{"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/51","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":51,"pages_in_order":142,"rows_per_page":100,"rows":[5001,5100],"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/50","next":"/task/language-modeling/papers/52","papers":[{"url":"/paper/towards-neural-programming-interfaces-1","slug":"towards-neural-programming-interfaces-1","title":"Towards Neural Programming Interfaces","date":"2020-12-10","arxiv_id":"2012.05983","repositories_listed":1,"syntology":null},{"url":"/paper/tap-text-aware-pre-training-for-text-vqa-and","slug":"tap-text-aware-pre-training-for-text-vqa-and","title":"TAP: Text-Aware Pre-training for Text-VQA and Text-Caption","date":"2020-12-08","arxiv_id":"2012.04638","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-protein-language-models-with","slug":"pre-training-protein-language-models-with","title":"Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream Tasks","date":"2020-12-05","arxiv_id":"2012.03084","repositories_listed":1,"syntology":null},{"url":"/paper/meta-kd-a-meta-knowledge-distillation","slug":"meta-kd-a-meta-knowledge-distillation","title":"Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains","date":"2020-12-02","arxiv_id":"2012.01266","repositories_listed":1,"syntology":null},{"url":"/paper/a-co-attentive-cross-lingual-neural-model-for","slug":"a-co-attentive-cross-lingual-neural-model-for","title":"A Co-Attentive Cross-Lingual Neural Model for Dialogue Breakdown Detection","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-sentiment-annotated-dataset-of-english","slug":"a-sentiment-annotated-dataset-of-english","title":"A Sentiment-annotated Dataset of English Causal Connectives","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/composing-byte-pair-encodings-for","slug":"composing-byte-pair-encodings-for","title":"Composing Byte-Pair Encodings for Morphological Sequence Classification","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-automatic-speech-recognition-for","slug":"end-to-end-automatic-speech-recognition-for","title":"End-to-End Automatic Speech Recognition for Gujarati","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-clinical-bert-embedding-using-a","slug":"enhancing-clinical-bert-embedding-using-a","title":"Enhancing Clinical BERT Embedding using a Biomedical Knowledge Base","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-zero-shot-limit-of-fewrel","slug":"exploring-the-zero-shot-limit-of-fewrel","title":"Exploring the zero-shot limit of FewRel","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/increasing-learning-efficiency-of-self","slug":"increasing-learning-efficiency-of-self","title":"Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/incremental-neural-lexical-coherence-modeling","slug":"incremental-neural-lexical-coherence-modeling","title":"Incremental Neural Lexical Coherence Modeling","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/kungfupanda-at-semeval-2020-task-12-bert-1","slug":"kungfupanda-at-semeval-2020-task-12-bert-1","title":"Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-TaskLearning for Offensive Language Detection","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/language-model-transformers-as-evaluators-for","slug":"language-model-transformers-as-evaluators-for","title":"Language Model Transformers as Evaluators for Open-domain Dialogues","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/monolingual-and-multilingual-reduction-of","slug":"monolingual-and-multilingual-reduction-of","title":"Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-learning-for-knowledge-graph","slug":"multi-task-learning-for-knowledge-graph","title":"Multi-Task Learning for Knowledge Graph Completion with Pre-trained Language Models","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/retrieving-skills-from-job-descriptions-a","slug":"retrieving-skills-from-job-descriptions-a","title":"Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/scale-down-transformer-by-grouping-features","slug":"scale-down-transformer-by-grouping-features","title":"Scale down Transformer by Grouping Features for a Lightweight Character-level Language Model","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sentix-a-sentiment-aware-pre-trained-model","slug":"sentix-a-sentiment-aware-pre-trained-model","title":"SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tablegpt-few-shot-table-to-text-generation","slug":"tablegpt-few-shot-table-to-text-generation","title":"TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-generating-query-to-perform-query","slug":"towards-generating-query-to-perform-query","title":"Towards Generating Query to Perform Query Focused Abstractive Summarization using Pre-trained Model","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/try-to-substitute-an-unsupervised-chinese","slug":"try-to-substitute-an-unsupervised-chinese","title":"Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unihanlm-coarse-to-fine-chinese-japanese","slug":"unihanlm-coarse-to-fine-chinese-japanese","title":"UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/coarse-to-fine-memory-matching-for-joint","slug":"coarse-to-fine-memory-matching-for-joint","title":"Coarse-to-Fine Memory Matching for Joint Retrieval and Classification","date":"2020-11-29","arxiv_id":"2012.02287","repositories_listed":1,"syntology":null},{"url":"/paper/automated-coding-of-under-studied-medical","slug":"automated-coding-of-under-studied-medical","title":"Automated Coding of Under-Studied Medical Concept Domains: Linking Physical Activity Reports to the International Classification of Functioning, Disability, and Health","date":"2020-11-27","arxiv_id":"2011.13978","repositories_listed":1,"syntology":null},{"url":"/paper/language-generation-via-combinatorial","slug":"language-generation-via-combinatorial","title":"Language Generation via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach","date":"2020-11-24","arxiv_id":"2011.12334","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-domain-adaptation-of-a","slug":"unsupervised-domain-adaptation-of-a","title":"Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model","date":"2020-11-23","arxiv_id":"2011.11499","repositories_listed":1,"syntology":null},{"url":"/paper/generating-negative-commonsense-knowledge","slug":"generating-negative-commonsense-knowledge","title":"NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases","date":"2020-11-15","arxiv_id":"2011.07497","repositories_listed":1,"syntology":null},{"url":"/paper/utilizing-bidirectional-encoder","slug":"utilizing-bidirectional-encoder","title":"Utilizing Bidirectional Encoder Representations from Transformers for Answer Selection","date":"2020-11-14","arxiv_id":"2011.07208","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-stand-alone-neural-spelling","slug":"context-aware-stand-alone-neural-spelling","title":"Context-aware Stand-alone Neural Spelling Correction","date":"2020-11-12","arxiv_id":"2011.06642","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-a-local-translation-mechanism","slug":"incorporating-a-local-translation-mechanism","title":"Incorporating a Local Translation Mechanism into Non-autoregressive Translation","date":"2020-11-12","arxiv_id":"2011.06132","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":2,"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 2 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","sample_list":"/paper/incorporating-a-local-translation-mechanism#ran","syntology_url":"https://syntology.ai/paper/2011.06132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.06132"}},"official":{"repos":["shawnkx/NAT-with-Local-AT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-hidden-markov-language-models","slug":"scaling-hidden-markov-language-models","title":"Scaling Hidden Markov Language Models","date":"2020-11-09","arxiv_id":"2011.04640","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-a-language-model-for-controlled","slug":"adapting-a-language-model-for-controlled","title":"Adapting a Language Model for Controlled Affective Text Generation","date":"2020-11-08","arxiv_id":"2011.04000","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adapting-a-language-model-for-controlled#ran","syntology_url":"https://syntology.ai/paper/2011.04000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.04000"}},"official":{"repos":["ishikasingh/Affective-text-gen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/knowledge-driven-self-supervision-for-zero","slug":"knowledge-driven-self-supervision-for-zero","title":"Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering","date":"2020-11-07","arxiv_id":"2011.03863","repositories_listed":1,"syntology":null},{"url":"/paper/indic-transformers-an-analysis-of-transformer","slug":"indic-transformers-an-analysis-of-transformer","title":"Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages","date":"2020-11-04","arxiv_id":"2011.02323","repositories_listed":1,"syntology":null},{"url":"/paper/charbert-character-aware-pre-trained-language","slug":"charbert-character-aware-pre-trained-language","title":"CharBERT: Character-aware Pre-trained Language Model","date":"2020-11-03","arxiv_id":"2011.01513","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/charbert-character-aware-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2011.01513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01513"}},"official":{"repos":["wtma/CharBERT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/data-to-text-generation-with-iterative-text","slug":"data-to-text-generation-with-iterative-text","title":"Data-to-Text Generation with Iterative Text Editing","date":"2020-11-03","arxiv_id":"2011.01694","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-contrastive-learning-for-pre-1","slug":"supervised-contrastive-learning-for-pre-1","title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning","date":"2020-11-03","arxiv_id":"2011.01403","repositories_listed":1,"syntology":null},{"url":"/paper/improving-variational-autoencoder-for-text","slug":"improving-variational-autoencoder-for-text","title":"Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation","date":"2020-11-02","arxiv_id":"2011.01136","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/improving-variational-autoencoder-for-text#ran","syntology_url":"https://syntology.ai/paper/2011.01136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01136"}},"official":{"repos":["ruizheliUOA/TWR-VAE"],"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/adapting-open-domain-fact-extraction-and","slug":"adapting-open-domain-fact-extraction-and","title":"Adapting Open Domain Fact Extraction and Verification to COVID-FACT through In-Domain Language Modeling","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-exploration-of-local-ordering","slug":"an-empirical-exploration-of-local-ordering","title":"An Empirical Exploration of Local Ordering Pre-training for Structured Prediction","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/analysing-word-representation-from-the-input","slug":"analysing-word-representation-from-the-input","title":"Analysing Word Representation from the Input and Output Embeddings in Neural Network Language Models","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/biomedical-event-extraction-as-multi-turn","slug":"biomedical-event-extraction-as-multi-turn","title":"Biomedical Event Extraction as Multi-turn Question Answering","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/coding-textual-inputs-boosts-the-accuracy-of","slug":"coding-textual-inputs-boosts-the-accuracy-of","title":"Coding Textual Inputs Boosts the Accuracy of Neural Networks","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/controlling-the-imprint-of-passivization-and","slug":"controlling-the-imprint-of-passivization-and","title":"Controlling the Imprint of Passivization and Negation in Contextualized Representations","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/detecting-entailment-in-code-mixed-hindi","slug":"detecting-entailment-in-code-mixed-hindi","title":"Detecting Entailment in Code-Mixed Hindi-English Conversations","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/filtering-noisy-parallel-corpus-using","slug":"filtering-noisy-parallel-corpus-using","title":"Filtering Noisy Parallel Corpus using Transformers with Proxy Task Learning","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/limit-bert-linguistics-informed-multi-task","slug":"limit-bert-linguistics-informed-multi-task","title":"LIMIT-BERT : Linguistics Informed Multi-Task BERT","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/personal-information-leakage-detection-in","slug":"personal-information-leakage-detection-in","title":"Personal Information Leakage Detection in Conversations","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semantic-labeling-using-a-deep-contextualized","slug":"semantic-labeling-using-a-deep-contextualized","title":"Semantic Labeling Using a Deep Contextualized Language Model","date":"2020-10-30","arxiv_id":"2010.16037","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-training-of-transformer-based","slug":"accelerating-training-of-transformer-based","title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping","date":"2020-10-26","arxiv_id":"2010.13369","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-spoken-language-understanding","slug":"semi-supervised-spoken-language-understanding","title":"Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining","date":"2020-10-26","arxiv_id":"2010.13826","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-legal-text-classification-using","slug":"large-scale-legal-text-classification-using","title":"Large Scale Legal Text Classification Using Transformer Models","date":"2020-10-24","arxiv_id":"2010.12871","repositories_listed":1,"syntology":null},{"url":"/paper/when-being-unseen-from-mbert-is-just-the","slug":"when-being-unseen-from-mbert-is-just-the","title":"When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models","date":"2020-10-24","arxiv_id":"2010.12858","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-contextualized-word-embeddings","slug":"dynamic-contextualized-word-embeddings","title":"Dynamic Contextualized Word Embeddings","date":"2020-10-23","arxiv_id":"2010.12684","repositories_listed":1,"syntology":null},{"url":"/paper/hatebert-retraining-bert-for-abusive-language","slug":"hatebert-retraining-bert-for-abusive-language","title":"HateBERT: Retraining BERT for Abusive Language Detection in English","date":"2020-10-23","arxiv_id":"2010.12472","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-knowledge-graph-based-synthetic","slug":"large-scale-knowledge-graph-based-synthetic","title":"Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training","date":"2020-10-23","arxiv_id":"2010.12688","repositories_listed":1,"syntology":null},{"url":"/paper/calibrated-language-model-fine-tuning-for-in","slug":"calibrated-language-model-fine-tuning-for-in","title":"Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data","date":"2020-10-22","arxiv_id":"2010.11506","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-estimation-for-attention-based","slug":"confidence-estimation-for-attention-based","title":"Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition","date":"2020-10-22","arxiv_id":"2010.11428","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-distillation-for-bert-unsupervised","slug":"knowledge-distillation-for-bert-unsupervised","title":"Knowledge Distillation for BERT Unsupervised Domain Adaptation","date":"2020-10-22","arxiv_id":"2010.11478","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-the-source-and-target-contributions","slug":"analyzing-the-source-and-target-contributions","title":"Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.10907","repositories_listed":1,"syntology":null},{"url":"/paper/german-s-next-language-model","slug":"german-s-next-language-model","title":"German's Next Language Model","date":"2020-10-21","arxiv_id":"2010.10906","repositories_listed":1,"syntology":null},{"url":"/paper/turngpt-a-transformer-based-language-model","slug":"turngpt-a-transformer-based-language-model","title":"TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog","date":"2020-10-21","arxiv_id":"2010.10874","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/turngpt-a-transformer-based-language-model#ran","syntology_url":"https://syntology.ai/paper/2010.10874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10874"}},"official":{"repos":["ErikEkstedt/TurnGPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-language-modeling-for-contextualized","slug":"neural-language-modeling-for-contextualized","title":"Neural Language Modeling for Contextualized Temporal Graph Generation","date":"2020-10-20","arxiv_id":"2010.10077","repositories_listed":1,"syntology":null},{"url":"/paper/prop-pre-training-with-representative-words","slug":"prop-pre-training-with-representative-words","title":"PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval","date":"2020-10-20","arxiv_id":"2010.10137","repositories_listed":1,"syntology":null},{"url":"/paper/cold-start-active-learning-through-self","slug":"cold-start-active-learning-through-self","title":"Cold-start Active Learning through Self-supervised Language Modeling","date":"2020-10-19","arxiv_id":"2010.09535","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cold-start-active-learning-through-self#ran","syntology_url":"https://syntology.ai/paper/2010.09535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09535"}},"official":{"repos":["forest-snow/alps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-grounded-dialogue-generation-with","slug":"knowledge-grounded-dialogue-generation-with","title":"Knowledge-Grounded Dialogue Generation with Pre-trained Language Models","date":"2020-10-17","arxiv_id":"2010.08824","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/knowledge-grounded-dialogue-generation-with#ran","syntology_url":"https://syntology.ai/paper/2010.08824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08824"}},"official":{"repos":["zhaoxlpku/KnowledGPT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/substance-over-style-document-level-targeted","slug":"substance-over-style-document-level-targeted","title":"Substance over Style: Document-Level Targeted Content Transfer","date":"2020-10-16","arxiv_id":"2010.08618","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/substance-over-style-document-level-targeted#ran","syntology_url":"https://syntology.ai/paper/2010.08618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08618"}},"official":{"repos":["microsoft/document-level-targeted-content-transfer"],"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/cxp949-at-wnut-2020-task-2-extracting","slug":"cxp949-at-wnut-2020-task-2-extracting","title":"CXP949 at WNUT-2020 Task 2: Extracting Informative COVID-19 Tweets -- RoBERTa Ensembles and The Continued Relevance of Handcrafted Features","date":"2020-10-15","arxiv_id":"2010.07988","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-pre-trained-language-model-with","slug":"fine-tuning-pre-trained-language-model-with","title":"Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach","date":"2020-10-15","arxiv_id":"2010.07835","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fine-tuning-pre-trained-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2010.07835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07835"}},"official":{"repos":["yueyu1030/COSINE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/natural-language-rationales-with-full-stack","slug":"natural-language-rationales-with-full-stack","title":"Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs","date":"2020-10-15","arxiv_id":"2010.07526","repositories_listed":1,"syntology":null},{"url":"/paper/pretrained-language-models-for-dialogue","slug":"pretrained-language-models-for-dialogue","title":"Pretrained Language Models for Dialogue Generation with Multiple Input Sources","date":"2020-10-15","arxiv_id":"2010.07576","repositories_listed":1,"syntology":null},{"url":"/paper/chinese-lexical-simplification","slug":"chinese-lexical-simplification","title":"Chinese Lexical Simplification","date":"2020-10-14","arxiv_id":"2010.07048","repositories_listed":1,"syntology":null},{"url":"/paper/vokenization-improving-language-understanding","slug":"vokenization-improving-language-understanding","title":"Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision","date":"2020-10-14","arxiv_id":"2010.06775","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vokenization-improving-language-understanding#ran","syntology_url":"https://syntology.ai/paper/2010.06775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06775"}},"official":{"repos":["airsplay/vokenization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/are-some-words-worth-more-than-others","slug":"are-some-words-worth-more-than-others","title":"Are Some Words Worth More than Others?","date":"2020-10-12","arxiv_id":"2010.06069","repositories_listed":1,"syntology":null},{"url":"/paper/biomegatron-larger-biomedical-domain-language","slug":"biomegatron-larger-biomedical-domain-language","title":"BioMegatron: Larger Biomedical Domain Language Model","date":"2020-10-12","arxiv_id":"2010.06060","repositories_listed":1,"syntology":null},{"url":"/paper/meta-context-transformers-for-domain-specific","slug":"meta-context-transformers-for-domain-specific","title":"Meta-Context Transformers for Domain-Specific Response Generation","date":"2020-10-12","arxiv_id":"2010.05572","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-complementary-nature-of-knowledge","slug":"on-the-complementary-nature-of-knowledge","title":"On the Complementary Nature of Knowledge Graph Embedding, Fine Grain Entity Types, and Language Modeling","date":"2020-10-12","arxiv_id":"2010.05732","repositories_listed":1,"syntology":null},{"url":"/paper/incremental-processing-in-the-age-of-non","slug":"incremental-processing-in-the-age-of-non","title":"Incremental Processing in the Age of Non-Incremental Encoders: An Empirical Assessment of Bidirectional Models for Incremental NLU","date":"2020-10-11","arxiv_id":"2010.05330","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-language-learning-commonsense-from","slug":"beyond-language-learning-commonsense-from","title":"Beyond Language: Learning Commonsense from Images for Reasoning","date":"2020-10-10","arxiv_id":"2010.05001","repositories_listed":1,"syntology":null},{"url":"/paper/discourse-structure-interacts-with-reference","slug":"discourse-structure-interacts-with-reference","title":"Discourse structure interacts with reference but not syntax in neural language models","date":"2020-10-10","arxiv_id":"2010.04887","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-formality-style-transfer","slug":"semi-supervised-formality-style-transfer","title":"Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization","date":"2020-10-10","arxiv_id":"2010.05090","repositories_listed":1,"syntology":null},{"url":"/paper/toward-micro-dialect-identification-in","slug":"toward-micro-dialect-identification-in","title":"Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments","date":"2020-10-10","arxiv_id":"2010.04900","repositories_listed":1,"syntology":null},{"url":"/paper/what-do-position-embeddings-learn-an","slug":"what-do-position-embeddings-learn-an","title":"What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding","date":"2020-10-10","arxiv_id":"2010.04903","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-do-position-embeddings-learn-an#ran","syntology_url":"https://syntology.ai/paper/2010.04903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04903"}},"official":{"repos":["MiuLab/PE-Study"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/online-back-parsing-for-amr-to-text","slug":"online-back-parsing-for-amr-to-text","title":"Online Back-Parsing for AMR-to-Text Generation","date":"2020-10-09","arxiv_id":"2010.04520","repositories_listed":1,"syntology":null},{"url":"/paper/plug-and-play-conversational-models","slug":"plug-and-play-conversational-models","title":"Plug-and-Play Conversational Models","date":"2020-10-09","arxiv_id":"2010.04344","repositories_listed":1,"syntology":null},{"url":"/paper/q-learning-with-language-model-for-edit-based","slug":"q-learning-with-language-model-for-edit-based","title":"Q-learning with Language Model for Edit-based Unsupervised Summarization","date":"2020-10-09","arxiv_id":"2010.04379","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/q-learning-with-language-model-for-edit-based#ran","syntology_url":"https://syntology.ai/paper/2010.04379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04379"}},"official":{"repos":["kohilin/ealm"],"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/precise-task-formalization-matters-in","slug":"precise-task-formalization-matters-in","title":"Precise Task Formalization Matters in Winograd Schema Evaluations","date":"2020-10-08","arxiv_id":"2010.04043","repositories_listed":1,"syntology":null},{"url":"/paper/cross-thought-for-sentence-encoder-pre","slug":"cross-thought-for-sentence-encoder-pre","title":"Cross-Thought for Sentence Encoder Pre-training","date":"2020-10-07","arxiv_id":"2010.03652","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-demographic-word-embeddings","slug":"compositional-demographic-word-embeddings","title":"Compositional Demographic Word Embeddings","date":"2020-10-06","arxiv_id":"2010.02986","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/compositional-demographic-word-embeddings#ran","syntology_url":"https://syntology.ai/paper/2010.02986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02986"}},"official":{"repos":["dbamman/geoSGLM"],"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/guiding-attention-for-self-supervised","slug":"guiding-attention-for-self-supervised","title":"Guiding Attention for Self-Supervised Learning with Transformers","date":"2020-10-06","arxiv_id":"2010.02399","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":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/guiding-attention-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2010.02399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02399"}},"official":{"repos":["ameet-1997/AttentionGuidance"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/keep-calm-and-explore-language-models-for","slug":"keep-calm-and-explore-language-models-for","title":"Keep CALM and Explore: Language Models for Action Generation in Text-based Games","date":"2020-10-06","arxiv_id":"2010.02903","repositories_listed":1,"syntology":null},{"url":"/paper/neural-mask-generator-learning-to-generate","slug":"neural-mask-generator-learning-to-generate","title":"Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation","date":"2020-10-06","arxiv_id":"2010.02705","repositories_listed":1,"syntology":null},{"url":"/paper/pretrained-language-model-embryology-the","slug":"pretrained-language-model-embryology-the","title":"Pretrained Language Model Embryology: The Birth of ALBERT","date":"2020-10-06","arxiv_id":"2010.02480","repositories_listed":1,"syntology":null},{"url":"/paper/a-pilot-study-of-text-to-sql-semantic-parsing","slug":"a-pilot-study-of-text-to-sql-semantic-parsing","title":"A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamese","date":"2020-10-05","arxiv_id":"2010.01891","repositories_listed":1,"syntology":null},{"url":"/paper/when-in-doubt-ask-generating-answerable-and","slug":"when-in-doubt-ask-generating-answerable-and","title":"When in Doubt, Ask: Generating Answerable and Unanswerable Questions, Unsupervised","date":"2020-10-04","arxiv_id":"2010.01611","repositories_listed":1,"syntology":null},{"url":"/paper/xda-accurate-robust-disassembly-with-transfer","slug":"xda-accurate-robust-disassembly-with-transfer","title":"XDA: Accurate, Robust Disassembly with Transfer Learning","date":"2020-10-02","arxiv_id":"2010.00770","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/xda-accurate-robust-disassembly-with-transfer#ran","syntology_url":"https://syntology.ai/paper/2010.00770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.00770"}},"official":{"repos":["CUMLSec/XDA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-investigation-towards-efficient","slug":"an-empirical-investigation-towards-efficient","title":"An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training","date":"2020-10-01","arxiv_id":"2010.00784","repositories_listed":1,"syntology":null},{"url":"/paper/improving-vietnamese-named-entity-recognition","slug":"improving-vietnamese-named-entity-recognition","title":"Improving Vietnamese Named Entity Recognition from Speech Using Word Capitalization and Punctuation Recovery Models","date":"2020-10-01","arxiv_id":"2010.00198","repositories_listed":1,"syntology":null},{"url":"/paper/near-imperceptible-neural-linguistic","slug":"near-imperceptible-neural-linguistic","title":"Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding","date":"2020-10-01","arxiv_id":"2010.00677","repositories_listed":1,"syntology":null}],"record_sha256":"b2c591ab713bc065ff7bb179e9c7d75cb3e5edbc263eb8135340db385429e9dd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}