","date":"2020-08-19","arxiv_id":"2008.08547","n_code_links":0,"syntology":null},{"paper":null,"slug":"ranking-clarification-questions-via-natural","title":"Ranking Clarification Questions via Natural Language Inference","date":"2020-08-18","arxiv_id":"2008.07688","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-models-are-unsupervised-predictors","title":"Generative Models are Unsupervised Predictors of Page Quality: A Colossal-Scale Study","date":"2020-08-17","arxiv_id":"2008.13533","n_code_links":0,"syntology":null},{"paper":null,"slug":"narrative-interpolation-for-generating-and","title":"Narrative Interpolation for Generating and Understanding Stories","date":"2020-08-17","arxiv_id":"2008.07466","n_code_links":0,"syntology":null},{"paper":null,"slug":"stock-index-prediction-with-multi-task","title":"Stock Index Prediction with Multi-task Learning and Word Polarity Over Time","date":"2020-08-17","arxiv_id":"2008.07605","n_code_links":0,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers","title":"Adding Recurrence to Pretrained Transformers for Improved Efficiency and Context Size","date":"2020-08-16","arxiv_id":"2008.07027","n_code_links":0,"syntology":null},{"paper":"/paper/devlbert-learning-deconfounded-visio","slug":"devlbert-learning-deconfounded-visio","title":"DeVLBert: Learning Deconfounded Visio-Linguistic Representations","date":"2020-08-16","arxiv_id":"2008.06884","n_code_links":1,"syntology":null},{"paper":null,"slug":"finding-fast-transformers-one-shot-neural","title":"Finding Fast Transformers: One-Shot Neural Architecture Search by Component Composition","date":"2020-08-15","arxiv_id":"2008.06808","n_code_links":0,"syntology":null},{"paper":"/paper/jointly-fine-tuning-bert-like-self-supervised","slug":"jointly-fine-tuning-bert-like-self-supervised","title":"Jointly Fine-Tuning \"BERT-like\" Self Supervised Models to Improve Multimodal Speech Emotion Recognition","date":"2020-08-15","arxiv_id":"2008.06682","n_code_links":1,"syntology":null},{"paper":"/paper/jointly-fine-tuning-bert-like-self-supervised-1","slug":"jointly-fine-tuning-bert-like-self-supervised-1","title":"Jointly Fine-Tuning “BERT-like” Self Supervised Models to Improve Multimodal Speech Emotion Recognition","date":"2020-08-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hate-speech-detection-and-racial-bias","title":"Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model","date":"2020-08-14","arxiv_id":"2008.06460","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-as-few-shot-learner-for-task","title":"Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems","date":"2020-08-14","arxiv_id":"2008.06239","n_code_links":0,"syntology":null},{"paper":"/paper/andes-at-semeval-2020-task-12-a-jointly","slug":"andes-at-semeval-2020-task-12-a-jointly","title":"ANDES at SemEval-2020 Task 12: A jointly-trained BERT multilingual model for offensive language detection","date":"2020-08-13","arxiv_id":"2008.06408","n_code_links":1,"syntology":null},{"paper":"/paper/mice-mining-idioms-with-contextual-embeddings","slug":"mice-mining-idioms-with-contextual-embeddings","title":"MICE: Mining Idioms with Contextual Embeddings","date":"2020-08-13","arxiv_id":"2008.05759","n_code_links":1,"syntology":null},{"paper":null,"slug":"variance-reduced-language-pretraining-via-a","title":"Variance-reduced Language Pretraining via a Mask Proposal Network","date":"2020-08-12","arxiv_id":"2008.05333","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-lexical-a-semantic-retrieval-framework","title":"Beyond Lexical: A Semantic Retrieval Framework for Textual SearchEngine","date":"2020-08-10","arxiv_id":"2008.03917","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-bert-solve-commonsense-task-via","title":"On Commonsense Cues in BERT for Solving Commonsense Tasks","date":"2020-08-10","arxiv_id":"2008.03945","n_code_links":0,"syntology":null},{"paper":"/paper/firebert-hardening-bert-based-classifiers","slug":"firebert-hardening-bert-based-classifiers","title":"FireBERT: Hardening BERT-based classifiers against adversarial attack","date":"2020-08-10","arxiv_id":"2008.04203","n_code_links":1,"syntology":null},{"paper":null,"slug":"ganbert-generative-adversarial-networks-with","title":"GANBERT: Generative Adversarial Networks with Bidirectional Encoder Representations from Transformers for MRI to PET synthesis","date":"2020-08-10","arxiv_id":"2008.04393","n_code_links":0,"syntology":null},{"paper":"/paper/kr-bert-a-small-scale-korean-specific","slug":"kr-bert-a-small-scale-korean-specific","title":"KR-BERT: A Small-Scale Korean-Specific Language Model","date":"2020-08-10","arxiv_id":"2008.03979","n_code_links":1,"syntology":null},{"paper":null,"slug":"navigating-language-models-with-synthetic","title":"Navigating Human Language Models with Synthetic Agents","date":"2020-08-10","arxiv_id":"2008.04162","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-the-knowledge-of-bert-for-sequence","slug":"distilling-the-knowledge-of-bert-for-sequence","title":"Distilling the Knowledge of BERT for Sequence-to-Sequence ASR","date":"2020-08-09","arxiv_id":"2008.03822","n_code_links":1,"syntology":null},{"paper":"/paper/fast-and-accurate-neural-crf-constituency-1","slug":"fast-and-accurate-neural-crf-constituency-1","title":"Fast and Accurate Neural CRF Constituency Parsing","date":"2020-08-09","arxiv_id":"2008.03736","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yzhangcs/crfpar"],"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":["found_in_text","official"]}}},{"paper":null,"slug":"semeval-2020-task-10-emphasis-selection-for","title":"SemEval-2020 Task 10: Emphasis Selection for Written Text in Visual Media","date":"2020-08-07","arxiv_id":"2008.03274","n_code_links":0,"syntology":null},{"paper":"/paper/aschern-at-semeval-2020-task-11-it-takes","slug":"aschern-at-semeval-2020-task-11-it-takes","title":"aschern at SemEval-2020 Task 11: It Takes Three to Tango: RoBERTa, CRF, and Transfer Learning","date":"2020-08-06","arxiv_id":"2008.02837","n_code_links":1,"syntology":null},{"paper":"/paper/convbert-improving-bert-with-span-based","slug":"convbert-improving-bert-with-span-based","title":"ConvBERT: Improving BERT with Span-based Dynamic Convolution","date":"2020-08-06","arxiv_id":"2008.02496","n_code_links":8,"syntology":null},{"paper":"/paper/detext-a-deep-text-ranking-framework-with","slug":"detext-a-deep-text-ranking-framework-with","title":"DeText: A Deep Text Ranking Framework with BERT","date":"2020-08-06","arxiv_id":"2008.02460","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["linkedin/detext"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/i-aid-identifying-actionable-information-from","slug":"i-aid-identifying-actionable-information-from","title":"I-AID: Identifying Actionable Information from Disaster-related Tweets","date":"2020-08-04","arxiv_id":"2008.13544","n_code_links":1,"syntology":null},{"paper":"/paper/nlpdove-at-semeval-2020-task-12-improving","slug":"nlpdove-at-semeval-2020-task-12-improving","title":"NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer","date":"2020-08-04","arxiv_id":"2008.01354","n_code_links":1,"syntology":null},{"paper":null,"slug":"taking-notes-on-the-fly-helps-bert-pre","title":"Taking Notes on the Fly Helps BERT Pre-training","date":"2020-08-04","arxiv_id":"2008.01466","n_code_links":0,"syntology":null},{"paper":"/paper/improving-one-stage-visual-grounding-by","slug":"improving-one-stage-visual-grounding-by","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","date":"2020-08-03","arxiv_id":"2008.01059","n_code_links":1,"syntology":{"ran":20,"of":22,"n_ran_checked":19,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zyang-ur/ReSC"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lt-helsinki-at-semeval-2020-task-12","title":"LT@Helsinki at SemEval-2020 Task 12: Multilingual or language-specific BERT?","date":"2020-08-03","arxiv_id":"2008.00805","n_code_links":0,"syntology":null},{"paper":null,"slug":"musicoder-a-universal-music-acoustic-encoder","title":"MusiCoder: A Universal Music-Acoustic Encoder Based on Transformers","date":"2020-08-03","arxiv_id":"2008.00781","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-node-bert-pretraining-cost-efficient","title":"Multi-node Bert-pretraining: Cost-efficient Approach","date":"2020-08-01","arxiv_id":"2008.00177","n_code_links":0,"syntology":null},{"paper":"/paper/trojaning-language-models-for-fun-and-profit","slug":"trojaning-language-models-for-fun-and-profit","title":"Trojaning Language Models for Fun and Profit","date":"2020-08-01","arxiv_id":"2008.00312","n_code_links":1,"syntology":null},{"paper":"/paper/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","n_code_links":2,"syntology":null},{"paper":null,"slug":"model-reduction-of-shallow-cnn-model-for","title":"Model Reduction of Shallow CNN Model for Reliable Deployment of Information Extraction from Medical Reports","date":"2020-07-31","arxiv_id":"2008.01572","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-learning-universal-representations-across","title":"On Learning Universal Representations Across Languages","date":"2020-07-31","arxiv_id":"2007.15960","n_code_links":0,"syntology":null},{"paper":"/paper/tweepfake-about-detecting-deepfake-tweets","slug":"tweepfake-about-detecting-deepfake-tweets","title":"TweepFake: about Detecting Deepfake Tweets","date":"2020-07-31","arxiv_id":"2008.00036","n_code_links":1,"syntology":null},{"paper":null,"slug":"depressive-drug-abusive-or-informative","title":"Depressive, Drug Abusive, or Informative: Knowledge-aware Study of News Exposure during COVID-19 Outbreak","date":"2020-07-30","arxiv_id":"2007.15209","n_code_links":0,"syntology":null},{"paper":"/paper/mkqa-a-linguistically-diverse-benchmark-for","slug":"mkqa-a-linguistically-diverse-benchmark-for","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","date":"2020-07-30","arxiv_id":"2007.15207","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["apple/ml-mkqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-does-bert-know-about-books-movies-and","slug":"what-does-bert-know-about-books-movies-and","title":"What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation","date":"2020-07-30","arxiv_id":"2007.15356","n_code_links":1,"syntology":null},{"paper":"/paper/composer-style-classification-of-piano-sheet","slug":"composer-style-classification-of-piano-sheet","title":"Composer Style Classification of Piano Sheet Music Images Using Language Model Pretraining","date":"2020-07-29","arxiv_id":"2007.14587","n_code_links":1,"syntology":null},{"paper":"/paper/but-fit-at-semeval-2020-task-5-automatic","slug":"but-fit-at-semeval-2020-task-5-automatic","title":"BUT-FIT at SemEval-2020 Task 5: Automatic detection of counterfactual statements with deep pre-trained language representation models","date":"2020-07-28","arxiv_id":"2007.14128","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-brasil-nlp-at-semeval-2020-task","title":"Deep Learning Brasil -- NLP at SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweets","date":"2020-07-28","arxiv_id":"2008.01544","n_code_links":0,"syntology":null},{"paper":null,"slug":"guir-at-semeval-2020-task-12-domain-tuned","title":"GUIR at SemEval-2020 Task 12: Domain-Tuned Contextualized Models for Offensive Language Detection","date":"2020-07-28","arxiv_id":"2007.14477","n_code_links":0,"syntology":null},{"paper":"/paper/improving-results-on-russian-sentiment","slug":"improving-results-on-russian-sentiment","title":"Improving Results on Russian Sentiment Datasets","date":"2020-07-28","arxiv_id":"2007.14310","n_code_links":1,"syntology":null},{"paper":null,"slug":"variants-of-bert-random-forests-and-svm","title":"Variants of BERT, Random Forests and SVM approach for Multimodal Emotion-Target Sub-challenge","date":"2020-07-28","arxiv_id":"2007.13928","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedemail-performance-measurement-of-privacy","title":"Evaluation of Federated Learning in Phishing Email Detection","date":"2020-07-27","arxiv_id":"2007.13300","n_code_links":0,"syntology":null},{"paper":"/paper/kuisail-at-semeval-2020-task-12-bert-cnn-for","slug":"kuisail-at-semeval-2020-task-12-bert-cnn-for","title":"KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media","date":"2020-07-26","arxiv_id":"2007.13184","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alisafaya/OffensEval2020"],"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":"reed-at-semeval-2020-task-9-sentiment","title":"Reed at SemEval-2020 Task 9: Fine-Tuning and Bag-of-Words Approaches to Code-Mixed Sentiment Analysis","date":"2020-07-26","arxiv_id":"2007.13061","n_code_links":0,"syntology":null},{"paper":null,"slug":"to-bert-or-not-to-bert-comparing-speech-and","title":"To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection","date":"2020-07-26","arxiv_id":"2008.01551","n_code_links":0,"syntology":null},{"paper":"/paper/multisem-at-semeval-2020-task-3-fine-tuning","slug":"multisem-at-semeval-2020-task-3-fine-tuning","title":"MULTISEM at SemEval-2020 Task 3: Fine-tuning BERT for Lexical Meaning","date":"2020-07-24","arxiv_id":"2007.12432","n_code_links":1,"syntology":null},{"paper":null,"slug":"product-title-generation-for-conversational","title":"Product Title Generation for Conversational Systems using BERT","date":"2020-07-23","arxiv_id":"2007.11768","n_code_links":0,"syntology":null},{"paper":"/paper/the-lottery-ticket-hypothesis-for-pre-trained","slug":"the-lottery-ticket-hypothesis-for-pre-trained","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","date":"2020-07-23","arxiv_id":"2007.12223","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":4,"n_instrument":5,"unverified":2,"pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["TAMU-VITA/BERT-Tickets","VITA-Group/BERT-Tickets"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"iitk-at-the-finsim-task-hypernym-detection-in","title":"IITK at the FinSim Task: Hypernym Detection in Financial Domain via Context-Free and Contextualized Word Embeddings","date":"2020-07-22","arxiv_id":"2007.11201","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-learning-for-natural-language-1","title":"Multi-task learning for natural language processing in the 2020s: where are we going?","date":"2020-07-22","arxiv_id":"2007.16008","n_code_links":0,"syntology":null},{"paper":"/paper/check-square-at-checkthat-2020-claim","slug":"check-square-at-checkthat-2020-claim","title":"Check_square at CheckThat! 2020: Claim Detection in Social Media via Fusion of Transformer and Syntactic Features","date":"2020-07-21","arxiv_id":"2007.10534","n_code_links":1,"syntology":null},{"paper":"/paper/newssweeper-at-semeval-2020-task-11-context","slug":"newssweeper-at-semeval-2020-task-11-context","title":"newsSweeper at SemEval-2020 Task 11: Context-Aware Rich Feature Representations For Propaganda Classification","date":"2020-07-21","arxiv_id":"2007.10827","n_code_links":1,"syntology":null},{"paper":"/paper/problemconquero-at-semeval-2020-task-12","slug":"problemconquero-at-semeval-2020-task-12","title":"problemConquero at SemEval-2020 Task 12: Transformer and Soft label-based approaches","date":"2020-07-21","arxiv_id":"2007.10877","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-bert-rankers-under-distillation","title":"Understanding BERT Rankers Under Distillation","date":"2020-07-21","arxiv_id":"2007.11088","n_code_links":0,"syntology":null},{"paper":"/paper/word-representation-for-rhythms","slug":"word-representation-for-rhythms","title":"Word Representation for Rhythms","date":"2020-07-21","arxiv_id":"2007.10610","n_code_links":1,"syntology":null},{"paper":"/paper/a-comparison-of-supervised-learning-to-match","slug":"a-comparison-of-supervised-learning-to-match","title":"A Comparison of Supervised Learning to Match Methods for Product Search","date":"2020-07-20","arxiv_id":"2007.10296","n_code_links":1,"syntology":null},{"paper":"/paper/mono-vs-multilingual-transformer-based-models","slug":"mono-vs-multilingual-transformer-based-models","title":"Mono vs Multilingual Transformer-based Models: a Comparison across Several Language Tasks","date":"2020-07-19","arxiv_id":"2007.09757","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-perspective-semantic-information","title":"Multi-Perspective Semantic Information Retrieval in the Biomedical Domain","date":"2020-07-17","arxiv_id":"2008.01526","n_code_links":0,"syntology":null},{"paper":"/paper/hopfield-networks-is-all-you-need","slug":"hopfield-networks-is-all-you-need","title":"Hopfield Networks is All You Need","date":"2020-07-16","arxiv_id":"2008.02217","n_code_links":3,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ml-jku/hopfield-layers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/investigating-pretrained-language-models-for","slug":"investigating-pretrained-language-models-for","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","date":"2020-07-16","arxiv_id":"2007.08426","n_code_links":3,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":2,"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) · 3 unverified","official":{"repos":["UKPLab/plms-graph2text"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-debiasing-sentence-representations-1","slug":"towards-debiasing-sentence-representations-1","title":"Towards Debiasing Sentence Representations","date":"2020-07-16","arxiv_id":"2007.08100","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pliang279/sent_debias"],"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":null,"slug":"translate-reverberated-speech-to-anechoic","title":"Translate Reverberated Speech to Anechoic Ones: Speech Dereverberation with BERT","date":"2020-07-16","arxiv_id":"2007.08052","n_code_links":0,"syntology":null},{"paper":"/paper/adapterhub-a-framework-for-adapting","slug":"adapterhub-a-framework-for-adapting","title":"AdapterHub: A Framework for Adapting Transformers","date":"2020-07-15","arxiv_id":"2007.07779","n_code_links":9,"syntology":{"ran":11,"of":15,"n_ran_checked":11,"n_instrument":0,"unverified":4,"pointer_only":12,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["Adapter-Hub/Hub","Adapter-Hub/adapter-transformers"],"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":["listed","official"]}}},{"paper":null,"slug":"deep-reinforced-query-reformulation-for","title":"Deep Reinforced Query Reformulation for Information Retrieval","date":"2020-07-15","arxiv_id":"2007.07987","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tune-longformer-for-jointly-predicting","title":"Fine-Tune Longformer for Jointly Predicting Rumor Stance and Veracity","date":"2020-07-15","arxiv_id":"2007.07803","n_code_links":0,"syntology":null},{"paper":"/paper/logic-constrained-pointer-networks-for","slug":"logic-constrained-pointer-networks-for","title":"Logic Constrained Pointer Networks for Interpretable Textual Similarity","date":"2020-07-15","arxiv_id":"2007.07670","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-word-sense-disambiguation-in","slug":"multimodal-word-sense-disambiguation-in","title":"Multimodal Word Sense Disambiguation in Creative Practice","date":"2020-07-15","arxiv_id":"2007.07758","n_code_links":1,"syntology":null},{"paper":"/paper/overview-of-checkthat-2020-automatic","slug":"overview-of-checkthat-2020-automatic","title":"Overview of CheckThat! 2020: Automatic Identification and Verification of Claims in Social Media","date":"2020-07-15","arxiv_id":"2007.07997","n_code_links":3,"syntology":null},{"paper":null,"slug":"predicting-clinical-diagnosis-from-patients","title":"Predicting Clinical Diagnosis from Patients Electronic Health Records Using BERT-based Neural Networks","date":"2020-07-15","arxiv_id":"2007.07562","n_code_links":0,"syntology":null}],"record_sha256":"6ce5d5d4651e615fc97f477144309925b63a01b9728652bdf0c4c4c9c482a824","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}