{"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/44","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":44,"pages_in_order":142,"rows_per_page":100,"rows":[4301,4400],"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/43","next":"/task/language-modeling/papers/45","papers":[{"url":"/paper/don-t-judge-a-language-model-by-its-last","slug":"don-t-judge-a-language-model-by-its-last","title":"Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling","date":"2022-09-13","arxiv_id":"2209.05972","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-neural-scaling-laws-in-language","slug":"revisiting-neural-scaling-laws-in-language","title":"Revisiting Neural Scaling Laws in Language and Vision","date":"2022-09-13","arxiv_id":"2209.06640","repositories_listed":1,"syntology":null},{"url":"/paper/open-domain-dialog-evaluation-using-follow","slug":"open-domain-dialog-evaluation-using-follow","title":"Open-Domain Dialog Evaluation using Follow-Ups Likelihood","date":"2022-09-12","arxiv_id":"2209.05185","repositories_listed":1,"syntology":null},{"url":"/paper/t-ner-an-all-round-python-library-for-1","slug":"t-ner-an-all-round-python-library-for-1","title":"T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition","date":"2022-09-09","arxiv_id":"2209.12616","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":3,"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/t-ner-an-all-round-python-library-for-1#ran","syntology_url":"https://syntology.ai/paper/2209.12616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12616"}},"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/idiapers-causal-news-corpus-2022-efficient","slug":"idiapers-causal-news-corpus-2022-efficient","title":"IDIAPers @ Causal News Corpus 2022: Efficient Causal Relation Identification Through a Prompt-based Few-shot Approach","date":"2022-09-08","arxiv_id":"2209.03895","repositories_listed":1,"syntology":null},{"url":"/paper/idiapers-causal-news-corpus-2022-extracting","slug":"idiapers-causal-news-corpus-2022-extracting","title":"IDIAPers @ Causal News Corpus 2022: Extracting Cause-Effect-Signal Triplets via Pre-trained Autoregressive Language Model","date":"2022-09-08","arxiv_id":"2209.03891","repositories_listed":1,"syntology":null},{"url":"/paper/non-autoregressive-error-correction-for-ctc","slug":"non-autoregressive-error-correction-for-ctc","title":"Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM","date":"2022-09-08","arxiv_id":"2209.04062","repositories_listed":1,"syntology":null},{"url":"/paper/asr2k-speech-recognition-for-around-2000","slug":"asr2k-speech-recognition-for-around-2000","title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","date":"2022-09-06","arxiv_id":"2209.02842","repositories_listed":1,"syntology":null},{"url":"/paper/mlphon-a-multifunctional-grapheme-phoneme","slug":"mlphon-a-multifunctional-grapheme-phoneme","title":"Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers","date":"2022-09-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/do-large-language-models-know-what-humans","slug":"do-large-language-models-know-what-humans","title":"Do Large Language Models know what humans know?","date":"2022-09-04","arxiv_id":"2209.01515","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-colbert-x","slug":"multilingual-colbert-x","title":"Neural Approaches to Multilingual Information Retrieval","date":"2022-09-03","arxiv_id":"2209.01335","repositories_listed":1,"syntology":null},{"url":"/paper/semantically-meaningful-metrics-for-norwegian","slug":"semantically-meaningful-metrics-for-norwegian","title":"Semantically Meaningful Metrics for Norwegian ASR Systems","date":"2022-09-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/transpolymer-a-transformer-based-language","slug":"transpolymer-a-transformer-based-language","title":"TransPolymer: a Transformer-based language model for polymer property predictions","date":"2022-09-03","arxiv_id":"2209.01307","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/transpolymer-a-transformer-based-language#ran","syntology_url":"https://syntology.ai/paper/2209.01307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.01307"}},"official":{"repos":["ChangwenXu98/TransPolymer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/folio-natural-language-reasoning-with-first","slug":"folio-natural-language-reasoning-with-first","title":"FOLIO: Natural Language Reasoning with First-Order Logic","date":"2022-09-02","arxiv_id":"2209.00840","repositories_listed":1,"syntology":null},{"url":"/paper/lexmae-lexicon-bottlenecked-pretraining-for","slug":"lexmae-lexicon-bottlenecked-pretraining-for","title":"LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval","date":"2022-08-31","arxiv_id":"2208.14754","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lexmae-lexicon-bottlenecked-pretraining-for#ran","syntology_url":"https://syntology.ai/paper/2208.14754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.14754"}},"official":{"repos":["taoshen58/lexmae"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/to-adapt-or-to-fine-tune-a-case-study-on","slug":"to-adapt-or-to-fine-tune-a-case-study-on","title":"To Adapt or to Fine-tune: A Case Study on Abstractive Summarization","date":"2022-08-30","arxiv_id":"2208.14559","repositories_listed":1,"syntology":null},{"url":"/paper/personal-attribute-prediction-from","slug":"personal-attribute-prediction-from","title":"Personal Attribute Prediction from Conversations","date":"2022-08-29","arxiv_id":"2209.09619","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-neural-network-language-modeling-for","slug":"bayesian-neural-network-language-modeling-for","title":"Bayesian Neural Network Language Modeling for Speech Recognition","date":"2022-08-28","arxiv_id":"2208.13259","repositories_listed":1,"syntology":null},{"url":"/paper/induced-natural-language-rationales-and","slug":"induced-natural-language-rationales-and","title":"Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models","date":"2022-08-24","arxiv_id":"2208.11445","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/induced-natural-language-rationales-and#ran","syntology_url":"https://syntology.ai/paper/2208.11445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.11445"}},"official":{"repos":["mirelleb/induced-rationales-markup-tokens"],"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/interpreting-song-lyrics-with-an-audio","slug":"interpreting-song-lyrics-with-an-audio","title":"Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model","date":"2022-08-24","arxiv_id":"2208.11671","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-unlabeled-3d-environments-for","slug":"learning-from-unlabeled-3d-environments-for","title":"Learning from Unlabeled 3D Environments for Vision-and-Language Navigation","date":"2022-08-24","arxiv_id":"2208.11781","repositories_listed":1,"syntology":null},{"url":"/paper/learning-better-masking-for-better-language","slug":"learning-better-masking-for-better-language","title":"Learning Better Masking for Better Language Model Pre-training","date":"2022-08-23","arxiv_id":"2208.10806","repositories_listed":1,"syntology":null},{"url":"/paper/learning-dynamic-contextualised-word","slug":"learning-dynamic-contextualised-word","title":"Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation","date":"2022-08-23","arxiv_id":"2208.10734","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-as-probing-using-language-models","slug":"prompting-as-probing-using-language-models","title":"Prompting as Probing: Using Language Models for Knowledge Base Construction","date":"2022-08-23","arxiv_id":"2208.11057","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prompting-as-probing-using-language-models#ran","syntology_url":"https://syntology.ai/paper/2208.11057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.11057"}},"official":{"repos":["hemile/iswc-challenge"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/z-code-a-pre-trained-language-model-optimized","slug":"z-code-a-pre-trained-language-model-optimized","title":"Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization","date":"2022-08-21","arxiv_id":"2208.09770","repositories_listed":1,"syntology":null},{"url":"/paper/ask-question-first-for-enhancing-lifelong","slug":"ask-question-first-for-enhancing-lifelong","title":"Ask Question First for Enhancing Lifelong Language Learning","date":"2022-08-17","arxiv_id":"2208.08367","repositories_listed":1,"syntology":null},{"url":"/paper/neural-embeddings-for-text","slug":"neural-embeddings-for-text","title":"Neural Embeddings for Text","date":"2022-08-17","arxiv_id":"2208.08386","repositories_listed":1,"syntology":null},{"url":"/paper/syntax-driven-data-augmentation-for-named","slug":"syntax-driven-data-augmentation-for-named","title":"Syntax-driven Data Augmentation for Named Entity Recognition","date":"2022-08-15","arxiv_id":"2208.06957","repositories_listed":1,"syntology":null},{"url":"/paper/lm-core-language-models-with-contextually-1","slug":"lm-core-language-models-with-contextually-1","title":"LM-CORE: Language Models with Contextually Relevant External Knowledge","date":"2022-08-12","arxiv_id":"2208.06458","repositories_listed":1,"syntology":null},{"url":"/paper/roc-a-new-paradigm-for-lyric-to-melody","slug":"roc-a-new-paradigm-for-lyric-to-melody","title":"Re-creation of Creations: A New Paradigm for Lyric-to-Melody Generation","date":"2022-08-11","arxiv_id":"2208.05697","repositories_listed":1,"syntology":null},{"url":"/paper/coditt5-pretraining-for-source-code-and","slug":"coditt5-pretraining-for-source-code-and","title":"CoditT5: Pretraining for Source Code and Natural Language Editing","date":"2022-08-10","arxiv_id":"2208.05446","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-perceived-emotion-in-symbolic","slug":"controlling-perceived-emotion-in-symbolic","title":"Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Search","date":"2022-08-10","arxiv_id":"2208.05162","repositories_listed":1,"syntology":null},{"url":"/paper/thai-wav2vec2-0-with-commonvoice-v8","slug":"thai-wav2vec2-0-with-commonvoice-v8","title":"Thai Wav2Vec2.0 with CommonVoice V8","date":"2022-08-09","arxiv_id":"2208.04799","repositories_listed":1,"syntology":null},{"url":"/paper/grit-vlp-grouped-mini-batch-sampling-for","slug":"grit-vlp-grouped-mini-batch-sampling-for","title":"GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training","date":"2022-08-08","arxiv_id":"2208.04060","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/grit-vlp-grouped-mini-batch-sampling-for#ran","syntology_url":"https://syntology.ai/paper/2208.04060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.04060"}},"official":{"repos":["jaeseokbyun/grit-vlp"],"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/when-can-i-speak-predicting-initiation-points","slug":"when-can-i-speak-predicting-initiation-points","title":"When can I Speak? Predicting initiation points for spoken dialogue agents","date":"2022-08-07","arxiv_id":"2208.03812","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-can-i-speak-predicting-initiation-points#ran","syntology_url":"https://syntology.ai/paper/2208.03812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03812"}},"official":{"repos":["siyan-sylvia-li/icarus_final"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-no-1-in-clue-semantic-matching","slug":"towards-no-1-in-clue-semantic-matching","title":"Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss","date":"2022-08-05","arxiv_id":"2208.02959","repositories_listed":1,"syntology":null},{"url":"/paper/fusing-sentence-embeddings-into-lstm-based","slug":"fusing-sentence-embeddings-into-lstm-based","title":"Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models","date":"2022-08-04","arxiv_id":"2208.02402","repositories_listed":1,"syntology":null},{"url":"/paper/alexatm-20b-few-shot-learning-using-a-large","slug":"alexatm-20b-few-shot-learning-using-a-large","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","date":"2022-08-02","arxiv_id":"2208.01448","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alexatm-20b-few-shot-learning-using-a-large#ran","syntology_url":"https://syntology.ai/paper/2208.01448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01448"}},"official":null}},{"url":"/paper/composable-text-control-operations-in-latent","slug":"composable-text-control-operations-in-latent","title":"Composable Text Controls in Latent Space with ODEs","date":"2022-08-01","arxiv_id":"2208.00638","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-limitations-of-sociodemographic","slug":"on-the-limitations-of-sociodemographic","title":"On the Limitations of Sociodemographic Adaptation with Transformers","date":"2022-08-01","arxiv_id":"2208.01029","repositories_listed":1,"syntology":null},{"url":"/paper/aggretriever-a-simple-approach-to-aggregate","slug":"aggretriever-a-simple-approach-to-aggregate","title":"Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval","date":"2022-07-31","arxiv_id":"2208.00511","repositories_listed":1,"syntology":null},{"url":"/paper/smoothing-entailment-graphs-with-language","slug":"smoothing-entailment-graphs-with-language","title":"Smoothing Entailment Graphs with Language Models","date":"2022-07-30","arxiv_id":"2208.00318","repositories_listed":1,"syntology":null},{"url":"/paper/helixfold-single-msa-free-protein-structure","slug":"helixfold-single-msa-free-protein-structure","title":"HelixFold-Single: MSA-free Protein Structure Prediction by Using Protein Language Model as an Alternative","date":"2022-07-28","arxiv_id":"2207.13921","repositories_listed":1,"syntology":null},{"url":"/paper/knowing-where-and-what-unified-word-block","slug":"knowing-where-and-what-unified-word-block","title":"Knowing Where and What: Unified Word Block Pretraining for Document Understanding","date":"2022-07-28","arxiv_id":"2207.13979","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-to-sequence-pretraining-for-a-less","slug":"sequence-to-sequence-pretraining-for-a-less","title":"Sequence to sequence pretraining for a less-resourced Slovenian language","date":"2022-07-28","arxiv_id":"2207.13988","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-information-and-commonsense-based","slug":"contextual-information-and-commonsense-based","title":"Contextual Information and Commonsense Based Prompt for Emotion Recognition in Conversation","date":"2022-07-27","arxiv_id":"2207.13254","repositories_listed":1,"syntology":null},{"url":"/paper/point-mcbert-a-multi-choice-self-supervised","slug":"point-mcbert-a-multi-choice-self-supervised","title":"Boosting Point-BERT by Multi-choice Tokens","date":"2022-07-27","arxiv_id":"2207.13226","repositories_listed":1,"syntology":null},{"url":"/paper/soundchoice-grapheme-to-phoneme-models-with","slug":"soundchoice-grapheme-to-phoneme-models-with","title":"SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation","date":"2022-07-27","arxiv_id":"2207.13703","repositories_listed":1,"syntology":null},{"url":"/paper/training-effective-neural-sentence-encoders","slug":"training-effective-neural-sentence-encoders","title":"Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases","date":"2022-07-26","arxiv_id":"2207.12759","repositories_listed":1,"syntology":null},{"url":"/paper/chunk-aware-alignment-and-lexical-constraint","slug":"chunk-aware-alignment-and-lexical-constraint","title":"Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations","date":"2022-07-23","arxiv_id":"2207.11401","repositories_listed":1,"syntology":null},{"url":"/paper/pangu-coder-program-synthesis-with-function","slug":"pangu-coder-program-synthesis-with-function","title":"PanGu-Coder: Program Synthesis with Function-Level Language Modeling","date":"2022-07-22","arxiv_id":"2207.11280","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-video-captioning-with-evolving","slug":"zero-shot-video-captioning-with-evolving","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","date":"2022-07-22","arxiv_id":"2207.11100","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-cascades","slug":"language-model-cascades","title":"Language Model Cascades","date":"2022-07-21","arxiv_id":"2207.10342","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":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-model-cascades#ran","syntology_url":"https://syntology.ai/paper/2207.10342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10342"}},"official":{"repos":["google-research/cascades"],"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/the-birth-of-bias-a-case-study-on-the-1","slug":"the-birth-of-bias-a-case-study-on-the-1","title":"The Birth of Bias: A case study on the evolution of gender bias in an English language model","date":"2022-07-21","arxiv_id":"2207.10245","repositories_listed":1,"syntology":null},{"url":"/paper/label2label-a-language-modeling-framework-for","slug":"label2label-a-language-modeling-framework-for","title":"Label2Label: A Language Modeling Framework for Multi-Attribute Learning","date":"2022-07-18","arxiv_id":"2207.08677","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"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) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/label2label-a-language-modeling-framework-for#ran","syntology_url":"https://syntology.ai/paper/2207.08677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08677"}},"official":{"repos":["li-wanhua/label2label"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/electra-is-a-zero-shot-learner-too","slug":"electra-is-a-zero-shot-learner-too","title":"ELECTRA is a Zero-Shot Learner, Too","date":"2022-07-17","arxiv_id":"2207.08141","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/electra-is-a-zero-shot-learner-too#ran","syntology_url":"https://syntology.ai/paper/2207.08141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08141"}},"official":{"repos":["nishiwen1214/rtd-electra"],"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/clover-towards-a-unified-video-language","slug":"clover-towards-a-unified-video-language","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","date":"2022-07-16","arxiv_id":"2207.07885","repositories_listed":1,"syntology":null},{"url":"/paper/multilinguals-at-semeval-2022-task-11-complex-1","slug":"multilinguals-at-semeval-2022-task-11-complex-1","title":"Multilinguals at SemEval-2022 Task 11: Complex NER in Semantically Ambiguous Settings for Low Resource Languages","date":"2022-07-14","arxiv_id":"2207.06882","repositories_listed":1,"syntology":null},{"url":"/paper/lm-nav-robotic-navigation-with-large-pre","slug":"lm-nav-robotic-navigation-with-large-pre","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","date":"2022-07-10","arxiv_id":"2207.04429","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/lm-nav-robotic-navigation-with-large-pre#ran","syntology_url":"https://syntology.ai/paper/2207.04429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.04429"}},"official":{"repos":["blazejosinski/lm_nav"],"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/the-harvard-uspto-patent-dataset-a-large-1","slug":"the-harvard-uspto-patent-dataset-a-large-1","title":"The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications","date":"2022-07-08","arxiv_id":"2207.04043","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/the-harvard-uspto-patent-dataset-a-large-1#ran","syntology_url":"https://syntology.ai/paper/2207.04043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.04043"}},"official":{"repos":["suzgunmirac/hupd"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/meta-learning-the-difference-preparing-large","slug":"meta-learning-the-difference-preparing-large","title":"Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation","date":"2022-07-07","arxiv_id":"2207.03509","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/meta-learning-the-difference-preparing-large#ran","syntology_url":"https://syntology.ai/paper/2207.03509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.03509"}},"official":{"repos":["amazon-research/meta-learning-the-difference"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/gender-biases-and-where-to-find-them","slug":"gender-biases-and-where-to-find-them","title":"Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruning","date":"2022-07-06","arxiv_id":"2207.02463","repositories_listed":1,"syntology":null},{"url":"/paper/simlm-pre-training-with-representation","slug":"simlm-pre-training-with-representation","title":"SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval","date":"2022-07-06","arxiv_id":"2207.02578","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-robustness-analysis-against","slug":"multi-modal-robustness-analysis-against","title":"Robustness Analysis of Video-Language Models Against Visual and Language Perturbations","date":"2022-07-05","arxiv_id":"2207.02159","repositories_listed":1,"syntology":null},{"url":"/paper/egocentric-video-language-pretraining-ego4d","slug":"egocentric-video-language-pretraining-ego4d","title":"Egocentric Video-Language Pretraining @ Ego4D Challenge 2022","date":"2022-07-04","arxiv_id":"2207.01622","repositories_listed":1,"syntology":null},{"url":"/paper/egocentric-video-language-pretraining-epic","slug":"egocentric-video-language-pretraining-epic","title":"Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022","date":"2022-07-04","arxiv_id":"2207.01334","repositories_listed":1,"syntology":null},{"url":"/paper/probing-via-prompting","slug":"probing-via-prompting","title":"Probing via Prompting","date":"2022-07-04","arxiv_id":"2207.01736","repositories_listed":1,"syntology":null},{"url":"/paper/generating-repetitions-with-appropriate","slug":"generating-repetitions-with-appropriate","title":"Generating Repetitions with Appropriate Repeated Words","date":"2022-07-03","arxiv_id":"2207.00929","repositories_listed":1,"syntology":null},{"url":"/paper/cl-relkt-cross-lingual-language-knowledge","slug":"cl-relkt-cross-lingual-language-knowledge","title":"CL-ReLKT: Cross-lingual Language Knowledge Transfer for Multilingual Retrieval Question Answering","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/clinical-flair-a-pre-trained-language-model","slug":"clinical-flair-a-pre-trained-language-model","title":"Clinical Flair: A Pre-Trained Language Model for Spanish Clinical Natural Language Processing","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/compm-context-modeling-with-speakers-pre","slug":"compm-context-modeling-with-speakers-pre","title":"CoMPM: Context Modeling with Speaker’s Pre-trained Memory Tracking for Emotion Recognition in Conversation","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/conflibert-a-pre-trained-language-model-for","slug":"conflibert-a-pre-trained-language-model-for","title":"ConfliBERT: A Pre-trained Language Model for Political Conflict and Violence","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exposing-the-limits-of-video-text-models-1","slug":"exposing-the-limits-of-video-text-models-1","title":"Exposing the Limits of Video-Text Models through Contrast Sets","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hate-ita-new-baselines-for-hate-speech","slug":"hate-ita-new-baselines-for-hate-speech","title":"HATE-ITA: New Baselines for Hate Speech Detection in Italian","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/identifying-human-needs-through-social-media","slug":"identifying-human-needs-through-social-media","title":"Identifying Human Needs through Social Media: A study on Indian cities during COVID-19","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-natural-language-generation-with","slug":"learning-natural-language-generation-with","title":"Learning Natural Language Generation with Truncated Reinforcement Learning","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/marsan-at-semeval-2022-task-11-multilingual","slug":"marsan-at-semeval-2022-task-11-multilingual","title":"MarSan at SemEval-2022 Task 11: Multilingual complex named entity recognition using T5 and transformer encoder","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/modal-dependency-parsing-via-language-model","slug":"modal-dependency-parsing-via-language-model","title":"Modal Dependency Parsing via Language Model Priming","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/valcat-variable-length-contextualized","slug":"valcat-variable-length-contextualized","title":"ValCAT: Variable-Length Contextualized Adversarial Transformations Using Encoder-Decoder Language Model","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/you-dont-know-my-favorite-color-preventing","slug":"you-dont-know-my-favorite-color-preventing","title":"You Don’t Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers’ Private Personas","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/forecasting-future-world-events-with-neural","slug":"forecasting-future-world-events-with-neural","title":"Forecasting Future World Events with Neural Networks","date":"2022-06-30","arxiv_id":"2206.15474","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/forecasting-future-world-events-with-neural#ran","syntology_url":"https://syntology.ai/paper/2206.15474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.15474"}},"official":{"repos":["andyzoujm/autocast"],"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/gsclip-a-framework-for-explaining","slug":"gsclip-a-framework-for-explaining","title":"GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language","date":"2022-06-30","arxiv_id":"2206.15007","repositories_listed":1,"syntology":null},{"url":"/paper/improving-visual-grounding-by-encouraging","slug":"improving-visual-grounding-by-encouraging","title":"Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations","date":"2022-06-30","arxiv_id":"2206.15462","repositories_listed":1,"syntology":null},{"url":"/paper/solving-quantitative-reasoning-problems-with","slug":"solving-quantitative-reasoning-problems-with","title":"Solving Quantitative Reasoning Problems with Language Models","date":"2022-06-29","arxiv_id":"2206.14858","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-data-driven-requirements","slug":"towards-a-data-driven-requirements","title":"Towards a Data-Driven Requirements Engineering Approach: Automatic Analysis of User Reviews","date":"2022-06-29","arxiv_id":"2206.14669","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-fine-grained-entity-typing-with","slug":"few-shot-fine-grained-entity-typing-with","title":"Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation","date":"2022-06-28","arxiv_id":"2206.13746","repositories_listed":1,"syntology":null},{"url":"/paper/long-range-language-modeling-via-gated-state","slug":"long-range-language-modeling-via-gated-state","title":"Long Range Language Modeling via Gated State Spaces","date":"2022-06-27","arxiv_id":"2206.13947","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-range-language-modeling-via-gated-state#ran","syntology_url":"https://syntology.ai/paper/2206.13947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13947"}},"official":null}},{"url":"/paper/distilling-a-pretrained-language-model-to-a","slug":"distilling-a-pretrained-language-model-to-a","title":"Distilling a Pretrained Language Model to a Multilingual ASR Model","date":"2022-06-25","arxiv_id":"2206.12638","repositories_listed":1,"syntology":null},{"url":"/paper/godel-large-scale-pre-training-for-goal","slug":"godel-large-scale-pre-training-for-goal","title":"GODEL: Large-Scale Pre-Training for Goal-Directed Dialog","date":"2022-06-22","arxiv_id":"2206.11309","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-controllable-product-copywriting","slug":"automatic-controllable-product-copywriting","title":"Automatic Controllable Product Copywriting for E-Commerce","date":"2022-06-21","arxiv_id":"2206.10103","repositories_listed":1,"syntology":null},{"url":"/paper/benchclamp-a-benchmark-for-evaluating","slug":"benchclamp-a-benchmark-for-evaluating","title":"BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing","date":"2022-06-21","arxiv_id":"2206.10668","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"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; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchclamp-a-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2206.10668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.10668"}},"official":{"repos":["microsoft/semantic_parsing_with_constrained_lm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/questions-are-all-you-need-to-train-a-dense","slug":"questions-are-all-you-need-to-train-a-dense","title":"Questions Are All You Need to Train a Dense Passage Retriever","date":"2022-06-21","arxiv_id":"2206.10658","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/questions-are-all-you-need-to-train-a-dense#ran","syntology_url":"https://syntology.ai/paper/2206.10658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.10658"}},"official":{"repos":["DevSinghSachan/art"],"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/semmae-semantic-guided-masking-for-learning","slug":"semmae-semantic-guided-masking-for-learning","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","date":"2022-06-21","arxiv_id":"2206.10207","repositories_listed":1,"syntology":null},{"url":"/paper/fewer-errors-but-more-stereotypes-the-effect","slug":"fewer-errors-but-more-stereotypes-the-effect","title":"Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias","date":"2022-06-20","arxiv_id":"2206.09860","repositories_listed":1,"syntology":null},{"url":"/paper/precogiiith-at-hinglisheval-leveraging-code","slug":"precogiiith-at-hinglisheval-leveraging-code","title":"PreCogIIITH at HinglishEval : Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix Quality","date":"2022-06-16","arxiv_id":"2206.07988","repositories_listed":1,"syntology":null},{"url":"/paper/director-generator-classifiers-for-supervised","slug":"director-generator-classifiers-for-supervised","title":"DIRECTOR: Generator-Classifiers For Supervised Language Modeling","date":"2022-06-15","arxiv_id":"2206.07694","repositories_listed":1,"syntology":null},{"url":"/paper/prefix-language-models-are-unified-modal","slug":"prefix-language-models-are-unified-modal","title":"Write and Paint: Generative Vision-Language Models are Unified Modal Learners","date":"2022-06-15","arxiv_id":"2206.07699","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/prefix-language-models-are-unified-modal#ran","syntology_url":"https://syntology.ai/paper/2206.07699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07699"}},"official":{"repos":["shizhediao/davinci"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lavender-unifying-video-language","slug":"lavender-unifying-video-language","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","date":"2022-06-14","arxiv_id":"2206.07160","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/lavender-unifying-video-language#ran","syntology_url":"https://syntology.ai/paper/2206.07160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07160"}},"official":{"repos":["microsoft/lavender"],"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/egru-event-based-gru-for-activity-sparse","slug":"egru-event-based-gru-for-activity-sparse","title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","date":"2022-06-13","arxiv_id":"2206.06178","repositories_listed":1,"syntology":null},{"url":"/paper/jiuzhang-a-chinese-pre-trained-language-model","slug":"jiuzhang-a-chinese-pre-trained-language-model","title":"JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding","date":"2022-06-13","arxiv_id":"2206.06315","repositories_listed":1,"syntology":null}],"record_sha256":"0b653a73859d6f2627bb5f24f878eb9c801e838c352abff932b12b03aca1060b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}