{"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/98","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":98,"pages_in_order":109,"rows_per_page":100,"rows":[9701,9800],"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/97","next":"/method/attention-dropout/papers/99","papers":[{"paper":null,"slug":"add-a-sidenet-to-your-mainnet","title":"Add a SideNet to your MainNet","date":"2020-07-14","arxiv_id":"2007.13512","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-on-robustness-to-spurious","slug":"an-empirical-study-on-robustness-to-spurious","title":"An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models","date":"2020-07-14","arxiv_id":"2007.06778","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-neural-networks-acquire-a-structural-bias","title":"Can neural networks acquire a structural bias from raw linguistic data?","date":"2020-07-14","arxiv_id":"2007.06761","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-transformer-based-data-augmentation-with","title":"Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR","date":"2020-07-14","arxiv_id":"2007.06949","n_code_links":0,"syntology":null},{"paper":"/paper/emoji-prediction-extensions-and-benchmarking","slug":"emoji-prediction-extensions-and-benchmarking","title":"Emoji Prediction: Extensions and Benchmarking","date":"2020-07-14","arxiv_id":"2007.07389","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-memory-placement-using","title":"Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning","date":"2020-07-14","arxiv_id":"2007.07298","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-s-in-a-name-are-bert-named-entity-1","title":"What's in a Name? Are BERT Named Entity Representations just as Good for any other Name?","date":"2020-07-14","arxiv_id":"2007.06897","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-enhanced-text-classification-to-explore","title":"An Enhanced Text Classification to Explore Health based Indian Government Policy Tweets","date":"2020-07-13","arxiv_id":"2007.06511","n_code_links":0,"syntology":null},{"paper":null,"slug":"hypergrid-efficient-multi-task-transformers","title":"HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections","date":"2020-07-12","arxiv_id":"2007.05891","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-learns-and-teaches-chemistry","title":"BERT Learns (and Teaches) Chemistry","date":"2020-07-11","arxiv_id":"2007.16012","n_code_links":0,"syntology":null},{"paper":"/paper/generative-graph-perturbations-for-scene","slug":"generative-graph-perturbations-for-scene","title":"Generative Compositional Augmentations for Scene Graph Prediction","date":"2020-07-11","arxiv_id":"2007.05756","n_code_links":1,"syntology":null},{"paper":"/paper/bison-bm25-weighted-self-attention-framework","slug":"bison-bm25-weighted-self-attention-framework","title":"GLOW : Global Weighted Self-Attention Network for Web Search","date":"2020-07-10","arxiv_id":"2007.05186","n_code_links":1,"syntology":null},{"paper":"/paper/multi-dialect-arabic-bert-for-country-level","slug":"multi-dialect-arabic-bert-for-country-level","title":"Multi-Dialect Arabic BERT for Country-Level Dialect Identification","date":"2020-07-10","arxiv_id":"2007.05612","n_code_links":1,"syntology":null},{"paper":null,"slug":"to-ban-or-not-to-ban-bayesian-attention","title":"To BAN or not to BAN: Bayesian Attention Networks for Reliable Hate Speech Detection","date":"2020-07-10","arxiv_id":"2007.05304","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-code-representation-learning","slug":"contrastive-code-representation-learning","title":"Contrastive Code Representation Learning","date":"2020-07-09","arxiv_id":"2007.04973","n_code_links":1,"syntology":null},{"paper":"/paper/fast-transformers-with-clustered-attention","slug":"fast-transformers-with-clustered-attention","title":"Fast Transformers with Clustered Attention","date":"2020-07-09","arxiv_id":"2007.04825","n_code_links":1,"syntology":null},{"paper":"/paper/continual-bert-continual-learning-for","slug":"continual-bert-continual-learning-for","title":"Continual BERT: Continual Learning for Adaptive Extractive Summarization of COVID-19 Literature","date":"2020-07-07","arxiv_id":"2007.03405","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-heterogeneous-information-networks","title":"Pre-Trained Models for Heterogeneous Information Networks","date":"2020-07-07","arxiv_id":"2007.03184","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-go-transformer-natural-language-modeling","title":"The Go Transformer: Natural Language Modeling for Game Play","date":"2020-07-07","arxiv_id":"2007.03500","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-contextual-embeddings-for-address","title":"Deep Contextual Embeddings for Address Classification in E-commerce","date":"2020-07-06","arxiv_id":"2007.03020","n_code_links":0,"syntology":null},{"paper":null,"slug":"you-autocomplete-me-poisoning-vulnerabilities","title":"You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion","date":"2020-07-05","arxiv_id":"2007.02220","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-prediction-of-punctuation-and-1","title":"Robust Prediction of Punctuation and Truecasing for Medical ASR","date":"2020-07-04","arxiv_id":"2007.02025","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-data-augmentation-towards-better","title":"Text Data Augmentation: Towards better detection of spear-phishing emails","date":"2020-07-04","arxiv_id":"2007.02033","n_code_links":0,"syntology":null},{"paper":"/paper/language-agnostic-bert-sentence-embedding","slug":"language-agnostic-bert-sentence-embedding","title":"Language-agnostic BERT Sentence Embedding","date":"2020-07-03","arxiv_id":"2007.01852","n_code_links":6,"syntology":null},{"paper":null,"slug":"mira-leveraging-multi-intention-co-click","title":"MIRA: Leveraging Multi-Intention Co-click Information in Web-scale Document Retrieval using Deep Neural Networks","date":"2020-07-03","arxiv_id":"2007.01510","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-fly-information-retrieval-augmentation-1","title":"On-The-Fly Information Retrieval Augmentation for Language Models","date":"2020-07-03","arxiv_id":"2007.01528","n_code_links":0,"syntology":null},{"paper":"/paper/playing-with-words-at-the-national-library-of","slug":"playing-with-words-at-the-national-library-of","title":"Playing with Words at the National Library of Sweden -- Making a Swedish BERT","date":"2020-07-03","arxiv_id":"2007.01658","n_code_links":1,"syntology":null},{"paper":null,"slug":"pretrained-semantic-speech-embeddings-for-end","title":"Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning","date":"2020-07-03","arxiv_id":"2007.01836","n_code_links":0,"syntology":null},{"paper":null,"slug":"reading-comprehension-in-czech-via-machine","title":"Reading Comprehension in Czech via Machine Translation and Cross-lingual Transfer","date":"2020-07-03","arxiv_id":"2007.01667","n_code_links":0,"syntology":null},{"paper":null,"slug":"bidirectional-encoder-representations-from","title":"Bidirectional Encoder Representations from Transformers (BERT): A sentiment analysis odyssey","date":"2020-07-02","arxiv_id":"2007.01127","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-event-detection-using-contextual","title":"Detecting Ongoing Events Using Contextual Word and Sentence Embeddings","date":"2020-07-02","arxiv_id":"2007.01379","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-explanations-on-ai-competency","title":"The Impact of Explanations on AI Competency Prediction in VQA","date":"2020-07-02","arxiv_id":"2007.00900","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bert-based-one-pass-multi-task-model-for","title":"A BERT-based One-Pass Multi-Task Model for Clinical Temporal Relation Extraction","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-generate-and-rank-framework-with-semantic","title":"A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-metric-learning-approach-to-misogyny","title":"A Metric Learning Approach to Misogyny Categorization","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-simple-and-effective-dependency-parser-for","title":"A Simple and Effective Dependency Parser for Telugu","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-transformer-approach-to-contextual-sarcasm","title":"A Transformer Approach to Contextual Sarcasm Detection in Twitter","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-and-domain-aware-bert-for-cross","title":"Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-evaluation-of-bert-for-biomedical","title":"Adversarial Evaluation of BERT for Biomedical Named Entity Recognition","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-citation-texts-in","title":"Automatic Generation of Citation Texts in Scholarly Papers: A Pilot Study","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"character-aware-models-with-similarity","title":"Character aware models with similarity learning for metaphor detection","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-sarcasm-detection-using-bert","title":"Context-Aware Sarcasm Detection Using BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-and-non-contextual-word-embeddings","title":"Contextual and Non-Contextual Word Embeddings: an in-depth Linguistic Investigation","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"copybert-a-unified-approach-to-question","title":"CopyBERT: A Unified Approach to Question Generation with Self-Attention","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-disaster-related-multi-label","slug":"cross-lingual-disaster-related-multi-label","title":"Cross-Lingual Disaster-related Multi-label Tweet Classification with Manifold Mixup","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-utility-of-model","title":"Evaluating the Utility of Model Configurations and Data Augmentation on Clinical Semantic Textual Similarity","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-limits-of-simple-learners-in","title":"Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-projection-for-improved-text","title":"Feature Projection for Improved Text Classification","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/gan-bert-generative-adversarial-learning-for","slug":"gan-bert-generative-adversarial-learning-for","title":"GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples","date":"2020-07-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"getting-the-life-out-of-living-how-adequate","title":"Getting the \\#\\#life out of living: How Adequate Are Word-Pieces for Modelling Complex Morphology?","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"go-figure-multi-task-transformer-based","title":"Go Figure! Multi-task transformer-based architecture for metaphor detection using idioms: ETS team in 2020 metaphor shared task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"go-wide-then-narrow-efficient-training-of","title":"Go Wide, Then Narrow: Efficient Training of Deep Thin Networks","date":"2020-07-01","arxiv_id":"2007.00811","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-bert-s-attention-change-when-you","title":"How does BERT's attention change when you fine-tune? An analysis methodology and a case study in negation scope","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"illinimet-illinois-system-for-metaphor","title":"IlliniMet: Illinois System for Metaphor Detection with Contextual and Linguistic Information","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-multimodal-named-entity-recognition","slug":"improving-multimodal-named-entity-recognition","title":"Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"information-retrieval-and-extraction-on-covid","title":"Information Retrieval and Extraction on COVID-19 Clinical Articles Using Graph Community Detection and Bio-BERT Embeddings","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"intermediate-task-transfer-learning-with-1","title":"Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-effect-of-auxiliary","title":"Investigating the effect of auxiliary objectives for the automated grading of learner English speech transcriptions","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"item-based-collaborative-filtering-with-bert","title":"Item-based Collaborative Filtering with BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-training-with-semantic-role-labeling","title":"Joint Training with Semantic Role Labeling for Better Generalization in Natural Language Inference","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"k-opsala-transition-based-graph-parsing-via","title":"K\\opsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lstm-and-gpt-2-synthetic-speech-transfer","title":"LSTM and GPT-2 Synthetic Speech Transfer Learning for Speaker Recognition to Overcome Data Scarcity","date":"2020-07-01","arxiv_id":"2007.00659","n_code_links":0,"syntology":null},{"paper":null,"slug":"metaphor-detection-using-contextual-word","title":"Metaphor Detection Using Contextual Word Embeddings From Transformers","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/modelling-context-and-syntactical-features","slug":"modelling-context-and-syntactical-features","title":"Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-sarcasm-detection-using-conversation","title":"Neural Sarcasm Detection using Conversation Context","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-higher-order-dependency-parsers","title":"Revisiting Higher-Order Dependency Parsers","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robertnlp-at-the-iwpt-2020-shared-task","title":"RobertNLP at the IWPT 2020 Shared Task: Surprisingly Simple Enhanced UD Parsing for English","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/roles-and-utilization-of-attention-heads-in","slug":"roles-and-utilization-of-attention-heads-in","title":"Roles and Utilization of Attention Heads in Transformer-based Neural Language Models","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"sarcasm-identification-and-detection-in","title":"Sarcasm Identification and Detection in Conversion Context using BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-context-aware-covid-19","slug":"self-supervised-context-aware-covid-19","title":"Self-supervised context-aware COVID-19 document exploration through atlas grounding","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"sentitel-tabsa-for-twitter-reviews-on-uganda","title":"SentiTel: TABSA for Twitter reviews on Uganda Telecoms","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"should-you-fine-tune-bert-for-automated-essay","title":"Should You Fine-Tune BERT for Automated Essay Scoring?","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tbert-topic-models-and-bert-joining-forces","slug":"tbert-topic-models-and-bert-joining-forces","title":"tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"the-hw-tsc-video-speech-translation-system-at","title":"The HW-TSC Video Speech Translation System at IWSLT 2020","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/towards-holistic-and-automatic-evaluation-of-1","slug":"towards-holistic-and-automatic-evaluation-of-1","title":"Towards Holistic and Automatic Evaluation of Open-Domain Dialogue Generation","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-on-sarcasm-detection-with","title":"Transformers on Sarcasm Detection with Context","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/transition-based-semantic-dependency-parsing-1","slug":"transition-based-semantic-dependency-parsing-1","title":"Transition-based Semantic Dependency Parsing with Pointer Networks","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"turku-enhanced-parser-pipeline-from-raw-text","title":"Turku Enhanced Parser Pipeline: From Raw Text to Enhanced Graphs in the IWPT 2020 Shared Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-advertisements-with-bert","title":"Understanding Advertisements with BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-faq-retrieval-with-question","title":"Unsupervised FAQ Retrieval with Question Generation and BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"why-is-penguin-more-similar-to-polar-bear","title":"Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"would-you-rather-a-new-benchmark-for-learning","title":"Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/data-movement-is-all-you-need-a-case-study-of","slug":"data-movement-is-all-you-need-a-case-study-of","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","date":"2020-06-30","arxiv_id":"2007.00072","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":["spcl/substation"],"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":"se3m-a-model-for-software-effort-estimation","title":"SE3M: A Model for Software Effort Estimation Using Pre-trained Embedding Models","date":"2020-06-30","arxiv_id":"2006.16831","n_code_links":0,"syntology":null},{"paper":null,"slug":"segmentation-approach-for-coreference","title":"Segmentation Approach for Coreference Resolution Task","date":"2020-06-30","arxiv_id":"2007.04301","n_code_links":0,"syntology":null},{"paper":"/paper/improving-sequence-tagging-for-vietnamese","slug":"improving-sequence-tagging-for-vietnamese","title":"Improving Sequence Tagging for Vietnamese Text Using Transformer-based Neural Models","date":"2020-06-29","arxiv_id":"2006.15994","n_code_links":2,"syntology":null},{"paper":null,"slug":"interpreting-hierarchical-linguistic","title":"Building Interpretable Interaction Trees for Deep NLP Models","date":"2020-06-29","arxiv_id":"2007.04298","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-aware-language-model-pretraining","title":"Knowledge-Aware Language Model Pretraining","date":"2020-06-29","arxiv_id":"2007.00655","n_code_links":0,"syntology":null},{"paper":null,"slug":"want-to-identify-extract-and-normalize","title":"Want to Identify, Extract and Normalize Adverse Drug Reactions in Tweets? Use RoBERTa","date":"2020-06-29","arxiv_id":"2006.16146","n_code_links":0,"syntology":null},{"paper":"/paper/bond-bert-assisted-open-domain-named-entity","slug":"bond-bert-assisted-open-domain-named-entity","title":"BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision","date":"2020-06-28","arxiv_id":"2006.15509","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["cliang1453/BOND"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/progressive-generation-of-long-text","slug":"progressive-generation-of-long-text","title":"Progressive Generation of Long Text with Pretrained Language Models","date":"2020-06-28","arxiv_id":"2006.15720","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":["tanyuqian/progressive-generation"],"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":"/paper/rethinking-the-positional-encoding-in","slug":"rethinking-the-positional-encoding-in","title":"Rethinking Positional Encoding in Language Pre-training","date":"2020-06-28","arxiv_id":"2006.15595","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["guolinke/TUPE"],"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":["listed","official"]}}},{"paper":null,"slug":"normalizador-neural-de-datas-e-enderecos","title":"Normalizador Neural de Datas e Endereços","date":"2020-06-27","arxiv_id":"2007.04300","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-grounded-dialogues-with-pretrained-1","title":"Video-Grounded Dialogues with Pretrained Generation Language Models","date":"2020-06-27","arxiv_id":"2006.15319","n_code_links":0,"syntology":null},{"paper":"/paper/fastspec-scalable-generation-and-detection-of","slug":"fastspec-scalable-generation-and-detection-of","title":"FastSpec: Scalable Generation and Detection of Spectre Gadgets Using Neural Embeddings","date":"2020-06-25","arxiv_id":"2006.14147","n_code_links":1,"syntology":null},{"paper":"/paper/lsbert-a-simple-framework-for-lexical","slug":"lsbert-a-simple-framework-for-lexical","title":"LSBert: A Simple Framework for Lexical Simplification","date":"2020-06-25","arxiv_id":"2006.14939","n_code_links":1,"syntology":null},{"paper":null,"slug":"normalizing-text-using-language-modelling","title":"Normalizing Text using Language Modelling based on Phonetics and String Similarity","date":"2020-06-25","arxiv_id":"2006.14116","n_code_links":0,"syntology":null},{"paper":"/paper/accelerated-large-batch-optimization-of-bert","slug":"accelerated-large-batch-optimization-of-bert","title":"Accelerated Large Batch Optimization of BERT Pretraining in 54 minutes","date":"2020-06-24","arxiv_id":"2006.13484","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-constituency-parsing-by-pointing-1","title":"Efficient Constituency Parsing by Pointing","date":"2020-06-24","arxiv_id":"2006.13557","n_code_links":0,"syntology":null},{"paper":"/paper/reco-a-large-scale-chinese-reading","slug":"reco-a-large-scale-chinese-reading","title":"ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion","date":"2020-06-22","arxiv_id":"2006.12146","n_code_links":1,"syntology":null}],"record_sha256":"684bf3aca3622dc116152b153da27306278c7ae5efaecf6fada06b4725ed34bb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}