{"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/discriminative-fine-tuning/papers/17","list_of":"/method/discriminative-fine-tuning","method":"Discriminative Fine-Tuning","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":17,"pages_in_order":20,"rows_per_page":100,"rows":[1601,1700],"of":1990,"counts":{"archive_papers_tagged":1990,"with_a_code_link":794,"where_syntology_ran_a_sample":271,"not_listed_spam_title":0,"listed":1990,"listed_where_code_ran":271,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":223,"every_run_a_failure_of_syntologys_instrument":48,"listed_with_a_run_with_no_instrument_failure":223,"listed_every_run_a_failure_of_syntologys_instrument":48,"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/discriminative-fine-tuning","prev":"/method/discriminative-fine-tuning/papers/16","next":"/method/discriminative-fine-tuning/papers/18","papers":[{"paper":null,"slug":"provably-confidential-language-modelling","title":"Provably Confidential Language Modelling","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-learning-for-conversational-1","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"when-a-sentence-does-not-introduce-a","title":"When a sentence does not introduce a discourse entity, Transformer-based models still often refer to it","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"why-does-surprisal-from-smaller-gpt-2-models","title":"Why Does Surprisal From Smaller GPT-2 Models Provide Better Fit to Human Reading Times?","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/assemble-foundation-models-for-automatic-code","slug":"assemble-foundation-models-for-automatic-code","title":"Assemble Foundation Models for Automatic Code Summarization","date":"2022-01-13","arxiv_id":"2201.05222","n_code_links":1,"syntology":null},{"paper":null,"slug":"submix-practical-private-prediction-for-large-1","title":"Submix: Practical Private Prediction for Large-Scale Language Models","date":"2022-01-04","arxiv_id":"2201.00971","n_code_links":0,"syntology":null},{"paper":"/paper/dense-to-sparse-gate-for-mixture-of-experts-1","slug":"dense-to-sparse-gate-for-mixture-of-experts-1","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","date":"2021-12-29","arxiv_id":"2112.14397","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["codecaution/evomoe"],"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/call-for-customized-conversation-customized","slug":"call-for-customized-conversation-customized","title":"Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge","date":"2021-12-16","arxiv_id":"2112.08619","n_code_links":3,"syntology":null},{"paper":"/paper/efficient-hierarchical-domain-adaptation-for","slug":"efficient-hierarchical-domain-adaptation-for","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","date":"2021-12-16","arxiv_id":"2112.08786","n_code_links":1,"syntology":null},{"paper":null,"slug":"reconsidering-the-past-optimizing-hidden-1","title":"Reconsidering the Past: Optimizing Hidden States in Language Models","date":"2021-12-16","arxiv_id":"2112.08653","n_code_links":0,"syntology":null},{"paper":"/paper/wechsel-effective-initialization-of-subword-1","slug":"wechsel-effective-initialization-of-subword-1","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","date":"2021-12-13","arxiv_id":"2112.06598","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":["cpjku/wechsel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-logical-level-natural-language","title":"Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation","date":"2021-12-12","arxiv_id":"2112.06240","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-knowledge-graph-representation","title":"Improving Knowledge Graph Representation Learning by Structure Contextual Pre-training","date":"2021-12-08","arxiv_id":"2112.04087","n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-learning-for-conversational","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","date":"2021-12-04","arxiv_id":"2112.05787","n_code_links":0,"syntology":null},{"paper":"/paper/think-big-teach-small-do-language-models","slug":"think-big-teach-small-do-language-models","title":"Think Big, Teach Small: Do Language Models Distil Occam’s Razor?","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"chemical-identification-and-indexing-in","title":"Chemical Identification and Indexing in PubMed Articles via BERT and Text-to-Text Approaches","date":"2021-11-30","arxiv_id":"2111.15622","n_code_links":0,"syntology":null},{"paper":"/paper/pixelated-butterfly-simple-and-efficient-1","slug":"pixelated-butterfly-simple-and-efficient-1","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","date":"2021-11-30","arxiv_id":"2112.00029","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["HazyResearch/pixelfly"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"context-matters-in-semantically-controlled","title":"Context Matters in Semantically Controlled Language Generation for Task-oriented Dialogue Systems","date":"2021-11-28","arxiv_id":"2111.14119","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-korean-pretrained-language","title":"Transformer-based Korean Pretrained Language Models: A Survey on Three Years of Progress","date":"2021-11-25","arxiv_id":"2112.03014","n_code_links":0,"syntology":null},{"paper":"/paper/clipcap-clip-prefix-for-image-captioning","slug":"clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","arxiv_id":"2111.09734","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rmokady/clip_prefix_caption"],"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":["listed","official"]}}},{"paper":null,"slug":"guiding-generative-language-models-for-data","title":"Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification","date":"2021-11-17","arxiv_id":"2111.09064","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-information-theoretic-measurement-of","title":"An Information Theoretic Measurement of Topical Relevance in Learner Essays","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models-1","slug":"building-chinese-biomedical-language-models-1","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"create-a-benchmark-for-chinese-short-video","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"elle-efficient-lifelong-pre-training-for","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-task-oriented-dialog-policy","title":"End-to-end Task-oriented Dialog Policy Learning based on Pre-trained Language Model","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-and-adapting-chinese-gpt-to-pinyin","title":"Exploring and Adapting Chinese GPT to Pinyin Input Method","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformer-for-design","title":"Generative Pre-Trained Transformer for Design Concept Generation: An Exploration","date":"2021-11-16","arxiv_id":"2111.08489","n_code_links":0,"syntology":null},{"paper":null,"slug":"glm-general-language-model-pretraining-with","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-tokenization-on-language-models-an","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-graph-is-in-rescue-task-oriented","title":"Knowledge Graph is in Rescue: Task Oriented Dialogue System for Response Generation without NLU and DM","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"life-after-bert-what-do-other-muppets","title":"Life after BERT: What do Other Muppets Understand about Language?","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"moving-the-eiffel-tower-to-rome-tracing-and","title":"Moving the Eiffel Tower to ROME: Tracing and Editing Facts in GPT","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-of-ambiguity-in-pre-trained","title":"Representation of Ambiguity in Pre-Trained Sentence Embeddings","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"softmax-bottleneck-makes-language-models","title":"Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tell-me-who-you-are-and-i-ll-tell-you-what-to","title":"Tell me who you are and i'll tell you what to do: A Persona Grounded Task Oriented Dialogue Generation System","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"when-classifying-grammatical-role-bert-doesn","title":"When classifying grammatical role, BERT doesn't care about word order... except when it matters","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-story-generation-with-multi-task","title":"Exploring Story Generation with Multi-task Objectives in Variational Autoencoders","date":"2021-11-15","arxiv_id":"2111.08133","n_code_links":0,"syntology":null},{"paper":"/paper/iiitt-dravidian-codemix-fire2021","slug":"iiitt-dravidian-codemix-fire2021","title":"IIITT@Dravidian-CodeMix-FIRE2021: Transliterate or translate? Sentiment analysis of code-mixed text in Dravidian languages","date":"2021-11-15","arxiv_id":"2111.07906","n_code_links":1,"syntology":null},{"paper":"/paper/a-novel-corpus-of-discourse-structure-in","slug":"a-novel-corpus-of-discourse-structure-in","title":"A Novel Corpus of Discourse Structure in Humans and Computers","date":"2021-11-10","arxiv_id":"2111.05940","n_code_links":1,"syntology":null},{"paper":null,"slug":"distir-an-intermediate-representation-and","title":"DistIR: An Intermediate Representation and Simulator for Efficient Neural Network Distribution","date":"2021-11-09","arxiv_id":"2111.05426","n_code_links":0,"syntology":null},{"paper":null,"slug":"fpm-a-collection-of-large-scale-foundation","title":"FPM: A Collection of Large-scale Foundation Pre-trained Language Models","date":"2021-11-09","arxiv_id":"2111.04909","n_code_links":0,"syntology":null},{"paper":"/paper/dsee-dually-sparsity-embedded-efficient-1","slug":"dsee-dually-sparsity-embedded-efficient-1","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","date":"2021-10-30","arxiv_id":"2111.00160","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":8,"n_instrument":2,"unverified":3,"pointer_only":10,"phrase":"10 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["vita-group/dsee"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/amendable-generation-for-dialogue-state","slug":"amendable-generation-for-dialogue-state","title":"Amendable Generation for Dialogue State Tracking","date":"2021-10-29","arxiv_id":"2110.15659","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-sequence-to-sequence-model-for-extracting","title":"A Sequence to Sequence Model for Extracting Multiple Product Name Entities from Dialog","date":"2021-10-28","arxiv_id":"2110.14843","n_code_links":0,"syntology":null},{"paper":"/paper/colossal-ai-a-unified-deep-learning-system","slug":"colossal-ai-a-unified-deep-learning-system","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","date":"2021-10-28","arxiv_id":"2110.14883","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-artificial-texts-as-substitution","title":"Generating artificial texts as substitution or complement of training data","date":"2021-10-25","arxiv_id":"2110.13016","n_code_links":0,"syntology":null},{"paper":"/paper/fast-model-editing-at-scale-1","slug":"fast-model-editing-at-scale-1","title":"Fast Model Editing at Scale","date":"2021-10-21","arxiv_id":"2110.11309","n_code_links":3,"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":["eric-mitchell/mend"],"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/illiterate-dall-cdot-e-learns-to-compose-1","slug":"illiterate-dall-cdot-e-learns-to-compose-1","title":"Illiterate DALL-E Learns to Compose","date":"2021-10-17","arxiv_id":"2110.11405","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["singhgautam/slate"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reminding-the-incremental-language-model-via","title":"Reminding the Incremental Language Model via Data-Free Self-Distillation","date":"2021-10-17","arxiv_id":"2110.08745","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-short-study-on-compressing-decoder-based","title":"A Short Study on Compressing Decoder-Based Language Models","date":"2021-10-16","arxiv_id":"2110.08460","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish","title":"Evaluation of Transfer Learning for Polish with a text-to-text model","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hydra-a-system-for-large-multi-model-deep","slug":"hydra-a-system-for-large-multi-model-deep","title":"Hydra: A System for Large Multi-Model Deep Learning","date":"2021-10-16","arxiv_id":"2110.08633","n_code_links":1,"syntology":null},{"paper":null,"slug":"pagnol-an-extra-large-french-generative-model","title":"PAGnol: An Extra-Large French Generative Model","date":"2021-10-16","arxiv_id":"2110.08554","n_code_links":0,"syntology":null},{"paper":null,"slug":"wechsel-effective-initialization-of-subword","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kronecker-decomposition-for-gpt-compression","title":"Kronecker Decomposition for GPT Compression","date":"2021-10-15","arxiv_id":"2110.08152","n_code_links":0,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models","slug":"building-chinese-biomedical-language-models","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-10-14","arxiv_id":"2110.07244","n_code_links":1,"syntology":null},{"paper":null,"slug":"covert-message-passing-over-public-internet","title":"Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for \"Dead-Drop\" Deployments","date":"2021-10-13","arxiv_id":"2110.07009","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-modelling-via-learning-to-rank","title":"Language Modelling via Learning to Rank","date":"2021-10-13","arxiv_id":"2110.06961","n_code_links":0,"syntology":null},{"paper":"/paper/lightseq-accelerated-training-for-transformer","slug":"lightseq-accelerated-training-for-transformer","title":"LightSeq2: Accelerated Training for Transformer-based Models on GPUs","date":"2021-10-12","arxiv_id":"2110.05722","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-learning-for-situated-multi-domain","title":"Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems","date":"2021-10-11","arxiv_id":"2110.05221","n_code_links":0,"syntology":null},{"paper":"/paper/vector-quantized-image-modeling-with-improved-1","slug":"vector-quantized-image-modeling-with-improved-1","title":"Vector-quantized Image Modeling with Improved VQGAN","date":"2021-10-09","arxiv_id":"2110.04627","n_code_links":5,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/word-acquisition-in-neural-language-models","slug":"word-acquisition-in-neural-language-models","title":"Word Acquisition in Neural Language Models","date":"2021-10-05","arxiv_id":"2110.02406","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-examples-generation-for-reducing","title":"Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models","date":"2021-10-03","arxiv_id":"2110.01094","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-frequency-names-exhibit-bias-and","title":"Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models","date":"2021-10-01","arxiv_id":"2110.00672","n_code_links":0,"syntology":null},{"paper":null,"slug":"illiterate-dall-cdot-e-learns-to-compose","title":"Illiterate DALL$\\cdot$E Learns to Compose","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"language-model-pre-training-improves","title":"Language Model Pre-training Improves Generalization in Policy Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mapping-language-models-to-grounded","title":"Mapping Language Models to Grounded Conceptual Spaces","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-reinforcement-learning-for-large","title":"Offline Reinforcement Learning for Large Scale Language Action Spaces","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"seqpate-differentially-private-text","title":"SeqPATE: Differentially Private Text Generation via Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-as-recommender-systems","title":"Language Models as Recommender Systems: Evaluations and Limitations","date":"2021-09-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-plug-and-play-method-for-controlled-text","slug":"a-plug-and-play-method-for-controlled-text","title":"A Plug-and-Play Method for Controlled Text Generation","date":"2021-09-20","arxiv_id":"2109.09707","n_code_links":1,"syntology":null},{"paper":null,"slug":"model-bias-in-nlp-application-to-hate-speech","title":"Model Bias in NLP -- Application to Hate Speech Classification using transfer learning techniques","date":"2021-09-20","arxiv_id":"2109.09725","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-low-frequency-patterns-with-a-pre","title":"Learning Low-frequency Patterns with A Pre-trained Document-Grounded Conversation Model","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"relating-neural-text-degeneration-to-exposure","title":"Relating Neural Text Degeneration to Exposure Bias","date":"2021-09-17","arxiv_id":"2109.08705","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-few-shot-multilingual","slug":"language-models-are-few-shot-multilingual","title":"Language Models are Few-shot Multilingual Learners","date":"2021-09-16","arxiv_id":"2109.07684","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gentaiscool/few-shot-lm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-text-auto-completion-with-next","title":"Improving Text Auto-Completion with Next Phrase Prediction","date":"2021-09-15","arxiv_id":"2109.07067","n_code_links":0,"syntology":null},{"paper":"/paper/a-temporal-variational-model-for-story","slug":"a-temporal-variational-model-for-story","title":"A Temporal Variational Model for Story Generation","date":"2021-09-14","arxiv_id":"2109.06807","n_code_links":3,"syntology":null},{"paper":"/paper/multilingual-translation-via-grafting-pre","slug":"multilingual-translation-via-grafting-pre","title":"Multilingual Translation via Grafting Pre-trained Language Models","date":"2021-09-11","arxiv_id":"2109.05256","n_code_links":1,"syntology":null},{"paper":null,"slug":"topicrefine-joint-topic-prediction-and","title":"TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System","date":"2021-09-11","arxiv_id":"2109.05187","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-self-disclosure-in-neural-dialog","title":"Enhancing Self-Disclosure In Neural Dialog Models By Candidate Re-ranking","date":"2021-09-10","arxiv_id":"2109.05090","n_code_links":0,"syntology":null},{"paper":"/paper/all-bark-and-no-bite-rogue-dimensions-in","slug":"all-bark-and-no-bite-rogue-dimensions-in","title":"All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality","date":"2021-09-09","arxiv_id":"2109.04404","n_code_links":1,"syntology":null},{"paper":"/paper/variational-latent-state-gpt-for-semi","slug":"variational-latent-state-gpt-for-semi","title":"Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems","date":"2021-09-09","arxiv_id":"2109.04314","n_code_links":2,"syntology":null},{"paper":"/paper/truthfulqa-measuring-how-models-mimic-human","slug":"truthfulqa-measuring-how-models-mimic-human","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","date":"2021-09-08","arxiv_id":"2109.07958","n_code_links":3,"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":["sylinrl/truthfulqa"],"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":"empathetic-dialogue-generation-with-pre","title":"Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge","date":"2021-09-07","arxiv_id":"2109.03004","n_code_links":0,"syntology":null},{"paper":null,"slug":"numgpt-improving-numeracy-ability-of","title":"NumGPT: Improving Numeracy Ability of Generative Pre-trained Models","date":"2021-09-07","arxiv_id":"2109.03137","n_code_links":0,"syntology":null},{"paper":"/paper/text-free-prosody-aware-generative-spoken","slug":"text-free-prosody-aware-generative-spoken","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","date":"2021-09-07","arxiv_id":"2109.03264","n_code_links":1,"syntology":null},{"paper":"/paper/codet5-identifier-aware-unified-pre-trained","slug":"codet5-identifier-aware-unified-pre-trained","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","date":"2021-09-02","arxiv_id":"2109.00859","n_code_links":5,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["salesforce/codet5"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"conqx-semantic-expansion-of-spoken-queries","title":"ConQX: Semantic Expansion of Spoken Queries for Intent Detection based on Conditioned Text Generation","date":"2021-09-02","arxiv_id":"2109.00729","n_code_links":0,"syntology":null},{"paper":null,"slug":"fight-fire-with-fire-fine-tuning-hate","title":"Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech","date":"2021-09-01","arxiv_id":"2109.00591","n_code_links":0,"syntology":null},{"paper":"/paper/optagan-entropy-based-finetuning-on-text-vae","slug":"optagan-entropy-based-finetuning-on-text-vae","title":"OptAGAN: Entropy-based finetuning on text VAE-GAN","date":"2021-09-01","arxiv_id":"2109.00239","n_code_links":1,"syntology":null},{"paper":"/paper/task-oriented-dialogue-system-as-natural","slug":"task-oriented-dialogue-system-as-natural","title":"Task-Oriented Dialogue System as Natural Language Generation","date":"2021-08-31","arxiv_id":"2108.13679","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":0,"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":["victorwz/tod_as_nlg"],"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/headlinecause-a-dataset-of-news-headlines-for","slug":"headlinecause-a-dataset-of-news-headlines-for","title":"HeadlineCause: A Dataset of News Headlines for Detecting Causalities","date":"2021-08-28","arxiv_id":"2108.12626","n_code_links":1,"syntology":null},{"paper":"/paper/offensive-language-identification-in-low","slug":"offensive-language-identification-in-low","title":"Offensive Language Identification in Low-resourced Code-mixed Dravidian languages using Pseudo-labeling","date":"2021-08-27","arxiv_id":"2108.12177","n_code_links":1,"syntology":null},{"paper":"/paper/sn-computer-science-towards-offensive","slug":"sn-computer-science-towards-offensive","title":"Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Posts","date":"2021-08-24","arxiv_id":"2108.10939","n_code_links":1,"syntology":null},{"paper":"/paper/table-caption-generation-in-scholarly","slug":"table-caption-generation-in-scholarly","title":"Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models","date":"2021-08-18","arxiv_id":"2108.08111","n_code_links":1,"syntology":null},{"paper":"/paper/curriculum-learning-a-regularization-method","slug":"curriculum-learning-a-regularization-method","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","date":"2021-08-13","arxiv_id":"2108.06084","n_code_links":1,"syntology":null},{"paper":"/paper/ammus-a-survey-of-transformer-based","slug":"ammus-a-survey-of-transformer-based","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","date":"2021-08-12","arxiv_id":"2108.05542","n_code_links":1,"syntology":null},{"paper":"/paper/patrickstar-parallel-training-of-pre-trained","slug":"patrickstar-parallel-training-of-pre-trained","title":"PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management","date":"2021-08-12","arxiv_id":"2108.05818","n_code_links":1,"syntology":null},{"paper":null,"slug":"offensive-language-and-hate-speech-detection-1","title":"Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learning","date":"2021-08-06","arxiv_id":"2108.03305","n_code_links":0,"syntology":null}],"record_sha256":"c64e866fb6621845c4d6f8d2cd4c5359e4afa884ac28d0a0bda3a619a975d4ad","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}