{"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":"/task/language-modeling/papers/43","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":43,"pages_in_order":142,"rows_per_page":100,"rows":[4201,4300],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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":"/task/language-modeling","prev":"/task/language-modeling/papers/42","next":"/task/language-modeling/papers/44","papers":[{"url":"/paper/an-empirical-revisiting-of-linguistic","slug":"an-empirical-revisiting-of-linguistic","title":"An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks","date":"2022-10-24","arxiv_id":"2210.13002","repositories_listed":1,"syntology":null},{"url":"/paper/elmer-a-non-autoregressive-pre-trained","slug":"elmer-a-non-autoregressive-pre-trained","title":"ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generation","date":"2022-10-24","arxiv_id":"2210.13304","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unifying-reference-expression","slug":"towards-unifying-reference-expression","title":"Towards Unifying Reference Expression Generation and Comprehension","date":"2022-10-24","arxiv_id":"2210.13076","repositories_listed":1,"syntology":null},{"url":"/paper/code4struct-code-generation-for-few-shot","slug":"code4struct-code-generation-for-few-shot","title":"Code4Struct: Code Generation for Few-Shot Event Structure Prediction","date":"2022-10-23","arxiv_id":"2210.12810","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-pre-training-with-sparse","slug":"language-model-pre-training-with-sparse","title":"Language Model Pre-Training with Sparse Latent Typing","date":"2022-10-23","arxiv_id":"2210.12582","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-model-pre-training-with-sparse#ran","syntology_url":"https://syntology.ai/paper/2210.12582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12582"}},"official":{"repos":["renll/sparselt"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/correcting-diverse-factual-errors-in","slug":"correcting-diverse-factual-errors-in","title":"Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling","date":"2022-10-22","arxiv_id":"2210.12378","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/correcting-diverse-factual-errors-in#ran","syntology_url":"https://syntology.ai/paper/2210.12378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12378"}},"official":{"repos":["vidhishanair/factedit"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/generative-prompt-tuning-for-relation-1","slug":"generative-prompt-tuning-for-relation-1","title":"Generative Prompt Tuning for Relation Classification","date":"2022-10-22","arxiv_id":"2210.12435","repositories_listed":1,"syntology":null},{"url":"/paper/neurocounterfactuals-beyond-minimal-edit","slug":"neurocounterfactuals-beyond-minimal-edit","title":"NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation","date":"2022-10-22","arxiv_id":"2210.12365","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-domain-learning-in-language","slug":"understanding-domain-learning-in-language","title":"Understanding Domain Learning in Language Models Through Subpopulation Analysis","date":"2022-10-22","arxiv_id":"2210.12553","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/understanding-domain-learning-in-language#ran","syntology_url":"https://syntology.ai/paper/2210.12553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12553"}},"official":{"repos":["zsquaredz/subpopulation_analysis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diffuser-efficient-transformers-with-multi","slug":"diffuser-efficient-transformers-with-multi","title":"Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences","date":"2022-10-21","arxiv_id":"2210.11794","repositories_listed":1,"syntology":null},{"url":"/paper/do-vision-and-language-transformers-learn","slug":"do-vision-and-language-transformers-learn","title":"Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?","date":"2022-10-21","arxiv_id":"2210.12079","repositories_listed":1,"syntology":null},{"url":"/paper/graphemic-normalization-of-the-perso-arabic","slug":"graphemic-normalization-of-the-perso-arabic","title":"Graphemic Normalization of the Perso-Arabic Script","date":"2022-10-21","arxiv_id":"2210.12273","repositories_listed":1,"syntology":null},{"url":"/paper/informask-unsupervised-informative-masking","slug":"informask-unsupervised-informative-masking","title":"InforMask: Unsupervised Informative Masking for Language Model Pretraining","date":"2022-10-21","arxiv_id":"2210.11771","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/informask-unsupervised-informative-masking#ran","syntology_url":"https://syntology.ai/paper/2210.11771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11771"}},"official":{"repos":["nafissadeq/informask"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/z-lavi-zero-shot-language-solver-fueled-by","slug":"z-lavi-zero-shot-language-solver-fueled-by","title":"Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination","date":"2022-10-21","arxiv_id":"2210.12261","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-out-of-distribution-detection-in","slug":"enhancing-out-of-distribution-detection-in","title":"Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble","date":"2022-10-20","arxiv_id":"2210.11034","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/enhancing-out-of-distribution-detection-in#ran","syntology_url":"https://syntology.ai/paper/2210.11034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11034"}},"official":{"repos":["hyunsoocho77/lacl-official"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tele-knowledge-pre-training-for-fault","slug":"tele-knowledge-pre-training-for-fault","title":"Tele-Knowledge Pre-training for Fault Analysis","date":"2022-10-20","arxiv_id":"2210.11298","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tele-knowledge-pre-training-for-fault#ran","syntology_url":"https://syntology.ai/paper/2210.11298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11298"}},"official":{"repos":["hackerchenzhuo/ktelebert"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/continued-pretraining-for-better-zero-and-few","slug":"continued-pretraining-for-better-zero-and-few","title":"Continued Pretraining for Better Zero- and Few-Shot Promptability","date":"2022-10-19","arxiv_id":"2210.10258","repositories_listed":1,"syntology":null},{"url":"/paper/improving-aspect-sentiment-quad-prediction","slug":"improving-aspect-sentiment-quad-prediction","title":"Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation","date":"2022-10-19","arxiv_id":"2210.10291","repositories_listed":1,"syntology":null},{"url":"/paper/language-detoxification-with-attribute","slug":"language-detoxification-with-attribute","title":"Language Detoxification with Attribute-Discriminative Latent Space","date":"2022-10-19","arxiv_id":"2210.10329","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-decomposition-quantifying-the","slug":"language-model-decomposition-quantifying-the","title":"Language Model Decomposition: Quantifying the Dependency and Correlation of Language Models","date":"2022-10-19","arxiv_id":"2210.10289","repositories_listed":1,"syntology":null},{"url":"/paper/tabllm-few-shot-classification-of-tabular","slug":"tabllm-few-shot-classification-of-tabular","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","date":"2022-10-19","arxiv_id":"2210.10723","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/tabllm-few-shot-classification-of-tabular#ran","syntology_url":"https://syntology.ai/paper/2210.10723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10723"}},"official":{"repos":["clinicalml/TabLLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/the-devil-in-linear-transformer","slug":"the-devil-in-linear-transformer","title":"The Devil in Linear Transformer","date":"2022-10-19","arxiv_id":"2210.10340","repositories_listed":1,"syntology":null},{"url":"/paper/alibaba-translate-china-s-submission-for-wmt","slug":"alibaba-translate-china-s-submission-for-wmt","title":"Alibaba-Translate China's Submission for WMT 2022 Metrics Shared Task","date":"2022-10-18","arxiv_id":"2210.09683","repositories_listed":1,"syntology":null},{"url":"/paper/alibaba-translate-china-s-submission-for-wmt-1","slug":"alibaba-translate-china-s-submission-for-wmt-1","title":"Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task","date":"2022-10-18","arxiv_id":"2210.10049","repositories_listed":1,"syntology":null},{"url":"/paper/arithmetic-sampling-parallel-diverse-decoding","slug":"arithmetic-sampling-parallel-diverse-decoding","title":"Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models","date":"2022-10-18","arxiv_id":"2210.15458","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 6 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/arithmetic-sampling-parallel-diverse-decoding#ran","syntology_url":"https://syntology.ai/paper/2210.15458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15458"}},"official":{"repos":["google-research/google-research"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/sentiment-aware-word-and-sentence-level-pre","slug":"sentiment-aware-word-and-sentence-level-pre","title":"Sentiment-Aware Word and Sentence Level Pre-training for Sentiment Analysis","date":"2022-10-18","arxiv_id":"2210.09803","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/sentiment-aware-word-and-sentence-level-pre#ran","syntology_url":"https://syntology.ai/paper/2210.09803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09803"}},"official":{"repos":["xmudm/sentiwsp"],"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"]}}},{"url":"/paper/the-tail-wagging-the-dog-dataset-construction","slug":"the-tail-wagging-the-dog-dataset-construction","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","date":"2022-10-18","arxiv_id":"2210.10040","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/the-tail-wagging-the-dog-dataset-construction#ran","syntology_url":"https://syntology.ai/paper/2210.10040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10040"}},"official":{"repos":["uclanlp/socialbias-dataset-construction-biases"],"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"]}}},{"url":"/paper/knowledge-prompting-in-pre-trained-language","slug":"knowledge-prompting-in-pre-trained-language","title":"Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding","date":"2022-10-16","arxiv_id":"2210.08536","repositories_listed":1,"syntology":null},{"url":"/paper/normsage-multi-lingual-multi-cultural-norm","slug":"normsage-multi-lingual-multi-cultural-norm","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","date":"2022-10-16","arxiv_id":"2210.08604","repositories_listed":1,"syntology":null},{"url":"/paper/construction-repetition-reduces-information","slug":"construction-repetition-reduces-information","title":"Construction Repetition Reduces Information Rate in Dialogue","date":"2022-10-15","arxiv_id":"2210.08321","repositories_listed":1,"syntology":null},{"url":"/paper/bertscore-is-unfair-on-social-bias-in","slug":"bertscore-is-unfair-on-social-bias-in","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation","date":"2022-10-14","arxiv_id":"2210.07626","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bertscore-is-unfair-on-social-bias-in#ran","syntology_url":"https://syntology.ai/paper/2210.07626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07626"}},"official":{"repos":["txsun1997/metric-fairness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cab-comprehensive-attention-benchmarking-on","slug":"cab-comprehensive-attention-benchmarking-on","title":"CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling","date":"2022-10-14","arxiv_id":"2210.07661","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-long-tail-generalization-with","slug":"benchmarking-long-tail-generalization-with","title":"Benchmarking Long-tail Generalization with Likelihood Splits","date":"2022-10-13","arxiv_id":"2210.06799","repositories_listed":1,"syntology":null},{"url":"/paper/can-demographic-factors-improve-text","slug":"can-demographic-factors-improve-text","title":"Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers","date":"2022-10-13","arxiv_id":"2210.07362","repositories_listed":1,"syntology":null},{"url":"/paper/imaginarynet-learning-object-detectors","slug":"imaginarynet-learning-object-detectors","title":"ImaginaryNet: Learning Object Detectors without Real Images and Annotations","date":"2022-10-13","arxiv_id":"2210.06886","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/imaginarynet-learning-object-detectors#ran","syntology_url":"https://syntology.ai/paper/2210.06886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06886"}},"official":{"repos":["kodenii/imaginarynet"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/language-model-decoding-as-likelihood-utility","slug":"language-model-decoding-as-likelihood-utility","title":"Language Model Decoding as Likelihood-Utility Alignment","date":"2022-10-13","arxiv_id":"2210.07228","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-model-decoding-as-likelihood-utility#ran","syntology_url":"https://syntology.ai/paper/2210.07228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07228"}},"official":{"repos":["epfl-dlab/understanding-decoding"],"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"]}}},{"url":"/paper/m2d2-a-massively-multi-domain-language","slug":"m2d2-a-massively-multi-domain-language","title":"M2D2: A Massively Multi-domain Language Modeling Dataset","date":"2022-10-13","arxiv_id":"2210.07370","repositories_listed":1,"syntology":null},{"url":"/paper/re3-generating-longer-stories-with-recursive","slug":"re3-generating-longer-stories-with-recursive","title":"Re3: Generating Longer Stories With Recursive Reprompting and Revision","date":"2022-10-13","arxiv_id":"2210.06774","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/re3-generating-longer-stories-with-recursive#ran","syntology_url":"https://syntology.ai/paper/2210.06774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06774"}},"official":{"repos":["yangkevin2/emnlp22-re3-story-generation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/sodapop-open-ended-discovery-of-social-biases","slug":"sodapop-open-ended-discovery-of-social-biases","title":"SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models","date":"2022-10-13","arxiv_id":"2210.07269","repositories_listed":1,"syntology":null},{"url":"/paper/a-context-aware-knowledge-transferring","slug":"a-context-aware-knowledge-transferring","title":"A context-aware knowledge transferring strategy for CTC-based ASR","date":"2022-10-12","arxiv_id":"2210.06244","repositories_listed":1,"syntology":null},{"url":"/paper/ad-drop-attribution-driven-dropout-for-robust","slug":"ad-drop-attribution-driven-dropout-for-robust","title":"AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning","date":"2022-10-12","arxiv_id":"2210.05883","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/ad-drop-attribution-driven-dropout-for-robust#ran","syntology_url":"https://syntology.ai/paper/2210.05883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05883"}},"official":{"repos":["taoyang225/ad-drop"],"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"]}}},{"url":"/paper/medjex-a-medical-jargon-extraction-model-with","slug":"medjex-a-medical-jargon-extraction-model-with","title":"MedJEx: A Medical Jargon Extraction Model with Wiki's Hyperlink Span and Contextualized Masked Language Model Score","date":"2022-10-12","arxiv_id":"2210.05875","repositories_listed":1,"syntology":null},{"url":"/paper/predictive-querying-for-autoregressive-neural","slug":"predictive-querying-for-autoregressive-neural","title":"Predictive Querying for Autoregressive Neural Sequence Models","date":"2022-10-12","arxiv_id":"2210.06464","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":2,"n_ran_checked":2,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 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; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/predictive-querying-for-autoregressive-neural#ran","syntology_url":"https://syntology.ai/paper/2210.06464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06464"}},"official":{"repos":["ajboyd2/prob_seq_queries"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/subword-segmental-language-modelling-for","slug":"subword-segmental-language-modelling-for","title":"Subword Segmental Language Modelling for Nguni Languages","date":"2022-10-12","arxiv_id":"2210.06525","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-prompting-for-implicit-intent","slug":"zero-shot-prompting-for-implicit-intent","title":"Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning","date":"2022-10-12","arxiv_id":"2210.05901","repositories_listed":1,"syntology":null},{"url":"/paper/a-kernel-based-view-of-language-model-fine","slug":"a-kernel-based-view-of-language-model-fine","title":"A Kernel-Based View of Language Model Fine-Tuning","date":"2022-10-11","arxiv_id":"2210.05643","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-kernel-based-view-of-language-model-fine#ran","syntology_url":"https://syntology.ai/paper/2210.05643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05643"}},"official":{"repos":["princeton-nlp/lm-kernel-ft"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-lingual-speaker-identification-using","slug":"cross-lingual-speaker-identification-using","title":"Cross-Lingual Speaker Identification Using Distant Supervision","date":"2022-10-11","arxiv_id":"2210.05780","repositories_listed":1,"syntology":null},{"url":"/paper/instance-regularization-for-discriminative","slug":"instance-regularization-for-discriminative","title":"Instance Regularization for Discriminative Language Model Pre-training","date":"2022-10-11","arxiv_id":"2210.05471","repositories_listed":1,"syntology":null},{"url":"/paper/map-modality-agnostic-uncertainty-aware","slug":"map-modality-agnostic-uncertainty-aware","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model","date":"2022-10-11","arxiv_id":"2210.05335","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-and-advancing-chinese-natural","slug":"revisiting-and-advancing-chinese-natural","title":"Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training","date":"2022-10-11","arxiv_id":"2210.05287","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-failure-of-batch","slug":"understanding-the-failure-of-batch","title":"Understanding the Failure of Batch Normalization for Transformers in NLP","date":"2022-10-11","arxiv_id":"2210.05153","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":8,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"9 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/understanding-the-failure-of-batch#ran","syntology_url":"https://syntology.ai/paper/2210.05153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05153"}},"official":{"repos":["wjxts/regularizedbn"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/core-a-retrieve-then-edit-framework-for","slug":"core-a-retrieve-then-edit-framework-for","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","date":"2022-10-10","arxiv_id":"2210.04873","repositories_listed":1,"syntology":null},{"url":"/paper/controllable-dialogue-simulation-with-in","slug":"controllable-dialogue-simulation-with-in","title":"Controllable Dialogue Simulation with In-Context Learning","date":"2022-10-09","arxiv_id":"2210.04185","repositories_listed":1,"syntology":null},{"url":"/paper/cross-align-modeling-deep-cross-lingual","slug":"cross-align-modeling-deep-cross-lingual","title":"Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment","date":"2022-10-09","arxiv_id":"2210.04141","repositories_listed":1,"syntology":null},{"url":"/paper/learning-fine-grained-visual-understanding","slug":"learning-fine-grained-visual-understanding","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","date":"2022-10-08","arxiv_id":"2210.03941","repositories_listed":1,"syntology":null},{"url":"/paper/named-entity-recognition-in-twitter-a-dataset","slug":"named-entity-recognition-in-twitter-a-dataset","title":"Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts","date":"2022-10-07","arxiv_id":"2210.03797","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/named-entity-recognition-in-twitter-a-dataset#ran","syntology_url":"https://syntology.ai/paper/2210.03797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03797"}},"official":{"repos":["asahi417/tner"],"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"]}}},{"url":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-sample-efficiency-of-prompt","slug":"improving-the-sample-efficiency-of-prompt","title":"Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation","date":"2022-10-06","arxiv_id":"2210.02952","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/improving-the-sample-efficiency-of-prompt#ran","syntology_url":"https://syntology.ai/paper/2210.02952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02952"}},"official":{"repos":["guoxuxu/soft-prompt-transfer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ccc-wav2vec-2-0-clustering-aided-cross","slug":"ccc-wav2vec-2-0-clustering-aided-cross","title":"CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations","date":"2022-10-05","arxiv_id":"2210.02592","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":2,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ccc-wav2vec-2-0-clustering-aided-cross#ran","syntology_url":"https://syntology.ai/paper/2210.02592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02592"}},"official":{"repos":["speech-lab-iitm/ccc-wav2vec-2.0"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/variational-prompt-tuning-improves","slug":"variational-prompt-tuning-improves","title":"Bayesian Prompt Learning for Image-Language Model Generalization","date":"2022-10-05","arxiv_id":"2210.02390","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/variational-prompt-tuning-improves#ran","syntology_url":"https://syntology.ai/paper/2210.02390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02390"}},"official":{"repos":["saic-fi/bayesian-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/less-is-more-task-aware-layer-wise","slug":"less-is-more-task-aware-layer-wise","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","date":"2022-10-04","arxiv_id":"2210.01351","repositories_listed":1,"syntology":null},{"url":"/paper/towards-improving-faithfulness-in-abstractive","slug":"towards-improving-faithfulness-in-abstractive","title":"Towards Improving Faithfulness in Abstractive Summarization","date":"2022-10-04","arxiv_id":"2210.01877","repositories_listed":1,"syntology":null},{"url":"/paper/a-non-monotonic-self-terminating-language","slug":"a-non-monotonic-self-terminating-language","title":"A Non-monotonic Self-terminating Language Model","date":"2022-10-03","arxiv_id":"2210.00660","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-non-monotonic-self-terminating-language#ran","syntology_url":"https://syntology.ai/paper/2210.00660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.00660"}},"official":{"repos":["nyu-dl/non-monotonic-self-terminating-lm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/contragen-effective-contrastive-learning-for","slug":"contragen-effective-contrastive-learning-for","title":"ContraCLM: Contrastive Learning For Causal Language Model","date":"2022-10-03","arxiv_id":"2210.01185","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_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) · 4 unverified","sample_list":"/paper/contragen-effective-contrastive-learning-for#ran","syntology_url":"https://syntology.ai/paper/2210.01185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01185"}},"official":null}},{"url":"/paper/speechclip-integrating-speech-with-pre","slug":"speechclip-integrating-speech-with-pre","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","date":"2022-10-03","arxiv_id":"2210.00705","repositories_listed":1,"syntology":null},{"url":"/paper/the-effectiveness-of-masked-language-modeling","slug":"the-effectiveness-of-masked-language-modeling","title":"The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection","date":"2022-10-03","arxiv_id":"2210.00907","repositories_listed":1,"syntology":null},{"url":"/paper/a-domain-knowledge-enhanced-pre-trained","slug":"a-domain-knowledge-enhanced-pre-trained","title":"A Domain Knowledge Enhanced Pre-Trained Language Model for Vertical Search: Case Study on Medicinal Products","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-japanese-masked-language-model-for-academic","slug":"a-japanese-masked-language-model-for-academic","title":"A Japanese Masked Language Model for Academic Domain","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/becel-benchmark-for-consistency-evaluation-of","slug":"becel-benchmark-for-consistency-evaluation-of","title":"BECEL: Benchmark for Consistency Evaluation of Language Models","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/can-we-guide-a-multi-hop-reasoning-language","slug":"can-we-guide-a-multi-hop-reasoning-language","title":"Can We Guide a Multi-Hop Reasoning Language Model to Incrementally Learn at Each Single-Hop?","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/docquerynet-value-retrieval-with-arbitrary","slug":"docquerynet-value-retrieval-with-arbitrary","title":"DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dont-judge-a-language-model-by-its-last-layer","slug":"dont-judge-a-language-model-by-its-last-layer","title":"Don’t Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/event-causality-identification-via-derivative","slug":"event-causality-identification-via-derivative","title":"Event Causality Identification via Derivative Prompt Joint Learning","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/how-about-time-probing-a-multilingual","slug":"how-about-time-probing-a-multilingual","title":"How about Time? Probing a Multilingual Language Model for Temporal Relations","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-distillation-with-reptile-meta","slug":"knowledge-distillation-with-reptile-meta","title":"Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model Compression","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/making-parameter-efficient-tuning-more","slug":"making-parameter-efficient-tuning-more","title":"Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nsp-bert-a-prompt-based-few-shot-learner","slug":"nsp-bert-a-prompt-based-few-shot-learner","title":"NSP-BERT: A Prompt-based Few-Shot Learner through an Original Pre-training Task —— Next Sentence Prediction","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/section-aware-commonsense-knowledge-grounded","slug":"section-aware-commonsense-knowledge-grounded","title":"Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/uper-boosting-multi-document-summarization","slug":"uper-boosting-multi-document-summarization","title":"UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zemi-learning-zero-shot-semi-parametric","slug":"zemi-learning-zero-shot-semi-parametric","title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","date":"2022-10-01","arxiv_id":"2210.00185","repositories_listed":1,"syntology":null},{"url":"/paper/speechlm-enhanced-speech-pre-training-with","slug":"speechlm-enhanced-speech-pre-training-with","title":"SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data","date":"2022-09-30","arxiv_id":"2209.15329","repositories_listed":1,"syntology":null},{"url":"/paper/arnli-arabic-natural-language-inference-for","slug":"arnli-arabic-natural-language-inference-for","title":"ArNLI: Arabic Natural Language Inference for Entailment and Contradiction Detection","date":"2022-09-28","arxiv_id":"2209.13953","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-time-invariance-assorted-time","slug":"breaking-time-invariance-assorted-time","title":"Breaking Time Invariance: Assorted-Time Normalization for RNNs","date":"2022-09-28","arxiv_id":"2209.14439","repositories_listed":1,"syntology":null},{"url":"/paper/who-is-gpt-3-an-exploration-of-personality","slug":"who-is-gpt-3-an-exploration-of-personality","title":"Who is GPT-3? An Exploration of Personality, Values and Demographics","date":"2022-09-28","arxiv_id":"2209.14338","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-purpose-material-property-data","slug":"a-general-purpose-material-property-data","title":"A general-purpose material property data extraction pipeline from large polymer corpora using Natural Language Processing","date":"2022-09-27","arxiv_id":"2209.13136","repositories_listed":1,"syntology":null},{"url":"/paper/entailment-semantics-can-be-extracted-from-an","slug":"entailment-semantics-can-be-extracted-from-an","title":"Entailment Semantics Can Be Extracted from an Ideal Language Model","date":"2022-09-26","arxiv_id":"2209.12407","repositories_listed":1,"syntology":null},{"url":"/paper/whodunit-learning-to-contrast-for-authorship","slug":"whodunit-learning-to-contrast-for-authorship","title":"Whodunit? Learning to Contrast for Authorship Attribution","date":"2022-09-23","arxiv_id":"2209.11887","repositories_listed":1,"syntology":null},{"url":"/paper/adaptation-of-domain-specific-transformer","slug":"adaptation-of-domain-specific-transformer","title":"Adaptation of domain-specific transformer models with text oversampling for sentiment analysis of social media posts on Covid-19 vaccines","date":"2022-09-22","arxiv_id":"2209.10966","repositories_listed":1,"syntology":null},{"url":"/paper/semantically-consistent-data-augmentation-for","slug":"semantically-consistent-data-augmentation-for","title":"Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model","date":"2022-09-22","arxiv_id":"2209.10875","repositories_listed":1,"syntology":null},{"url":"/paper/a-few-shot-approach-to-resume-information","slug":"a-few-shot-approach-to-resume-information","title":"A Few-shot Approach to Resume Information Extraction via Prompts","date":"2022-09-20","arxiv_id":"2209.09450","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-label-sequence-generation-for","slug":"automatic-label-sequence-generation-for","title":"Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models","date":"2022-09-20","arxiv_id":"2209.09401","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-generative-transformer-language","slug":"probabilistic-generative-transformer-language","title":"Probabilistic Generative Transformer Language models for Generative Design of Molecules","date":"2022-09-20","arxiv_id":"2209.09406","repositories_listed":1,"syntology":null},{"url":"/paper/relaxed-attention-for-transformer-models","slug":"relaxed-attention-for-transformer-models","title":"Relaxed Attention for Transformer Models","date":"2022-09-20","arxiv_id":"2209.09735","repositories_listed":1,"syntology":null},{"url":"/paper/from-disfluency-detection-to-intent-detection","slug":"from-disfluency-detection-to-intent-detection","title":"From Disfluency Detection to Intent Detection and Slot Filling","date":"2022-09-17","arxiv_id":"2209.08359","repositories_listed":1,"syntology":null},{"url":"/paper/selective-token-generation-for-few-shot-1","slug":"selective-token-generation-for-few-shot-1","title":"Selective Token Generation for Few-shot Natural Language Generation","date":"2022-09-17","arxiv_id":"2209.08206","repositories_listed":1,"syntology":null},{"url":"/paper/the-whole-truth-and-nothing-but-the-truth","slug":"the-whole-truth-and-nothing-but-the-truth","title":"The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding","date":"2022-09-16","arxiv_id":"2209.07800","repositories_listed":1,"syntology":null},{"url":"/paper/cold-start-data-selection-for-few-shot","slug":"cold-start-data-selection-for-few-shot","title":"Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach","date":"2022-09-15","arxiv_id":"2209.06995","repositories_listed":1,"syntology":null},{"url":"/paper/stateful-memory-augmented-transformers-for","slug":"stateful-memory-augmented-transformers-for","title":"Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling","date":"2022-09-15","arxiv_id":"2209.07634","repositories_listed":1,"syntology":null},{"url":"/paper/twhin-bert-a-socially-enriched-pre-trained","slug":"twhin-bert-a-socially-enriched-pre-trained","title":"TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter","date":"2022-09-15","arxiv_id":"2209.07562","repositories_listed":1,"syntology":null},{"url":"/paper/space-3-unified-dialog-model-pre-training-for","slug":"space-3-unified-dialog-model-pre-training-for","title":"SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation","date":"2022-09-14","arxiv_id":"2209.06664","repositories_listed":1,"syntology":null}],"record_sha256":"b5167a4164766e27ca29211e369879b407821ab574b6a876cb6cf2fce251e38e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}