{"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-modelling/papers/57","list_of":"/task/language-modelling","task":"Language Modelling","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":57,"pages_in_order":177,"rows_per_page":100,"rows":[5601,5700],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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-modelling","prev":"/task/language-modelling/papers/56","next":"/task/language-modelling/papers/58","papers":[{"url":"/paper/extracting-latent-steering-vectors-from","slug":"extracting-latent-steering-vectors-from","title":"Extracting Latent Steering Vectors from Pretrained Language Models","date":"2022-05-10","arxiv_id":"2205.05124","repositories_listed":1,"syntology":null},{"url":"/paper/human-language-modeling-1","slug":"human-language-modeling-1","title":"Human Language Modeling","date":"2022-05-10","arxiv_id":"2205.05128","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/human-language-modeling-1#ran","syntology_url":"https://syntology.ai/paper/2205.05128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05128"}},"official":{"repos":["humanlab/hart"],"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/symphony-generation-with-permutation","slug":"symphony-generation-with-permutation","title":"Symphony Generation with Permutation Invariant Language Model","date":"2022-05-10","arxiv_id":"2205.05448","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/symphony-generation-with-permutation#ran","syntology_url":"https://syntology.ai/paper/2205.05448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05448"}},"official":{"repos":["symphonynet/SymphonyNet"],"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"]}}},{"url":"/paper/beyond-distributional-hypothesis-let-language","slug":"beyond-distributional-hypothesis-let-language","title":"Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text Correspondence","date":"2022-05-08","arxiv_id":"2205.03815","repositories_listed":1,"syntology":null},{"url":"/paper/vietnamese-automatic-speech-recognition-using","slug":"vietnamese-automatic-speech-recognition-using","title":"Vietnamese Automatic Speech Recognition using Wav2vec 2.0","date":"2022-05-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/aki-bert-a-pre-trained-clinical-language","slug":"aki-bert-a-pre-trained-clinical-language","title":"AKI-BERT: a Pre-trained Clinical Language Model for Early Prediction of Acute Kidney Injury","date":"2022-05-07","arxiv_id":"2205.03695","repositories_listed":1,"syntology":null},{"url":"/paper/a-data-cartography-based-mixup-for-pre","slug":"a-data-cartography-based-mixup-for-pre","title":"A Data Cartography based MixUp for Pre-trained Language Models","date":"2022-05-06","arxiv_id":"2205.03403","repositories_listed":1,"syntology":null},{"url":"/paper/kecp-knowledge-enhanced-contrastive-prompting","slug":"kecp-knowledge-enhanced-contrastive-prompting","title":"KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering","date":"2022-05-06","arxiv_id":"2205.03071","repositories_listed":1,"syntology":null},{"url":"/paper/the-unreliability-of-explanations-in-few-shot","slug":"the-unreliability-of-explanations-in-few-shot","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","date":"2022-05-06","arxiv_id":"2205.03401","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-contrastive-learning-objective-for","slug":"a-simple-contrastive-learning-objective-for","title":"A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration","date":"2022-05-05","arxiv_id":"2205.02517","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-simple-contrastive-learning-objective-for#ran","syntology_url":"https://syntology.ai/paper/2205.02517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.02517"}},"official":{"repos":["shaojiejiang/ct-loss"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/declaration-based-prompt-tuning-for-visual","slug":"declaration-based-prompt-tuning-for-visual","title":"Declaration-based Prompt Tuning for Visual Question Answering","date":"2022-05-05","arxiv_id":"2205.02456","repositories_listed":1,"syntology":null},{"url":"/paper/fastre-towards-fast-relation-extraction-with","slug":"fastre-towards-fast-relation-extraction-with","title":"FastRE: Towards Fast Relation Extraction with Convolutional Encoder and Improved Cascade Binary Tagging Framework","date":"2022-05-05","arxiv_id":"2205.02490","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-n-grams-induced-by-recurrence","slug":"implicit-n-grams-induced-by-recurrence","title":"Implicit N-grams Induced by Recurrence","date":"2022-05-05","arxiv_id":"2205.02724","repositories_listed":1,"syntology":null},{"url":"/paper/robust-conversational-agents-against","slug":"robust-conversational-agents-against","title":"Robust Conversational Agents against Imperceptible Toxicity Triggers","date":"2022-05-05","arxiv_id":"2205.02392","repositories_listed":1,"syntology":null},{"url":"/paper/provably-confidential-language-modelling-1","slug":"provably-confidential-language-modelling-1","title":"Provably Confidential Language Modelling","date":"2022-05-04","arxiv_id":"2205.01863","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/provably-confidential-language-modelling-1#ran","syntology_url":"https://syntology.ai/paper/2205.01863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01863"}},"official":{"repos":["xuandongzhao/crt"],"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":["found_in_text"]}}},{"url":"/paper/tlmote-a-topic-based-language-modelling","slug":"tlmote-a-topic-based-language-modelling","title":"TLMOTE: A Topic-based Language Modelling Approach for Text Oversampling","date":"2022-05-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-for-prompt-based-few","slug":"contrastive-learning-for-prompt-based-few","title":"Contrastive Learning for Prompt-Based Few-Shot Language Learners","date":"2022-05-03","arxiv_id":"2205.01308","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/contrastive-learning-for-prompt-based-few#ran","syntology_url":"https://syntology.ai/paper/2205.01308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01308"}},"official":{"repos":["yiren-jian/lm-supcon"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/embedding-hallucination-for-few-shot-language","slug":"embedding-hallucination-for-few-shot-language","title":"Embedding Hallucination for Few-Shot Language Fine-tuning","date":"2022-05-03","arxiv_id":"2205.01307","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":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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/embedding-hallucination-for-few-shot-language#ran","syntology_url":"https://syntology.ai/paper/2205.01307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01307"}},"official":{"repos":["yiren-jian/embedhalluc"],"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/entity-aware-transformers-for-entity-search","slug":"entity-aware-transformers-for-entity-search","title":"Entity-aware Transformers for Entity Search","date":"2022-05-02","arxiv_id":"2205.00820","repositories_listed":1,"syntology":null},{"url":"/paper/an-embarrassingly-simple-method-to-mitigate","slug":"an-embarrassingly-simple-method-to-mitigate","title":"An Embarrassingly Simple Method to Mitigate Undesirable Properties of Pretrained Language Model Tokenizers","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/answer-level-calibration-for-free-form","slug":"answer-level-calibration-for-free-form","title":"Answer-level Calibration for Free-form Multiple Choice Question Answering","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/chipsong-a-controllable-lyric-generation","slug":"chipsong-a-controllable-lyric-generation","title":"ChipSong: A Controllable Lyric Generation System for Chinese Popular Song","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/composing-structure-aware-batches-for-1","slug":"composing-structure-aware-batches-for-1","title":"Composing Structure-Aware Batches for Pairwise Sentence Classification","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-umls-named-entity-linking-using-1","slug":"cross-lingual-umls-named-entity-linking-using-1","title":"Cross-Lingual UMLS Named Entity Linking using UMLS Dictionary Fine-Tuning","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-cloze-task-a-new-task-to-brain-to","slug":"cross-modal-cloze-task-a-new-task-to-brain-to","title":"Cross-Modal Cloze Task: A New Task to Brain-to-Word Decoding","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/debiasing-pre-trained-language-models-via","slug":"debiasing-pre-trained-language-models-via","title":"Debiasing Pre-Trained Language Models via Efficient Fine-Tuning","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-neural-representations-for-multiword","slug":"deep-neural-representations-for-multiword","title":"Deep Neural Representations for Multiword Expressions Detection","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/domain-knowledge-transferring-for-pre-trained","slug":"domain-knowledge-transferring-for-pre-trained","title":"Domain Knowledge Transferring for Pre-trained Language Model via Calibrated Activation Boundary Distillation","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ds-tod-efficient-domain-specialization-for-2","slug":"ds-tod-efficient-domain-specialization-for-2","title":"DS-TOD: Efficient Domain Specialization for Task-Oriented Dialog","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cross-lingual-natural-language","slug":"enhancing-cross-lingual-natural-language","title":"Enhancing Cross-lingual Natural Language Inference by Prompt-learning from Cross-lingual Templates","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fire-burns-sword-cuts-commonsense-inductive","slug":"fire-burns-sword-cuts-commonsense-inductive","title":"Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/imputing-out-of-vocabulary-embeddings-with-1","slug":"imputing-out-of-vocabulary-embeddings-with-1","title":"Imputing Out-of-Vocabulary Embeddings with LOVE Makes LanguageModels Robust with Little Cost","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/infty-former-infinite-memory-transformer-1","slug":"infty-former-infinite-memory-transformer-1","title":"\\infty-former: Infinite Memory Transformer","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/joint-entity-and-relation-extraction-based-on","slug":"joint-entity-and-relation-extraction-based-on","title":"Joint Entity and Relation Extraction Based on Table Labeling Using Convolutional Neural Networks","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/language-models-as-context-sensitive-word","slug":"language-models-as-context-sensitive-word","title":"Language Models as Context-sensitive Word Search Engines","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mix-and-match-learning-free-controllable-text-3","slug":"mix-and-match-learning-free-controllable-text-3","title":"Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-structural-knowledge","slug":"multi-granularity-structural-knowledge","title":"Multi-Granularity Structural Knowledge Distillation for Language Model Compression","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/opi-lt-edi-acl2022-detecting-signs-of","slug":"opi-lt-edi-acl2022-detecting-signs-of","title":"OPI@LT-EDI-ACL2022: Detecting Signs of Depression from Social Media Text using RoBERTa Pre-trained Language Models","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/phone-ing-it-in-towards-flexible-multi-modal-1","slug":"phone-ing-it-in-towards-flexible-multi-modal-1","title":"Phone-ing it in: Towards Flexible Multi-Modal Language Model Training by Phonetic Representations of Data","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stylistic-response-generation-by-controlling","slug":"stylistic-response-generation-by-controlling","title":"Stylistic Response Generation by Controlling Personality Traits and Intent","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/thai-nested-named-entity-recognition-corpus","slug":"thai-nested-named-entity-recognition-corpus","title":"Thai Nested Named Entity Recognition Corpus","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-dependency-graph-network-1","slug":"unsupervised-dependency-graph-network-1","title":"Unsupervised Dependency Graph Network","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/c3-stisr-scene-text-image-super-resolution","slug":"c3-stisr-scene-text-image-super-resolution","title":"C3-STISR: Scene Text Image Super-resolution with Triple Clues","date":"2022-04-29","arxiv_id":"2204.14044","repositories_listed":1,"syntology":null},{"url":"/paper/oa-mine-open-world-attribute-mining-for-e","slug":"oa-mine-open-world-attribute-mining-for-e","title":"OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision","date":"2022-04-29","arxiv_id":"2204.13874","repositories_listed":1,"syntology":null},{"url":"/paper/cogview2-faster-and-better-text-to-image","slug":"cogview2-faster-and-better-text-to-image","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","date":"2022-04-28","arxiv_id":"2204.14217","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/cogview2-faster-and-better-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2204.14217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14217"}},"official":{"repos":["thudm/cogview2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hpt-hierarchy-aware-prompt-tuning-for","slug":"hpt-hierarchy-aware-prompt-tuning-for","title":"HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification","date":"2022-04-28","arxiv_id":"2204.13413","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 5 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/hpt-hierarchy-aware-prompt-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2204.13413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13413"}},"official":{"repos":["wzh9969/hpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/a-comprehensive-understanding-of-code-mixed","slug":"a-comprehensive-understanding-of-code-mixed","title":"A Comprehensive Understanding of Code-mixed Language Semantics using Hierarchical Transformer","date":"2022-04-27","arxiv_id":"2204.12753","repositories_listed":1,"syntology":null},{"url":"/paper/dialogved-a-pre-trained-latent-variable-1","slug":"dialogved-a-pre-trained-latent-variable-1","title":"DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation","date":"2022-04-27","arxiv_id":"2204.13031","repositories_listed":1,"syntology":null},{"url":"/paper/probing-simile-knowledge-from-pre-trained","slug":"probing-simile-knowledge-from-pre-trained","title":"Probing Simile Knowledge from Pre-trained Language Models","date":"2022-04-27","arxiv_id":"2204.12807","repositories_listed":1,"syntology":null},{"url":"/paper/ubert-a-novel-language-model-for-synonymy-1","slug":"ubert-a-novel-language-model-for-synonymy-1","title":"UBERT: A Novel Language Model for Synonymy Prediction at Scale in the UMLS Metathesaurus","date":"2022-04-27","arxiv_id":"2204.12716","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-machine-translation-domain-1","slug":"efficient-machine-translation-domain-1","title":"Efficient Machine Translation Domain Adaptation","date":"2022-04-26","arxiv_id":"2204.12608","repositories_listed":1,"syntology":null},{"url":"/paper/gypsum-learning-hybrid-representations-for","slug":"gypsum-learning-hybrid-representations-for","title":"GypSum: Learning Hybrid Representations for Code Summarization","date":"2022-04-26","arxiv_id":"2204.12916","repositories_listed":1,"syntology":null},{"url":"/paper/you-don-t-know-my-favorite-color-preventing","slug":"you-don-t-know-my-favorite-color-preventing","title":"You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas","date":"2022-04-26","arxiv_id":"2205.10228","repositories_listed":1,"syntology":null},{"url":"/paper/the-causal-news-corpus-annotating-causal","slug":"the-causal-news-corpus-annotating-causal","title":"The Causal News Corpus: Annotating Causal Relations in Event Sentences from News","date":"2022-04-25","arxiv_id":"2204.11714","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-causal-news-corpus-annotating-causal#ran","syntology_url":"https://syntology.ai/paper/2204.11714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.11714"}},"official":{"repos":["tanfiona/causalnewscorpus"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-representation-learning-of-2","slug":"unsupervised-representation-learning-of-2","title":"Unsupervised Representation Learning of Player Behavioral Data with Confidence Guided Masking","date":"2022-04-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/which-discriminator-for-cooperative-text","slug":"which-discriminator-for-cooperative-text","title":"Which Discriminator for Cooperative Text Generation?","date":"2022-04-25","arxiv_id":"2204.11586","repositories_listed":1,"syntology":null},{"url":"/paper/emotion-aware-transformer-encoder-for-1","slug":"emotion-aware-transformer-encoder-for-1","title":"Emotion-Aware Transformer Encoder for Empathetic Dialogue Generation","date":"2022-04-24","arxiv_id":"2204.11320","repositories_listed":1,"syntology":null},{"url":"/paper/kala-knowledge-augmented-language-model-1","slug":"kala-knowledge-augmented-language-model-1","title":"KALA: Knowledge-Augmented Language Model Adaptation","date":"2022-04-22","arxiv_id":"2204.10555","repositories_listed":1,"syntology":{"n":16,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/kala-knowledge-augmented-language-model-1#ran","syntology_url":"https://syntology.ai/paper/2204.10555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.10555"}},"official":{"repos":["nardien/kala"],"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":["found_in_text"]}}},{"url":"/paper/sparse-and-dense-approaches-for-the-full-rank","slug":"sparse-and-dense-approaches-for-the-full-rank","title":"Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues","date":"2022-04-22","arxiv_id":"2204.10558","repositories_listed":1,"syntology":null},{"url":"/paper/diffcse-difference-based-contrastive-learning","slug":"diffcse-difference-based-contrastive-learning","title":"DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings","date":"2022-04-21","arxiv_id":"2204.10298","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 2 unverified","sample_list":"/paper/diffcse-difference-based-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2204.10298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.10298"}},"official":{"repos":["voidism/diffcse"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/when-does-syntax-mediate-neural-language-1","slug":"when-does-syntax-mediate-neural-language-1","title":"When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes","date":"2022-04-20","arxiv_id":"2204.09722","repositories_listed":1,"syntology":null},{"url":"/paper/dialokg-knowledge-structure-aware-task","slug":"dialokg-knowledge-structure-aware-task","title":"DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation","date":"2022-04-19","arxiv_id":"2204.09149","repositories_listed":1,"syntology":null},{"url":"/paper/l3cube-hingcorpus-and-hingbert-a-code-mixed","slug":"l3cube-hingcorpus-and-hingbert-a-code-mixed","title":"L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models","date":"2022-04-18","arxiv_id":"2204.08398","repositories_listed":1,"syntology":null},{"url":"/paper/stablemoe-stable-routing-strategy-for-mixture-1","slug":"stablemoe-stable-routing-strategy-for-mixture-1","title":"StableMoE: Stable Routing Strategy for Mixture of Experts","date":"2022-04-18","arxiv_id":"2204.08396","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/stablemoe-stable-routing-strategy-for-mixture-1#ran","syntology_url":"https://syntology.ai/paper/2204.08396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08396"}},"official":{"repos":["hunter-ddm/stablemoe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-contrastive-cross-channel-data-augmentation","slug":"a-contrastive-cross-channel-data-augmentation","title":"A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis","date":"2022-04-16","arxiv_id":"2204.07832","repositories_listed":1,"syntology":null},{"url":"/paper/blcu-icall-at-semeval-2022-task-1-cross","slug":"blcu-icall-at-semeval-2022-task-1-cross","title":"BLCU-ICALL at SemEval-2022 Task 1: Cross-Attention Multitasking Framework for Definition Modeling","date":"2022-04-16","arxiv_id":"2204.07701","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-with-hard-negative","slug":"contrastive-learning-with-hard-negative","title":"Contrastive Learning with Hard Negative Entities for Entity Set Expansion","date":"2022-04-16","arxiv_id":"2204.07789","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-benchmarks-for-spanish-sentence","slug":"evaluation-benchmarks-for-spanish-sentence","title":"Evaluation Benchmarks for Spanish Sentence Representations","date":"2022-04-15","arxiv_id":"2204.07571","repositories_listed":1,"syntology":null},{"url":"/paper/improving-passage-retrieval-with-zero-shot","slug":"improving-passage-retrieval-with-zero-shot","title":"Improving Passage Retrieval with Zero-Shot Question Generation","date":"2022-04-15","arxiv_id":"2204.07496","repositories_listed":1,"syntology":{"n":14,"n_ran":8,"n_constructed":4,"n_ran_checked":5,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/improving-passage-retrieval-with-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2204.07496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07496"}},"official":{"repos":["DevSinghSachan/unsupervised-passage-reranking"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lamemo-language-modeling-with-look-ahead","slug":"lamemo-language-modeling-with-look-ahead","title":"LaMemo: Language Modeling with Look-Ahead Memory","date":"2022-04-15","arxiv_id":"2204.07341","repositories_listed":1,"syntology":null},{"url":"/paper/text-revision-by-on-the-fly-representation","slug":"text-revision-by-on-the-fly-representation","title":"Text Revision by On-the-Fly Representation Optimization","date":"2022-04-15","arxiv_id":"2204.07359","repositories_listed":1,"syntology":null},{"url":"/paper/generative-power-of-a-protein-language-model","slug":"generative-power-of-a-protein-language-model","title":"Generative power of a protein language model trained on multiple sequence alignments","date":"2022-04-14","arxiv_id":"2204.07110","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-multi-label-prompting-simple-and-1","slug":"automatic-multi-label-prompting-simple-and-1","title":"Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification","date":"2022-04-13","arxiv_id":"2204.06305","repositories_listed":1,"syntology":null},{"url":"/paper/gap-a-graph-aware-language-model-framework","slug":"gap-a-graph-aware-language-model-framework","title":"GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation","date":"2022-04-13","arxiv_id":"2204.06674","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-language-model-adaptive-fine","slug":"multilingual-language-model-adaptive-fine","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","date":"2022-04-13","arxiv_id":"2204.06487","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 2 unverified","sample_list":"/paper/multilingual-language-model-adaptive-fine#ran","syntology_url":"https://syntology.ai/paper/2204.06487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06487"}},"official":{"repos":["uds-lsv/afro-maft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/what-language-model-architecture-and","slug":"what-language-model-architecture-and","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","date":"2022-04-12","arxiv_id":"2204.05832","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/what-language-model-architecture-and#ran","syntology_url":"https://syntology.ai/paper/2204.05832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05832"}},"official":{"repos":["bigscience-workshop/architecture-objective"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-generative-language-model-for-few-shot-1","slug":"a-generative-language-model-for-few-shot-1","title":"A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis","date":"2022-04-11","arxiv_id":"2204.05356","repositories_listed":1,"syntology":null},{"url":"/paper/data-augmentation-for-biomedical-factoid-1","slug":"data-augmentation-for-biomedical-factoid-1","title":"Data Augmentation for Biomedical Factoid Question Answering","date":"2022-04-10","arxiv_id":"2204.04711","repositories_listed":1,"syntology":null},{"url":"/paper/biobart-pretraining-and-evaluation-of-a","slug":"biobart-pretraining-and-evaluation-of-a","title":"BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model","date":"2022-04-08","arxiv_id":"2204.03905","repositories_listed":1,"syntology":null},{"url":"/paper/characterizing-and-understanding-the-behavior","slug":"characterizing-and-understanding-the-behavior","title":"Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment","date":"2022-04-08","arxiv_id":"2204.04220","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-representation-learning-beyond-1","slug":"contextual-representation-learning-beyond-1","title":"Contextual Representation Learning beyond Masked Language Modeling","date":"2022-04-08","arxiv_id":"2204.04163","repositories_listed":1,"syntology":null},{"url":"/paper/enhance-incomplete-utterance-restoration-by","slug":"enhance-incomplete-utterance-restoration-by","title":"Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation","date":"2022-04-08","arxiv_id":"2204.03958","repositories_listed":1,"syntology":null},{"url":"/paper/fair-and-argumentative-language-modeling-for","slug":"fair-and-argumentative-language-modeling-for","title":"Fair and Argumentative Language Modeling for Computational Argumentation","date":"2022-04-08","arxiv_id":"2204.04026","repositories_listed":1,"syntology":null},{"url":"/paper/rubioroberta-a-pre-trained-biomedical","slug":"rubioroberta-a-pre-trained-biomedical","title":"RuBioRoBERTa: a pre-trained biomedical language model for Russian language biomedical text mining","date":"2022-04-08","arxiv_id":"2204.03951","repositories_listed":1,"syntology":null},{"url":"/paper/music-robust-automatic-lyrics-transcription","slug":"music-robust-automatic-lyrics-transcription","title":"Music-robust Automatic Lyrics Transcription of Polyphonic Music","date":"2022-04-07","arxiv_id":"2204.03306","repositories_listed":1,"syntology":null},{"url":"/paper/itervm-iterative-vision-modeling-module-for","slug":"itervm-iterative-vision-modeling-module-for","title":"IterVM: Iterative Vision Modeling Module for Scene Text Recognition","date":"2022-04-06","arxiv_id":"2204.02630","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-for-text-analytic-in","slug":"language-model-for-text-analytic-in","title":"SecureBERT: A Domain-Specific Language Model for Cybersecurity","date":"2022-04-06","arxiv_id":"2204.02685","repositories_listed":1,"syntology":null},{"url":"/paper/structure-aware-protein-self-supervised","slug":"structure-aware-protein-self-supervised","title":"Structure-aware Protein Self-supervised Learning","date":"2022-04-06","arxiv_id":"2204.04213","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-neural-reranking-for","slug":"parameter-efficient-neural-reranking-for","title":"Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval","date":"2022-04-05","arxiv_id":"2204.02292","repositories_listed":1,"syntology":null},{"url":"/paper/semanticcap-chromatin-accessibility","slug":"semanticcap-chromatin-accessibility","title":"SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model","date":"2022-04-05","arxiv_id":"2204.02130","repositories_listed":1,"syntology":null},{"url":"/paper/using-pre-trained-language-models-for","slug":"using-pre-trained-language-models-for","title":"Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study","date":"2022-04-04","arxiv_id":"2204.01440","repositories_listed":1,"syntology":null},{"url":"/paper/pos-bert-point-cloud-one-stage-bert-pre","slug":"pos-bert-point-cloud-one-stage-bert-pre","title":"POS-BERT: Point Cloud One-Stage BERT Pre-Training","date":"2022-04-03","arxiv_id":"2204.00989","repositories_listed":1,"syntology":null},{"url":"/paper/bert-assisted-semantic-annotation-correction","slug":"bert-assisted-semantic-annotation-correction","title":"BERT-Assisted Semantic Annotation Correction for Emotion-Related Questions","date":"2022-04-02","arxiv_id":"2204.00916","repositories_listed":1,"syntology":null},{"url":"/paper/ctrleval-an-unsupervised-reference-free","slug":"ctrleval-an-unsupervised-reference-free","title":"CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation","date":"2022-04-02","arxiv_id":"2204.00862","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/ctrleval-an-unsupervised-reference-free#ran","syntology_url":"https://syntology.ai/paper/2204.00862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.00862"}},"official":{"repos":["thu-coai/ctrleval"],"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/generating-recommendations-for-entity","slug":"generating-recommendations-for-entity","title":"Entity-Centric Query Refinement","date":"2022-04-02","arxiv_id":"2204.00743","repositories_listed":1,"syntology":null},{"url":"/paper/feature-structure-distillation-for-bert-1","slug":"feature-structure-distillation-for-bert-1","title":"Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring","date":"2022-04-01","arxiv_id":"2204.08922","repositories_listed":1,"syntology":null},{"url":"/paper/an-exploration-of-prompt-tuning-on-generative","slug":"an-exploration-of-prompt-tuning-on-generative","title":"SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks","date":"2022-03-31","arxiv_id":"2203.16773","repositories_listed":1,"syntology":null},{"url":"/paper/pada-pruning-assisted-domain-adaptation-for","slug":"pada-pruning-assisted-domain-adaptation-for","title":"PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations","date":"2022-03-31","arxiv_id":"2203.16965","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/pada-pruning-assisted-domain-adaptation-for#ran","syntology_url":"https://syntology.ai/paper/2203.16965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16965"}},"official":{"repos":["speech-lab-iitm/pada"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/pre-training-transformer-decoder-for-end-to","slug":"pre-training-transformer-decoder-for-end-to","title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","date":"2022-03-31","arxiv_id":"2203.17113","repositories_listed":1,"syntology":null},{"url":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","repositories_listed":1,"syntology":{"n":14,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 11 unverified","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}},"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]}}}],"record_sha256":"250e496ec0dca57152618723b5b2e73f9f33c73047ea3002a1a45caaea3eb1c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}