{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/weight-decay/papers/79","list_of":"/method/weight-decay","method":"Weight Decay","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":79,"pages_in_order":108,"rows_per_page":100,"rows":[7801,7900],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"listed_every_run_a_failure_of_syntologys_instrument":227,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/weight-decay","prev":"/method/weight-decay/papers/78","next":"/method/weight-decay/papers/80","papers":[{"paper":null,"slug":"ad-text-classification-with-transformer-based","title":"Ad Text Classification with Transformer-Based Natural Language Processing Methods","date":"2021-06-21","arxiv_id":"2106.10899","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-models-in-detection-of-dietary","title":"Deep Learning Models in Detection of Dietary Supplement Adverse Event Signals from Twitter","date":"2021-06-21","arxiv_id":"2106.11403","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-do-adam-and-training-strategies-help-bnns","title":"How Do Adam and Training Strategies Help BNNs Optimization?","date":"2021-06-21","arxiv_id":"2106.11309","n_code_links":0,"syntology":null},{"paper":"/paper/iterative-network-pruning-with-uncertainty","slug":"iterative-network-pruning-with-uncertainty","title":"Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification","date":"2021-06-21","arxiv_id":"2106.11197","n_code_links":1,"syntology":null},{"paper":"/paper/pseudo-relevance-feedback-for-multiple","slug":"pseudo-relevance-feedback-for-multiple","title":"Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval","date":"2021-06-21","arxiv_id":"2106.11251","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["terrierteam/pyterrier_colbert","cmacdonald/pyterrier_colbert"],"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/context-aware-legal-citation-recommendation","slug":"context-aware-legal-citation-recommendation","title":"Context-Aware Legal Citation Recommendation using Deep Learning","date":"2021-06-20","arxiv_id":"2106.10776","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-approach-to-detecting-symptoms-of","title":"Hybrid approach to detecting symptoms of depression in social media entries","date":"2021-06-19","arxiv_id":"2106.10485","n_code_links":0,"syntology":null},{"paper":null,"slug":"vln-bert-a-recurrent-vision-and-language-bert","title":"VLN BERT: A Recurrent Vision-and-Language BERT for Navigation","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/all-you-can-embed-natural-language-based","slug":"all-you-can-embed-natural-language-based","title":"All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformers","date":"2021-06-18","arxiv_id":"2106.10153","n_code_links":1,"syntology":null},{"paper":"/paper/bitfit-simple-parameter-efficient-fine-tuning","slug":"bitfit-simple-parameter-efficient-fine-tuning","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","date":"2021-06-18","arxiv_id":"2106.10199","n_code_links":6,"syntology":{"ran":4,"of":13,"n_ran_checked":3,"n_instrument":1,"unverified":9,"pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["benzakenelad/BitFit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"graph-based-joint-pandemic-concern-and","title":"Graph-based Joint Pandemic Concern and Relation Extraction on Twitter","date":"2021-06-18","arxiv_id":"2106.09929","n_code_links":0,"syntology":null},{"paper":null,"slug":"process-for-adapting-language-models-to","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","date":"2021-06-18","arxiv_id":"2106.10328","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-reinforcement-learning-approach-for-an-irs","title":"A Reinforcement Learning Approach for an IRS-assisted NOMA Network","date":"2021-06-17","arxiv_id":"2106.09611","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-based-1","title":"Deep Reinforcement Learning Based Optimization for IRS Based UAV-NOMA Downlink Networks","date":"2021-06-17","arxiv_id":"2106.09616","n_code_links":0,"syntology":null},{"paper":"/paper/knowledgeable-or-educated-guess-revisiting","slug":"knowledgeable-or-educated-guess-revisiting","title":"Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases","date":"2021-06-17","arxiv_id":"2106.09231","n_code_links":1,"syntology":null},{"paper":"/paper/large-scale-private-learning-via-low-rank","slug":"large-scale-private-learning-via-low-rank","title":"Large Scale Private Learning via Low-rank Reparametrization","date":"2021-06-17","arxiv_id":"2106.09352","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":1,"n_instrument":3,"unverified":4,"pointer_only":8,"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) · 4 unverified","official":{"repos":["dayu11/Differentially-Private-Deep-Learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/lnn-el-a-neuro-symbolic-approach-to-short","slug":"lnn-el-a-neuro-symbolic-approach-to-short","title":"LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking","date":"2021-06-17","arxiv_id":"2106.09795","n_code_links":1,"syntology":null},{"paper":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","n_code_links":74,"syntology":{"ran":51,"of":84,"n_ran_checked":44,"n_instrument":7,"unverified":33,"pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 7 where Syntology's instrument failed) · 33 unverified","official":{"repos":["microsoft/LoRA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"many-agent-reinforcement-learning-under","title":"Many Agent Reinforcement Learning Under Partial Observability","date":"2021-06-17","arxiv_id":"2106.09825","n_code_links":0,"syntology":null},{"paper":null,"slug":"algorithm-to-compilation-codesign-an","title":"Algorithm to Compilation Co-design: An Integrated View of Neural Network Sparsity","date":"2021-06-16","arxiv_id":"2106.08846","n_code_links":0,"syntology":null},{"paper":"/paper/tssubert-tweet-stream-summarization-using","slug":"tssubert-tweet-stream-summarization-using","title":"TSSuBERT: Tweet Stream Summarization Using BERT","date":"2021-06-16","arxiv_id":"2106.08770","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-automated-quality-evaluation-framework-of","title":"An Automated Quality Evaluation Framework of Psychotherapy Conversations with Local Quality Estimates","date":"2021-06-15","arxiv_id":"2106.07922","n_code_links":0,"syntology":null},{"paper":"/paper/beit-bert-pre-training-of-image-transformers","slug":"beit-bert-pre-training-of-image-transformers","title":"BEiT: BERT Pre-Training of Image Transformers","date":"2021-06-15","arxiv_id":"2106.08254","n_code_links":14,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/incorporating-word-sense-disambiguation-in","slug":"incorporating-word-sense-disambiguation-in","title":"Incorporating Word Sense Disambiguation in Neural Language Models","date":"2021-06-15","arxiv_id":"2106.07967","n_code_links":2,"syntology":null},{"paper":"/paper/knowledge-rich-bert-embeddings-for","slug":"knowledge-rich-bert-embeddings-for","title":"BERT Embeddings for Automatic Readability Assessment","date":"2021-06-15","arxiv_id":"2106.07935","n_code_links":1,"syntology":null},{"paper":"/paper/medical-code-prediction-from-discharge","slug":"medical-code-prediction-from-discharge","title":"Medical Code Prediction from Discharge Summary: Document to Sequence BERT using Sequence Attention","date":"2021-06-15","arxiv_id":"2106.07932","n_code_links":1,"syntology":null},{"paper":null,"slug":"textual-data-distributions-kullback-leibler","title":"Textual Data Distributions: Kullback Leibler Textual Distributions Contrasts on GPT-2 Generated Texts, with Supervised, Unsupervised Learning on Vaccine & Market Topics & Sentiment","date":"2021-06-15","arxiv_id":"2107.02025","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-bert-dig-it-named-entity-recognition-for","title":"Can BERT Dig It? -- Named Entity Recognition for Information Retrieval in the Archaeology Domain","date":"2021-06-14","arxiv_id":"2106.07742","n_code_links":0,"syntology":null},{"paper":"/paper/dataset-of-propaganda-techniques-of-the-state","slug":"dataset-of-propaganda-techniques-of-the-state","title":"Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China","date":"2021-06-14","arxiv_id":"2106.07544","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-sentence-level-representations-for","slug":"exploiting-sentence-level-representations-for","title":"Exploiting Sentence-Level Representations for Passage Ranking","date":"2021-06-14","arxiv_id":"2106.07316","n_code_links":1,"syntology":null},{"paper":"/paper/gpt3-to-plan-extracting-plans-from-text-using","slug":"gpt3-to-plan-extracting-plans-from-text-using","title":"GPT3-to-plan: Extracting plans from text using GPT-3","date":"2021-06-14","arxiv_id":"2106.07131","n_code_links":1,"syntology":null},{"paper":"/paper/hubert-self-supervised-speech-representation","slug":"hubert-self-supervised-speech-representation","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","date":"2021-06-14","arxiv_id":"2106.07447","n_code_links":11,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["pytorch/fairseq","huggingface/transformers"],"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/modeling-profanity-and-hate-speech-in-social","slug":"modeling-profanity-and-hate-speech-in-social","title":"Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces","date":"2021-06-14","arxiv_id":"2106.07505","n_code_links":1,"syntology":null},{"paper":null,"slug":"pre-trained-models-past-present-and-future","title":"Pre-Trained Models: Past, Present and Future","date":"2021-06-14","arxiv_id":"2106.07139","n_code_links":0,"syntology":null},{"paper":"/paper/sas-self-augmented-strategy-for-language","slug":"sas-self-augmented-strategy-for-language","title":"SAS: Self-Augmentation Strategy for Language Model Pre-training","date":"2021-06-14","arxiv_id":"2106.07176","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-can-you-lay-off-heads-investigating-how","title":"Why Can You Lay Off Heads? Investigating How BERT Heads Transfer","date":"2021-06-14","arxiv_id":"2106.07137","n_code_links":0,"syntology":null},{"paper":null,"slug":"sasicm-a-multi-task-benchmark-for-subtext","title":"SASICM A Multi-Task Benchmark For Subtext Recognition","date":"2021-06-13","arxiv_id":"2106.06944","n_code_links":0,"syntology":null},{"paper":null,"slug":"target-model-agnostic-adversarial-attacks","title":"Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models","date":"2021-06-13","arxiv_id":"2106.07047","n_code_links":0,"syntology":null},{"paper":"/paper/a-sentence-level-hierarchical-bert-model-for","slug":"a-sentence-level-hierarchical-bert-model-for","title":"A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data","date":"2021-06-12","arxiv_id":"2106.06738","n_code_links":1,"syntology":null},{"paper":null,"slug":"explaining-the-deep-natural-language","title":"Explaining the Deep Natural Language Processing by Mining Textual Interpretable Features","date":"2021-06-12","arxiv_id":"2106.06697","n_code_links":0,"syntology":null},{"paper":"/paper/bioelectra-pretrained-biomedical-text-encoder","slug":"bioelectra-pretrained-biomedical-text-encoder","title":"BioELECTRA:Pretrained Biomedical text Encoder using Discriminators","date":"2021-06-11","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamic-language-models-for-continuously","title":"Dynamic Language Models for Continuously Evolving Content","date":"2021-06-11","arxiv_id":"2106.06297","n_code_links":0,"syntology":null},{"paper":"/paper/generate-annotate-and-learn-generative-models","slug":"generate-annotate-and-learn-generative-models","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","date":"2021-06-11","arxiv_id":"2106.06168","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xlhex/gal_syntex"],"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","unlocated"]}}},{"paper":"/paper/n-best-asr-transformer-enhancing-slu","slug":"n-best-asr-transformer-enhancing-slu","title":"N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses","date":"2021-06-11","arxiv_id":"2106.06519","n_code_links":1,"syntology":null},{"paper":null,"slug":"refbert-compressing-bert-by-referencing-to","title":"RefBERT: Compressing BERT by Referencing to Pre-computed Representations","date":"2021-06-11","arxiv_id":"2106.08898","n_code_links":0,"syntology":null},{"paper":"/paper/amu-euranova-at-case-2021-task-1-assessing","slug":"amu-euranova-at-case-2021-task-1-assessing","title":"AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT","date":"2021-06-10","arxiv_id":"2106.14625","n_code_links":1,"syntology":null},{"paper":"/paper/convolutions-and-self-attention-re","slug":"convolutions-and-self-attention-re","title":"Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models","date":"2021-06-10","arxiv_id":"2106.05505","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-lingual-emotion-detection","title":"Cross-lingual Emotion Detection","date":"2021-06-10","arxiv_id":"2106.06017","n_code_links":0,"syntology":null},{"paper":null,"slug":"groupbert-enhanced-transformer-architecture","title":"GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures","date":"2021-06-10","arxiv_id":"2106.05822","n_code_links":0,"syntology":null},{"paper":"/paper/marginal-utility-diminishes-exploring-the","slug":"marginal-utility-diminishes-exploring-the","title":"Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation","date":"2021-06-10","arxiv_id":"2106.05691","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["llyx97/Marginal-Utility-Diminishes"],"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/programming-puzzles","slug":"programming-puzzles","title":"Programming Puzzles","date":"2021-06-10","arxiv_id":"2106.05784","n_code_links":3,"syntology":null},{"paper":null,"slug":"semantic-aware-binary-code-representation","title":"Semantic-aware Binary Code Representation with BERT","date":"2021-06-10","arxiv_id":"2106.05478","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-sexism-detection-with-multilingual","title":"Automatic Sexism Detection with Multilingual Transformer Models","date":"2021-06-09","arxiv_id":"2106.04908","n_code_links":0,"syntology":null},{"paper":"/paper/phraseformer-multimodal-key-phrase-extraction","slug":"phraseformer-multimodal-key-phrase-extraction","title":"Phraseformer: Multimodal Key-phrase Extraction using Transformer and Graph Embedding","date":"2021-06-09","arxiv_id":"2106.04939","n_code_links":0,"syntology":null},{"paper":"/paper/sentence-embeddings-using-supervised","slug":"sentence-embeddings-using-supervised","title":"Sentence Embeddings using Supervised Contrastive Learning","date":"2021-06-09","arxiv_id":"2106.04791","n_code_links":1,"syntology":null},{"paper":"/paper/cheap-and-good-simple-and-effective-data","slug":"cheap-and-good-simple-and-effective-data","title":"Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading","date":"2021-06-08","arxiv_id":"2106.04134","n_code_links":1,"syntology":null},{"paper":null,"slug":"engines-of-power-electricity-ai-and-general","title":"Engines of Power: Electricity, AI, and General-Purpose Military Transformations","date":"2021-06-08","arxiv_id":"2106.04338","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-bert-embedding-for-improving-prosody","title":"Speech BERT Embedding For Improving Prosody in Neural TTS","date":"2021-06-08","arxiv_id":"2106.04312","n_code_links":0,"syntology":null},{"paper":"/paper/timedial-temporal-commonsense-reasoning-in","slug":"timedial-temporal-commonsense-reasoning-in","title":"TIMEDIAL: Temporal Commonsense Reasoning in Dialog","date":"2021-06-08","arxiv_id":"2106.04571","n_code_links":1,"syntology":null},{"paper":"/paper/ultra-fine-entity-typing-with-weak","slug":"ultra-fine-entity-typing-with-weak","title":"Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model","date":"2021-06-08","arxiv_id":"2106.04098","n_code_links":1,"syntology":null},{"paper":"/paper/bertgen-multi-task-generation-through-bert","slug":"bertgen-multi-task-generation-through-bert","title":"BERTGEN: Multi-task Generation through BERT","date":"2021-06-07","arxiv_id":"2106.03484","n_code_links":1,"syntology":null},{"paper":null,"slug":"lawdr-language-agnostic-weighted-document","title":"LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models","date":"2021-06-07","arxiv_id":"2106.03379","n_code_links":0,"syntology":null},{"paper":null,"slug":"measuring-and-improving-bert-s-mathematical","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning","date":"2021-06-07","arxiv_id":"2106.03921","n_code_links":0,"syntology":null},{"paper":"/paper/neural-abstractive-unsupervised-summarization","slug":"neural-abstractive-unsupervised-summarization","title":"Neural Abstractive Unsupervised Summarization of Online News Discussions","date":"2021-06-07","arxiv_id":"2106.03953","n_code_links":1,"syntology":null},{"paper":null,"slug":"never-guess-what-i-heard-rumor-detection-in","title":"Never guess what I heard... Rumor Detection in Finnish News: a Dataset and a Baseline","date":"2021-06-07","arxiv_id":"2106.03389","n_code_links":0,"syntology":null},{"paper":"/paper/causal-abstractions-of-neural-networks","slug":"causal-abstractions-of-neural-networks","title":"Causal Abstractions of Neural Networks","date":"2021-06-06","arxiv_id":"2106.02997","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-continuous-control-with-double","slug":"efficient-continuous-control-with-double","title":"Efficient Continuous Control with Double Actors and Regularized Critics","date":"2021-06-06","arxiv_id":"2106.03050","n_code_links":1,"syntology":null},{"paper":null,"slug":"transient-chaos-in-bert","title":"Transient Chaos in BERT","date":"2021-06-06","arxiv_id":"2106.03181","n_code_links":0,"syntology":null},{"paper":"/paper/bertnesia-investigating-the-capture-and-1","slug":"bertnesia-investigating-the-capture-and-1","title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT","date":"2021-06-05","arxiv_id":"2106.02902","n_code_links":1,"syntology":null},{"paper":"/paper/bert-based-sentiment-analysis-a-software","slug":"bert-based-sentiment-analysis-a-software","title":"BERT-Based Sentiment Analysis: A Software Engineering Perspective","date":"2021-06-04","arxiv_id":"2106.02581","n_code_links":2,"syntology":null},{"paper":null,"slug":"do-syntactic-probes-probe-syntax-experiments","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","date":"2021-06-04","arxiv_id":"2106.02559","n_code_links":0,"syntology":null},{"paper":"/paper/ernie-tiny-a-progressive-distillation","slug":"ernie-tiny-a-progressive-distillation","title":"ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer Compression","date":"2021-06-04","arxiv_id":"2106.02241","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-equal-gender-representation-in-the","title":"Towards Equal Gender Representation in the Annotations of Toxic Language Detection","date":"2021-06-04","arxiv_id":"2106.02183","n_code_links":0,"syntology":null},{"paper":"/paper/you-only-compress-once-towards-effective-and","slug":"you-only-compress-once-towards-effective-and","title":"You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient","date":"2021-06-04","arxiv_id":"2106.02435","n_code_links":1,"syntology":null},{"paper":null,"slug":"auto-tagging-of-short-conversational","title":"Auto-tagging of Short Conversational Sentences using Transformer Methods","date":"2021-06-03","arxiv_id":"2106.01735","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-meets-liwc-exploring-state-of-the-art","title":"BERT meets LIWC: Exploring State-of-the-Art Language Models for Predicting Communication Behavior in Couples' Conflict Interactions","date":"2021-06-03","arxiv_id":"2106.01536","n_code_links":0,"syntology":null},{"paper":"/paper/ccpm-a-chinese-classical-poetry-matching","slug":"ccpm-a-chinese-classical-poetry-matching","title":"CCPM: A Chinese Classical Poetry Matching Dataset","date":"2021-06-03","arxiv_id":"2106.01979","n_code_links":1,"syntology":null},{"paper":null,"slug":"defending-democracy-using-deep-learning-to","title":"Defending Democracy: Using Deep Learning to Identify and Prevent Misinformation","date":"2021-06-03","arxiv_id":"2106.02607","n_code_links":0,"syntology":null},{"paper":"/paper/generate-prune-select-a-pipeline-for","slug":"generate-prune-select-a-pipeline-for","title":"Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech","date":"2021-06-03","arxiv_id":"2106.01625","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["WanzhengZhu/GPS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-guided-contrastive-learning-for-bert","slug":"self-guided-contrastive-learning-for-bert","title":"Self-Guided Contrastive Learning for BERT Sentence Representations","date":"2021-06-03","arxiv_id":"2106.07345","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["galsang/SG-BERT"],"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":["official"]}}},{"paper":"/paper/template-based-named-entity-recognition-using","slug":"template-based-named-entity-recognition-using","title":"Template-Based Named Entity Recognition Using BART","date":"2021-06-03","arxiv_id":"2106.01760","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-limitations-of-limited-context-for","title":"The Limitations of Limited Context for Constituency Parsing","date":"2021-06-03","arxiv_id":"2106.01580","n_code_links":0,"syntology":null},{"paper":null,"slug":"you-made-me-feel-this-way-investigating","title":"\"You made me feel this way\": Investigating Partners' Influence in Predicting Emotions in Couples' Conflict Interactions using Speech Data","date":"2021-06-03","arxiv_id":"2106.01526","n_code_links":0,"syntology":null},{"paper":null,"slug":"belabbert-a-dutch-roberta-based-language","title":"belabBERT: a Dutch RoBERTa-based language model applied to psychiatric classification","date":"2021-06-02","arxiv_id":"2106.01091","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-based-uav","title":"Deep Reinforcement Learning-based UAV Navigation and Control: A Soft Actor-Critic with Hindsight Experience Replay Approach","date":"2021-06-02","arxiv_id":"2106.01016","n_code_links":0,"syntology":null},{"paper":"/paper/differential-privacy-for-text-analytics-via","slug":"differential-privacy-for-text-analytics-via","title":"Differential Privacy for Text Analytics via Natural Text Sanitization","date":"2021-06-02","arxiv_id":"2106.01221","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xiangyue9607/SanText"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluating-the-efficacy-of-summarization","slug":"evaluating-the-efficacy-of-summarization","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","date":"2021-06-02","arxiv_id":"2106.01478","n_code_links":1,"syntology":null},{"paper":"/paper/mathbert-a-pre-trained-language-model-for","slug":"mathbert-a-pre-trained-language-model-for","title":"MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education","date":"2021-06-02","arxiv_id":"2106.07340","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["tbs17/MathBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-the-distribution-sparsity-and-inference","title":"On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers","date":"2021-06-02","arxiv_id":"2106.01335","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-document-similarity-ranking","slug":"self-supervised-document-similarity-ranking","title":"Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference","date":"2021-06-02","arxiv_id":"2106.01186","n_code_links":1,"syntology":null},{"paper":null,"slug":"t-bert-model-for-sentiment-analysis-of-micro","title":"T-BERT -- Model for Sentiment Analysis of Micro-blogs Integrating Topic Model and BERT","date":"2021-06-02","arxiv_id":"2106.01097","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-architecture-for-accelerated-large-scale","title":"An Architecture for Accelerated Large-Scale Inference of Transformer-Based Language Models","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"contextualized-and-generalized-sentence","title":"Contextualized and Generalized Sentence Representations by Contrastive Self-Supervised Learning: A Case Study on Discourse Relation Analysis","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-effective-deployment-of-bert-models-in-1","title":"Cost-effective Deployment of BERT Models in Serverless Environment","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cultural-and-geographical-influences-on-image","slug":"cultural-and-geographical-influences-on-image","title":"Cultural and Geographical Influences on Image Translatability of Words across Languages","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/domain-adaptation-for-arabic-cross-domain-and","slug":"domain-adaptation-for-arabic-cross-domain-and","title":"Domain Adaptation for Arabic Cross-Domain and Cross-Dialect Sentiment Analysis from Contextualized Word Embedding","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"dreca-a-general-task-augmentation-strategy","title":"DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dual-objective-fine-tuning-of-bert-for-entity","slug":"dual-objective-fine-tuning-of-bert-for-entity","title":"Dual-Objective Fine-Tuning of BERT for Entity Matching","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/emotion-infused-models-for-explainable","slug":"emotion-infused-models-for-explainable","title":"Emotion-Infused Models for Explainable Psychological Stress Detection","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-multihop-retrieval-for","slug":"end-to-end-multihop-retrieval-for","title":"Iterative Hierarchical Attention for Answering Complex Questions over Long Documents","date":"2021-06-01","arxiv_id":"2106.00200","n_code_links":0,"syntology":null}],"record_sha256":"a7e8afad80db2ccc62ee7270a4a7873d601ecc4c82918fa8ffc757d76e6e9189","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}