{"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/gpt-2/papers/7","list_of":"/method/gpt-2","method":"GPT-2","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":7,"pages_in_order":8,"rows_per_page":100,"rows":[601,700],"of":768,"counts":{"archive_papers_tagged":768,"with_a_code_link":339,"where_syntology_ran_a_sample":125,"not_listed_spam_title":0,"listed":768,"listed_where_code_ran":125,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":99,"every_run_a_failure_of_syntologys_instrument":26,"listed_with_a_run_with_no_instrument_failure":99,"listed_every_run_a_failure_of_syntologys_instrument":26,"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/gpt-2","prev":"/method/gpt-2/papers/6","next":"/method/gpt-2/papers/8","papers":[{"paper":"/paper/surface-form-competition-why-the-highest","slug":"surface-form-competition-why-the-highest","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","date":"2021-04-16","arxiv_id":"2104.08315","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["peterwestuw/surface-form-competition"],"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/nareor-the-narrative-reordering-problem","slug":"nareor-the-narrative-reordering-problem","title":"NAREOR: The Narrative Reordering Problem","date":"2021-04-14","arxiv_id":"2104.06669","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-transformers-for-bot-detection","slug":"understanding-transformers-for-bot-detection","title":"Understanding Transformers for Bot Detection in Twitter","date":"2021-04-13","arxiv_id":"2104.06182","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-aware-graph-enhanced-gpt-2-for","slug":"knowledge-aware-graph-enhanced-gpt-2-for","title":"Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking","date":"2021-04-09","arxiv_id":"2104.04466","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-gpt-2-to-create-synthetic-data-to","title":"Using GPT-2 to Create Synthetic Data to Improve the Prediction Performance of NLP Machine Learning Classification Models","date":"2021-04-02","arxiv_id":"2104.10658","n_code_links":0,"syntology":null},{"paper":null,"slug":"thinking-aloud-dynamic-context-generation","title":"Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2","date":"2021-03-24","arxiv_id":"2103.13033","n_code_links":0,"syntology":null},{"paper":null,"slug":"play-the-shannon-game-with-language-models-a","title":"Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation","date":"2021-03-19","arxiv_id":"2103.10918","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-have-a-moral-dimension","slug":"language-models-have-a-moral-dimension","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","date":"2021-03-08","arxiv_id":"2103.11790","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ml-research/MoRT_NMI"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"decomposing-lexical-and-compositional-syntax","title":"Disentangling Syntax and Semantics in the Brain with Deep Networks","date":"2021-03-02","arxiv_id":"2103.01620","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-document-summarization-in-a-low-resource","title":"Long Document Summarization in a Low Resource Setting using Pretrained Language Models","date":"2021-03-01","arxiv_id":"2103.00751","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-and-transferable-anomaly-detection-in","title":"Robust and Transferable Anomaly Detection in Log Data using Pre-Trained Language Models","date":"2021-02-23","arxiv_id":"2102.11570","n_code_links":0,"syntology":null},{"paper":null,"slug":"theaitre-1-0-interactive-generation-of","title":"THEaiTRE 1.0: Interactive generation of theatre play scripts","date":"2021-02-17","arxiv_id":"2102.08892","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-corruptive-force-of-ai-generated-advice","title":"The corruptive force of AI-generated advice","date":"2021-02-15","arxiv_id":"2102.07536","n_code_links":0,"syntology":null},{"paper":"/paper/augpt-dialogue-with-pre-trained-language","slug":"augpt-dialogue-with-pre-trained-language","title":"AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models","date":"2021-02-09","arxiv_id":"2102.05126","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-hybrid-task-oriented-dialog-system-with","title":"A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining","date":"2021-02-08","arxiv_id":"2102.04506","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-fake-cyber-threat-intelligence","title":"Generating Fake Cyber Threat Intelligence Using Transformer-Based Models","date":"2021-02-08","arxiv_id":"2102.04351","n_code_links":0,"syntology":null},{"paper":"/paper/how-true-is-gpt-2-an-empirical-analysis-of","slug":"how-true-is-gpt-2-an-empirical-analysis-of","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","date":"2021-02-08","arxiv_id":"2102.04130","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["oxai/intersectional_gpt2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"jointly-improving-language-understanding-and","title":"Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling","date":"2021-02-06","arxiv_id":"2102.03551","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-data-to-text-generation-with-lm-based","title":"Neural Data-to-Text Generation with LM-based Text Augmentation","date":"2021-02-06","arxiv_id":"2102.03556","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthesizing-monolingual-data-for-neural","title":"Synthesizing Monolingual Data for Neural Machine Translation","date":"2021-01-29","arxiv_id":"2101.12462","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-transformer-model-for-detecting-arabic","title":"BERT Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets","date":"2021-01-22","arxiv_id":"2101.09345","n_code_links":0,"syntology":null},{"paper":"/paper/towards-facilitating-empathic-conversations","slug":"towards-facilitating-empathic-conversations","title":"Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach","date":"2021-01-19","arxiv_id":"2101.07714","n_code_links":1,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers-1","title":"Adding Recurrence to Pretrained Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ketg-a-knowledge-enhanced-text-generation","title":"KETG: A Knowledge Enhanced Text Generation Framework","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/polyjuice-automated-general-purpose","slug":"polyjuice-automated-general-purpose","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","date":"2021-01-01","arxiv_id":"2101.00288","n_code_links":1,"syntology":null},{"paper":"/paper/prefix-tuning-optimizing-continuous-prompts","slug":"prefix-tuning-optimizing-continuous-prompts","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","date":"2021-01-01","arxiv_id":"2101.00190","n_code_links":13,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["XiangLi1999/PrefixTuning"],"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":"pretrain-knowledge-aware-language-models","title":"Pretrain Knowledge-Aware Language Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"conditional-generation-of-temporally-ordered","title":"Conditional Generation of Temporally-ordered Event Sequences","date":"2020-12-31","arxiv_id":"2012.15786","n_code_links":0,"syntology":null},{"paper":"/paper/directed-beam-search-plug-and-play-lexically","slug":"directed-beam-search-plug-and-play-lexically","title":"Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation","date":"2020-12-31","arxiv_id":"2012.15416","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":["dapascual/DirectedBeamSearch"],"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":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","slug":"the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","arxiv_id":"2101.00027","n_code_links":22,"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":["EleutherAI/The-Pile"],"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/robust-dialogue-utterance-rewriting-as","slug":"robust-dialogue-utterance-rewriting-as","title":"Robust Dialogue Utterance Rewriting as Sequence Tagging","date":"2020-12-29","arxiv_id":"2012.14535","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-and-surprisal-jointly-deliver-the","title":"Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition","date":"2020-12-22","arxiv_id":"2012.12007","n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-and-contextualised-writing-tool","title":"Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models","date":"2020-12-19","arxiv_id":"2101.03216","n_code_links":0,"syntology":null},{"paper":null,"slug":"query-expansion-with-artificially-generated","title":"Query expansion with artificially generated texts","date":"2020-12-16","arxiv_id":"2012.08787","n_code_links":0,"syntology":null},{"paper":"/paper/recipenlg-a-cooking-recipes-dataset-for-semi","slug":"recipenlg-a-cooking-recipes-dataset-for-semi","title":"RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation","date":"2020-12-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/extracting-training-data-from-large-language","slug":"extracting-training-data-from-large-language","title":"Extracting Training Data from Large Language Models","date":"2020-12-14","arxiv_id":"2012.07805","n_code_links":3,"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":["ftramer/LM_Memorization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/as-good-as-new-how-to-successfully-recycle","slug":"as-good-as-new-how-to-successfully-recycle","title":"As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages","date":"2020-12-10","arxiv_id":"2012.05628","n_code_links":1,"syntology":null},{"paper":"/paper/towards-neural-programming-interfaces-1","slug":"towards-neural-programming-interfaces-1","title":"Towards Neural Programming Interfaces","date":"2020-12-10","arxiv_id":"2012.05983","n_code_links":1,"syntology":null},{"paper":"/paper/cx-db8-a-queryable-extractive-summarizer-and","slug":"cx-db8-a-queryable-extractive-summarizer-and","title":"CX DB8: A queryable extractive summarizer and semantic search engine","date":"2020-12-07","arxiv_id":"2012.03942","n_code_links":2,"syntology":null},{"paper":"/paper/ubar-towards-fully-end-to-end-task-oriented","slug":"ubar-towards-fully-end-to-end-task-oriented","title":"UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2","date":"2020-12-07","arxiv_id":"2012.03539","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-offensive-language-detection-through","title":"Enhanced Offensive Language Detection Through Data Augmentation","date":"2020-12-05","arxiv_id":"2012.02954","n_code_links":0,"syntology":null},{"paper":"/paper/how-can-we-know-when-language-models-know","slug":"how-can-we-know-when-language-models-know","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","date":"2020-12-02","arxiv_id":"2012.00955","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-generative-approach-to-native-language","title":"A Deep Generative Approach to Native Language Identification","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-probabilistic-distributional-and","title":"Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-11-an-empirical","title":"Hitachi at SemEval-2020 Task 11: An Empirical Study of Pre-Trained Transformer Family for Propaganda Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-7-stacking-at","title":"Hitachi at SemEval-2020 Task 7: Stacking at Scale with Heterogeneous Language Models for Humor Recognition","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-8-simple-but","title":"Hitachi at SemEval-2020 Task 8: Simple but Effective Modality Ensemble for Meme Emotion Recognition","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tablegpt-few-shot-table-to-text-generation","slug":"tablegpt-few-shot-table-to-text-generation","title":"TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"ui-at-semeval-2020-task-4-commonsense","title":"UI at SemEval-2020 Task 4: Commonsense Validation and Explanation by Exploiting Contradiction","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-training-for-paraphrase","title":"Generative Pre-training for Paraphrase Generation by Representing and Predicting Spans in Exemplars","date":"2020-11-29","arxiv_id":"2011.14344","n_code_links":0,"syntology":null},{"paper":"/paper/debatesum-a-large-scale-argument-mining-and","slug":"debatesum-a-large-scale-argument-mining-and","title":"DebateSum: A large-scale argument mining and summarization dataset","date":"2020-11-14","arxiv_id":"2011.07251","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":["Hellisotherpeople/DebateSum","Hellisotherpeople/debate2vec","arvind-balaji/debate-cards"],"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/adapting-a-language-model-for-controlled","slug":"adapting-a-language-model-for-controlled","title":"Adapting a Language Model for Controlled Affective Text Generation","date":"2020-11-08","arxiv_id":"2011.04000","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ishikasingh/Affective-text-gen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/semi-supervised-low-resource-style-transfer","slug":"semi-supervised-low-resource-style-transfer","title":"Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation","date":"2020-11-06","arxiv_id":"2011.03286","n_code_links":1,"syntology":null},{"paper":"/paper/visually-grounded-planning-without-vision-1","slug":"visually-grounded-planning-without-vision-1","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"topic-preserving-synthetic-news-generation-an","title":"Topic-Preserving Synthetic News Generation: An Adversarial Deep Reinforcement Learning Approach","date":"2020-10-30","arxiv_id":"2010.16324","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-paraphrase-generation-via","title":"Unsupervised Paraphrasing with Pretrained Language Models","date":"2020-10-24","arxiv_id":"2010.12885","n_code_links":0,"syntology":null},{"paper":null,"slug":"topic-modeling-with-contextualized-word","title":"Topic Modeling with Contextualized Word Representation Clusters","date":"2020-10-23","arxiv_id":"2010.12626","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-distractions-transformer-based","title":"Better Distractions: Transformer-based Distractor Generation and Multiple Choice Question Filtering","date":"2020-10-19","arxiv_id":"2010.09598","n_code_links":0,"syntology":null},{"paper":"/paper/decoding-methods-for-neural-narrative","slug":"decoding-methods-for-neural-narrative","title":"Decoding Methods for Neural Narrative Generation","date":"2020-10-14","arxiv_id":"2010.07375","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-workweek-is-the-best-time-to-start-a","title":"The workweek is the best time to start a family -- A Study of GPT-2 Based Claim Generation","date":"2020-10-13","arxiv_id":"2010.06185","n_code_links":0,"syntology":null},{"paper":"/paper/meta-context-transformers-for-domain-specific","slug":"meta-context-transformers-for-domain-specific","title":"Meta-Context Transformers for Domain-Specific Response Generation","date":"2020-10-12","arxiv_id":"2010.05572","n_code_links":1,"syntology":null},{"paper":"/paper/incremental-processing-in-the-age-of-non","slug":"incremental-processing-in-the-age-of-non","title":"Incremental Processing in the Age of Non-Incremental Encoders: An Empirical Assessment of Bidirectional Models for Incremental NLU","date":"2020-10-11","arxiv_id":"2010.05330","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-african-american-vernacular","slug":"investigating-african-american-vernacular","title":"Investigating African-American Vernacular English in Transformer-Based Text Generation","date":"2020-10-06","arxiv_id":"2010.02510","n_code_links":1,"syntology":null},{"paper":"/paper/genaug-data-augmentation-for-finetuning-text","slug":"genaug-data-augmentation-for-finetuning-text","title":"GenAug: Data Augmentation for Finetuning Text Generators","date":"2020-10-05","arxiv_id":"2010.01794","n_code_links":2,"syntology":null},{"paper":"/paper/inquisitive-question-generation-for-high","slug":"inquisitive-question-generation-for-high","title":"Inquisitive Question Generation for High Level Text Comprehension","date":"2020-10-04","arxiv_id":"2010.01657","n_code_links":1,"syntology":null},{"paper":null,"slug":"examining-the-rhetorical-capacities-of-neural","title":"Examining the rhetorical capacities of neural language models","date":"2020-10-01","arxiv_id":"2010.00153","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-design-and-implementation-of-language","title":"The design and implementation of Language Learning Chatbot with XAI using Ontology and Transfer Learning","date":"2020-09-29","arxiv_id":"2009.13984","n_code_links":0,"syntology":null},{"paper":"/paper/visually-grounded-planning-without-vision","slug":"visually-grounded-planning-without-vision","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","date":"2020-09-29","arxiv_id":"2009.14259","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":["cognitiveailab/alfred-gpt2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-data-augmentation-for-extreme-multi-label","title":"On Data Augmentation for Extreme Multi-label Classification","date":"2020-09-22","arxiv_id":"2009.10778","n_code_links":0,"syntology":null},{"paper":null,"slug":"prior-art-search-and-reranking-for-generated","title":"Prior Art Search and Reranking for Generated Patent Text","date":"2020-09-19","arxiv_id":"2009.09132","n_code_links":0,"syntology":null},{"paper":"/paper/critical-thinking-for-language-models","slug":"critical-thinking-for-language-models","title":"Critical Thinking for Language Models","date":"2020-09-15","arxiv_id":"2009.07185","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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":["debatelab/aacorpus"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dialogue-response-ranking-training-with-large","slug":"dialogue-response-ranking-training-with-large","title":"Dialogue Response Ranking Training with Large-Scale Human Feedback Data","date":"2020-09-15","arxiv_id":"2009.06978","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"the-radicalization-risks-of-gpt-3-and","title":"The Radicalization Risks of GPT-3 and Advanced Neural Language Models","date":"2020-09-15","arxiv_id":"2009.06807","n_code_links":0,"syntology":null},{"paper":"/paper/gedi-generative-discriminator-guided-sequence","slug":"gedi-generative-discriminator-guided-sequence","title":"GeDi: Generative Discriminator Guided Sequence Generation","date":"2020-09-14","arxiv_id":"2009.06367","n_code_links":3,"syntology":{"ran":6,"of":11,"n_ran_checked":3,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["salesforce/GeDi"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/brain2word-decoding-brain-activity-for","slug":"brain2word-decoding-brain-activity-for","title":"Brain2Word: Decoding Brain Activity for Language Generation","date":"2020-09-10","arxiv_id":"2009.04765","n_code_links":1,"syntology":null},{"paper":"/paper/modern-methods-for-text-generation","slug":"modern-methods-for-text-generation","title":"Modern Methods for Text Generation","date":"2020-09-10","arxiv_id":"2009.04968","n_code_links":2,"syntology":null},{"paper":null,"slug":"black-box-to-white-box-discover-model","title":"Black Box to White Box: Discover Model Characteristics Based on Strategic Probing","date":"2020-09-07","arxiv_id":"2009.03136","n_code_links":0,"syntology":null},{"paper":"/paper/improving-language-generation-with-sentence","slug":"improving-language-generation-with-sentence","title":"Improving Language Generation with Sentence Coherence Objective","date":"2020-09-07","arxiv_id":"2009.06358","n_code_links":1,"syntology":null},{"paper":"/paper/comparative-evaluation-of-pretrained-transfer","slug":"comparative-evaluation-of-pretrained-transfer","title":"Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer Grading","date":"2020-09-02","arxiv_id":"2009.01303","n_code_links":1,"syntology":null},{"paper":null,"slug":"dave-deriving-automatically-verilog-from","title":"DAVE: Deriving Automatically Verilog from English","date":"2020-08-27","arxiv_id":"2009.01026","n_code_links":0,"syntology":null},{"paper":"/paper/etc-nlg-end-to-end-topic-conditioned-natural","slug":"etc-nlg-end-to-end-topic-conditioned-natural","title":"ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation","date":"2020-08-25","arxiv_id":"2008.10875","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-models-are-unsupervised-predictors","title":"Generative Models are Unsupervised Predictors of Page Quality: A Colossal-Scale Study","date":"2020-08-17","arxiv_id":"2008.13533","n_code_links":0,"syntology":null},{"paper":null,"slug":"narrative-interpolation-for-generating-and","title":"Narrative Interpolation for Generating and Understanding Stories","date":"2020-08-17","arxiv_id":"2008.07466","n_code_links":0,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers","title":"Adding Recurrence to Pretrained Transformers for Improved Efficiency and Context Size","date":"2020-08-16","arxiv_id":"2008.07027","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-as-few-shot-learner-for-task","title":"Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems","date":"2020-08-14","arxiv_id":"2008.06239","n_code_links":0,"syntology":null},{"paper":null,"slug":"navigating-language-models-with-synthetic","title":"Navigating Human Language Models with Synthetic Agents","date":"2020-08-10","arxiv_id":"2008.04162","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-node-bert-pretraining-cost-efficient","title":"Multi-node Bert-pretraining: Cost-efficient Approach","date":"2020-08-01","arxiv_id":"2008.00177","n_code_links":0,"syntology":null},{"paper":"/paper/trojaning-language-models-for-fun-and-profit","slug":"trojaning-language-models-for-fun-and-profit","title":"Trojaning Language Models for Fun and Profit","date":"2020-08-01","arxiv_id":"2008.00312","n_code_links":1,"syntology":null},{"paper":"/paper/tweepfake-about-detecting-deepfake-tweets","slug":"tweepfake-about-detecting-deepfake-tweets","title":"TweepFake: about Detecting Deepfake Tweets","date":"2020-07-31","arxiv_id":"2008.00036","n_code_links":1,"syntology":null},{"paper":"/paper/composer-style-classification-of-piano-sheet","slug":"composer-style-classification-of-piano-sheet","title":"Composer Style Classification of Piano Sheet Music Images Using Language Model Pretraining","date":"2020-07-29","arxiv_id":"2007.14587","n_code_links":1,"syntology":null},{"paper":"/paper/generative-pretraining-from-pixels","slug":"generative-pretraining-from-pixels","title":"Generative Pretraining from Pixels","date":"2020-07-17","arxiv_id":null,"n_code_links":4,"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":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":"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":"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":"/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":"/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":"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":"/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":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}],"record_sha256":"d638d3b8e9a543507029518497705f3c983c1ce9732388afca44229763d6886d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}