{"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/62","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":62,"pages_in_order":177,"rows_per_page":100,"rows":[6101,6200],"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/61","next":"/task/language-modelling/papers/63","papers":[{"url":"/paper/counterfactual-data-augmentation-for-neural","slug":"counterfactual-data-augmentation-for-neural","title":"Counterfactual Data Augmentation for Neural Machine Translation","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-oriented-pre-training","slug":"dialogue-oriented-pre-training","title":"Dialogue-oriented Pre-training","date":"2021-06-01","arxiv_id":"2106.00420","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"6 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dialogue-oriented-pre-training#ran","syntology_url":"https://syntology.ai/paper/2106.00420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00420"}},"official":{"repos":["xyease/Dialog-PrLM"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/emotion-infused-models-for-explainable","slug":"emotion-infused-models-for-explainable","title":"Emotion-Infused Models for Explainable Psychological Stress Detection","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-visual-layout-structures-for","slug":"incorporating-visual-layout-structures-for","title":"VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups","date":"2021-06-01","arxiv_id":"2106.00676","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/incorporating-visual-layout-structures-for#ran","syntology_url":"https://syntology.ai/paper/2106.00676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00676"}},"official":{"repos":["allenai/VILA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-variation-in-written-forms-of","slug":"investigating-variation-in-written-forms-of","title":"Investigating variation in written forms of Nahuatl using character-based language models","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/target-specified-sequence-labeling-with-multi","slug":"target-specified-sequence-labeling-with-multi","title":"Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/team-ohio-state-at-cmcl-2021-shared-task-fine","slug":"team-ohio-state-at-cmcl-2021-shared-task-fine","title":"Team Ohio State at CMCL 2021 Shared Task: Fine-Tuned RoBERTa for Eye-Tracking Data Prediction","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/that-looks-hard-characterizing-linguistic","slug":"that-looks-hard-characterizing-linguistic","title":"That Looks Hard: Characterizing Linguistic Complexity in Humans and Language Models","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cascaded-head-colliding-attention","slug":"cascaded-head-colliding-attention","title":"Cascaded Head-colliding Attention","date":"2021-05-31","arxiv_id":"2105.14850","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":4,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":5,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cascaded-head-colliding-attention#ran","syntology_url":"https://syntology.ai/paper/2105.14850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14850"}},"official":{"repos":["LZhengisme/CODA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official","unlocated"]}}},{"url":"/paper/connecting-language-and-vision-for-natural","slug":"connecting-language-and-vision-for-natural","title":"Connecting Language and Vision for Natural Language-Based Vehicle Retrieval","date":"2021-05-31","arxiv_id":"2105.14897","repositories_listed":1,"syntology":null},{"url":"/paper/effect-of-large-scale-pre-training-on-full","slug":"effect-of-large-scale-pre-training-on-full","title":"Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images","date":"2021-05-31","arxiv_id":"2106.00116","repositories_listed":1,"syntology":null},{"url":"/paper/effective-batching-for-recurrent-neural","slug":"effective-batching-for-recurrent-neural","title":"Effective Batching for Recurrent Neural Network Grammars","date":"2021-05-31","arxiv_id":"2105.14822","repositories_listed":1,"syntology":null},{"url":"/paper/verdi-quality-estimation-and-error-detection","slug":"verdi-quality-estimation-and-error-detection","title":"Verdi: Quality Estimation and Error Detection for Bilingual Corpora","date":"2021-05-31","arxiv_id":"2105.14878","repositories_listed":1,"syntology":null},{"url":"/paper/commitbert-commit-message-generation-using","slug":"commitbert-commit-message-generation-using","title":"CommitBERT: Commit Message Generation Using Pre-Trained Programming Language Model","date":"2021-05-29","arxiv_id":"2105.14242","repositories_listed":1,"syntology":null},{"url":"/paper/neurallog-natural-language-inference-with","slug":"neurallog-natural-language-inference-with","title":"NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning","date":"2021-05-29","arxiv_id":"2105.14167","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/neurallog-natural-language-inference-with#ran","syntology_url":"https://syntology.ai/paper/2105.14167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14167"}},"official":{"repos":["eric11eca/NeuralLog"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sentiment-analysis-in-tweets-an-assessment","slug":"sentiment-analysis-in-tweets-an-assessment","title":"Sentiment analysis in tweets: an assessment study from classical to modern text representation models","date":"2021-05-29","arxiv_id":"2105.14373","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-cross-lingual-sentence","slug":"lightweight-cross-lingual-sentence","title":"Lightweight Cross-Lingual Sentence Representation Learning","date":"2021-05-28","arxiv_id":"2105.13856","repositories_listed":1,"syntology":null},{"url":"/paper/generative-text-modeling-through-short-run","slug":"generative-text-modeling-through-short-run","title":"Generative Text Modeling through Short Run Inference","date":"2021-05-27","arxiv_id":"2106.02513","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generative-text-modeling-through-short-run#ran","syntology_url":"https://syntology.ai/paper/2106.02513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02513"}},"official":{"repos":["bpucla/sri_text"],"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","unlocated"]}}},{"url":"/paper/protaugment-unsupervised-diverse-short-texts","slug":"protaugment-unsupervised-diverse-short-texts","title":"ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning","date":"2021-05-27","arxiv_id":"2105.12995","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/protaugment-unsupervised-diverse-short-texts#ran","syntology_url":"https://syntology.ai/paper/2105.12995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12995"}},"official":{"repos":["tdopierre/ProtAugment"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-enhanced-masked-language-model-for","slug":"knowledge-enhanced-masked-language-model-for","title":"Knowledge Enhanced Masked Language Model for Stance Detection","date":"2021-05-26","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/language-model-as-an-annotator-exploring","slug":"language-model-as-an-annotator-exploring","title":"Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization","date":"2021-05-26","arxiv_id":"2105.12544","repositories_listed":1,"syntology":null},{"url":"/paper/treebert-a-tree-based-pre-trained-model-for","slug":"treebert-a-tree-based-pre-trained-model-for","title":"TreeBERT: A Tree-Based Pre-Trained Model for Programming Language","date":"2021-05-26","arxiv_id":"2105.12485","repositories_listed":1,"syntology":null},{"url":"/paper/empirical-error-modeling-improves-robustness","slug":"empirical-error-modeling-improves-robustness","title":"Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling","date":"2021-05-25","arxiv_id":"2105.11872","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-transformer-for-explainable","slug":"personalized-transformer-for-explainable","title":"Personalized Transformer for Explainable Recommendation","date":"2021-05-25","arxiv_id":"2105.11601","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":8,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/personalized-transformer-for-explainable#ran","syntology_url":"https://syntology.ai/paper/2105.11601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11601"}},"official":{"repos":["lileipisces/PETER"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/few-shot-upsampling-for-protest-size","slug":"few-shot-upsampling-for-protest-size","title":"Few-Shot Upsampling for Protest Size Detection","date":"2021-05-24","arxiv_id":"2105.11260","repositories_listed":1,"syntology":null},{"url":"/paper/prevent-the-language-model-from-being","slug":"prevent-the-language-model-from-being","title":"Prevent the Language Model from being Overconfident in Neural Machine Translation","date":"2021-05-24","arxiv_id":"2105.11098","repositories_listed":1,"syntology":null},{"url":"/paper/citeworth-cite-worthiness-detection-for","slug":"citeworth-cite-worthiness-detection-for","title":"CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding","date":"2021-05-23","arxiv_id":"2105.10912","repositories_listed":1,"syntology":null},{"url":"/paper/gappredict-a-language-model-for-resolving","slug":"gappredict-a-language-model-for-resolving","title":"GapPredict: A Language Model for Resolving Gaps in Draft Genome Assemblies","date":"2021-05-21","arxiv_id":"2105.10552","repositories_listed":1,"syntology":null},{"url":"/paper/scatterbrain-unifying-sparse-and-low-rank-1","slug":"scatterbrain-unifying-sparse-and-low-rank-1","title":"Scatterbrain: Unifying Sparse and Low-rank Attention","date":"2021-05-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vlm-task-agnostic-video-language-model-pre","slug":"vlm-task-agnostic-video-language-model-pre","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","date":"2021-05-20","arxiv_id":"2105.09996","repositories_listed":1,"syntology":null},{"url":"/paper/effective-attention-sheds-light-on","slug":"effective-attention-sheds-light-on","title":"Effective Attention Sheds Light On Interpretability","date":"2021-05-18","arxiv_id":"2105.08855","repositories_listed":1,"syntology":null},{"url":"/paper/stage-wise-fine-tuning-for-graph-to-text","slug":"stage-wise-fine-tuning-for-graph-to-text","title":"Stage-wise Fine-tuning for Graph-to-Text Generation","date":"2021-05-17","arxiv_id":"2105.08021","repositories_listed":1,"syntology":null},{"url":"/paper/doc2dict-information-extraction-as-text","slug":"doc2dict-information-extraction-as-text","title":"Doc2Dict: Information Extraction as Text Generation","date":"2021-05-16","arxiv_id":"2105.07510","repositories_listed":1,"syntology":null},{"url":"/paper/joint-retrieval-and-generation-training-for","slug":"joint-retrieval-and-generation-training-for","title":"RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling","date":"2021-05-14","arxiv_id":"2105.06597","repositories_listed":1,"syntology":null},{"url":"/paper/not-all-memories-are-created-equal-learning-1","slug":"not-all-memories-are-created-equal-learning-1","title":"Not All Memories are Created Equal: Learning to Forget by Expiring","date":"2021-05-13","arxiv_id":"2105.06548","repositories_listed":1,"syntology":null},{"url":"/paper/mate-kd-masked-adversarial-text-a-companion","slug":"mate-kd-masked-adversarial-text-a-companion","title":"MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation","date":"2021-05-12","arxiv_id":"2105.05912","repositories_listed":1,"syntology":null},{"url":"/paper/bert-is-to-nlp-what-alexnet-is-to-cv-can-pre","slug":"bert-is-to-nlp-what-alexnet-is-to-cv-can-pre","title":"BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?","date":"2021-05-11","arxiv_id":"2105.04949","repositories_listed":1,"syntology":null},{"url":"/paper/matching-visual-features-to-hierarchical","slug":"matching-visual-features-to-hierarchical","title":"Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning","date":"2021-05-10","arxiv_id":"2105.04143","repositories_listed":1,"syntology":null},{"url":"/paper/dispatcher-a-message-passing-approach-to","slug":"dispatcher-a-message-passing-approach-to","title":"Dispatcher: A Message-Passing Approach To Language Modelling","date":"2021-05-09","arxiv_id":"2105.03994","repositories_listed":1,"syntology":null},{"url":"/paper/docscan-unsupervised-text-classification-via","slug":"docscan-unsupervised-text-classification-via","title":"DocSCAN: Unsupervised Text Classification via Learning from Neighbors","date":"2021-05-09","arxiv_id":"2105.04024","repositories_listed":1,"syntology":null},{"url":"/paper/lawformer-a-pre-trained-language-model-for","slug":"lawformer-a-pre-trained-language-model-for","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","date":"2021-05-09","arxiv_id":"2105.03887","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-transformers-with-gradient-boosted","slug":"enhancing-transformers-with-gradient-boosted","title":"Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning","date":"2021-05-08","arxiv_id":"2105.03791","repositories_listed":1,"syntology":null},{"url":"/paper/is-incoherence-surprising-targeted-evaluation","slug":"is-incoherence-surprising-targeted-evaluation","title":"Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models","date":"2021-05-07","arxiv_id":"2105.03495","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-fly-controlled-text-generation-with","slug":"on-the-fly-controlled-text-generation-with","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","date":"2021-05-07","arxiv_id":"2105.03023","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/on-the-fly-controlled-text-generation-with#ran","syntology_url":"https://syntology.ai/paper/2105.03023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03023"}},"official":{"repos":["alisawuffles/DExperts"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-by-understanding-not-modeling","slug":"understanding-by-understanding-not-modeling","title":"Understanding by Understanding Not: Modeling Negation in Language Models","date":"2021-05-07","arxiv_id":"2105.03519","repositories_listed":1,"syntology":null},{"url":"/paper/graphformers-gnn-nested-language-models-for","slug":"graphformers-gnn-nested-language-models-for","title":"GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph","date":"2021-05-06","arxiv_id":"2105.02605","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/graphformers-gnn-nested-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2105.02605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02605"}},"official":{"repos":["microsoft/graphformers"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/inferring-the-reader-guiding-automated-story","slug":"inferring-the-reader-guiding-automated-story","title":"Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning","date":"2021-05-04","arxiv_id":"2105.01311","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-document-expansion-for","slug":"unsupervised-document-expansion-for","title":"Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation","date":"2021-05-03","arxiv_id":"2105.00666","repositories_listed":1,"syntology":null},{"url":"/paper/error-analysis-of-using-bart-for-multi","slug":"error-analysis-of-using-bart-for-multi","title":"Error Analysis of using BART for Multi-Document Summarization: A Study for English and German Language","date":"2021-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hidden-backdoors-in-human-centric-language","slug":"hidden-backdoors-in-human-centric-language","title":"Hidden Backdoors in Human-Centric Language Models","date":"2021-05-01","arxiv_id":"2105.00164","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":3,"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/hidden-backdoors-in-human-centric-language#ran","syntology_url":"https://syntology.ai/paper/2105.00164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.00164"}},"official":{"repos":["lishaofeng/NLP_Backdoor"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/when-to-fold-em-how-to-answer-unanswerable","slug":"when-to-fold-em-how-to-answer-unanswerable","title":"When to Fold'em: How to answer Unanswerable questions","date":"2021-05-01","arxiv_id":"2105.00328","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-groundedness-in-dialogue-systems","slug":"evaluating-groundedness-in-dialogue-systems","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","date":"2021-04-30","arxiv_id":"2105.00071","repositories_listed":1,"syntology":null},{"url":"/paper/phrase-break-prediction-with-bidirectional","slug":"phrase-break-prediction-with-bidirectional","title":"Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis","date":"2021-04-26","arxiv_id":"2104.12395","repositories_listed":1,"syntology":null},{"url":"/paper/xlm-t-a-multilingual-language-model-toolkit","slug":"xlm-t-a-multilingual-language-model-toolkit","title":"XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond","date":"2021-04-25","arxiv_id":"2104.12250","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/xlm-t-a-multilingual-language-model-toolkit#ran","syntology_url":"https://syntology.ai/paper/2104.12250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12250"}},"official":{"repos":["cardiffnlp/xlm-t"],"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/learning-passage-impacts-for-inverted-indexes","slug":"learning-passage-impacts-for-inverted-indexes","title":"Learning Passage Impacts for Inverted Indexes","date":"2021-04-24","arxiv_id":"2104.12016","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/learning-passage-impacts-for-inverted-indexes#ran","syntology_url":"https://syntology.ai/paper/2104.12016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12016"}},"official":{"repos":["DI4IR/SIGIR2021"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-biomedical-pretrained-language","slug":"improving-biomedical-pretrained-language","title":"Improving Biomedical Pretrained Language Models with Knowledge","date":"2021-04-21","arxiv_id":"2104.10344","repositories_listed":1,"syntology":null},{"url":"/paper/should-we-stop-training-more-monolingual","slug":"should-we-stop-training-more-monolingual","title":"Should we Stop Training More Monolingual Models, and Simply Use Machine Translation Instead?","date":"2021-04-21","arxiv_id":"2104.10441","repositories_listed":1,"syntology":null},{"url":"/paper/b-prop-bootstrapped-pre-training-with","slug":"b-prop-bootstrapped-pre-training-with","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","date":"2021-04-20","arxiv_id":"2104.09791","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/b-prop-bootstrapped-pre-training-with#ran","syntology_url":"https://syntology.ai/paper/2104.09791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09791"}},"official":{"repos":["Albert-Ma/PROP"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/differentiable-model-compression-via-pseudo","slug":"differentiable-model-compression-via-pseudo","title":"Differentiable Model Compression via Pseudo Quantization Noise","date":"2021-04-20","arxiv_id":"2104.09987","repositories_listed":1,"syntology":null},{"url":"/paper/frustratingly-easy-edit-based-linguistic","slug":"frustratingly-easy-edit-based-linguistic","title":"Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model","date":"2021-04-20","arxiv_id":"2104.09833","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/frustratingly-easy-edit-based-linguistic#ran","syntology_url":"https://syntology.ai/paper/2104.09833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09833"}},"official":{"repos":["ku-nlp/steganography-with-masked-lm"],"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/when-fasttext-pays-attention-efficient","slug":"when-fasttext-pays-attention-efficient","title":"When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting","date":"2021-04-19","arxiv_id":"2104.09691","repositories_listed":1,"syntology":null},{"url":"/paper/fednlp-a-research-platform-for-federated","slug":"fednlp-a-research-platform-for-federated","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","date":"2021-04-18","arxiv_id":"2104.08815","repositories_listed":1,"syntology":null},{"url":"/paper/go-forth-and-prosper-language-modeling-with","slug":"go-forth-and-prosper-language-modeling-with","title":"Go Forth and Prosper: Language Modeling with Ancient Textual History","date":"2021-04-18","arxiv_id":"2104.08742","repositories_listed":1,"syntology":null},{"url":"/paper/lifelong-learning-of-few-shot-learners-across","slug":"lifelong-learning-of-few-shot-learners-across","title":"Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning","date":"2021-04-18","arxiv_id":"2104.08808","repositories_listed":1,"syntology":null},{"url":"/paper/simmc-2-0-a-task-oriented-dialog-dataset-for","slug":"simmc-2-0-a-task-oriented-dialog-dataset-for","title":"SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations","date":"2021-04-18","arxiv_id":"2104.08667","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-answers-with-entailment-trees","slug":"explaining-answers-with-entailment-trees","title":"Explaining Answers with Entailment Trees","date":"2021-04-17","arxiv_id":"2104.08661","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":1,"phrase":"16 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/explaining-answers-with-entailment-trees#ran","syntology_url":"https://syntology.ai/paper/2104.08661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08661"}},"official":null}},{"url":"/paper/a-masked-segmental-language-model-for","slug":"a-masked-segmental-language-model-for","title":"A Masked Segmental Language Model for Unsupervised Natural Language Segmentation","date":"2021-04-16","arxiv_id":"2104.07829","repositories_listed":1,"syntology":null},{"url":"/paper/effect-of-vision-and-language-extensions-on","slug":"effect-of-vision-and-language-extensions-on","title":"Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models","date":"2021-04-16","arxiv_id":"2104.08066","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/effect-of-vision-and-language-extensions-on#ran","syntology_url":"https://syntology.ai/paper/2104.08066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08066"}},"official":{"repos":["alab-nii/eval_vl_glue"],"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/is-your-language-model-ready-for-dense","slug":"is-your-language-model-ready-for-dense","title":"Condenser: a Pre-training Architecture for Dense Retrieval","date":"2021-04-16","arxiv_id":"2104.08253","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"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 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) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/is-your-language-model-ready-for-dense#ran","syntology_url":"https://syntology.ai/paper/2104.08253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08253"}},"official":{"repos":["luyug/Condenser"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/probing-across-time-what-does-roberta-know","slug":"probing-across-time-what-does-roberta-know","title":"Probing Across Time: What Does RoBERTa Know and When?","date":"2021-04-16","arxiv_id":"2104.07885","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/probing-across-time-what-does-roberta-know#ran","syntology_url":"https://syntology.ai/paper/2104.07885","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07885"}},"official":{"repos":["leo-liuzy/probe-across-time"],"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/adaprompt-adaptive-prompt-based-finetuning","slug":"adaprompt-adaptive-prompt-based-finetuning","title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","date":"2021-04-15","arxiv_id":"2104.07650","repositories_listed":1,"syntology":null},{"url":"/paper/bilingual-alignment-transfers-to-multilingual","slug":"bilingual-alignment-transfers-to-multilingual","title":"Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining","date":"2021-04-15","arxiv_id":"2104.07642","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-polarized-topics-in-covid-19-news","slug":"detecting-polarized-topics-in-covid-19-news","title":"Detecting Polarized Topics Using Partisanship-aware Contextualized Topic Embeddings","date":"2021-04-15","arxiv_id":"2104.07814","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-gender-bias-towards-politicians","slug":"quantifying-gender-bias-towards-politicians","title":"Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models","date":"2021-04-15","arxiv_id":"2104.07505","repositories_listed":1,"syntology":null},{"url":"/paper/time-stamped-language-model-teaching-language","slug":"time-stamped-language-model-teaching-language","title":"Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events","date":"2021-04-15","arxiv_id":"2104.07635","repositories_listed":1,"syntology":null},{"url":"/paper/event-detection-as-question-answering-with","slug":"event-detection-as-question-answering-with","title":"Event Detection as Question Answering with Entity Information","date":"2021-04-14","arxiv_id":"2104.06969","repositories_listed":1,"syntology":null},{"url":"/paper/iga-an-intent-guided-authoring-assistant","slug":"iga-an-intent-guided-authoring-assistant","title":"IGA : An Intent-Guided Authoring Assistant","date":"2021-04-14","arxiv_id":"2104.07000","repositories_listed":1,"syntology":null},{"url":"/paper/k-plug-knowledge-injected-pre-trained-1","slug":"k-plug-knowledge-injected-pre-trained-1","title":"K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce","date":"2021-04-14","arxiv_id":"2104.06960","repositories_listed":1,"syntology":null},{"url":"/paper/udalm-unsupervised-domain-adaptation-through","slug":"udalm-unsupervised-domain-adaptation-through","title":"UDALM: Unsupervised Domain Adaptation through Language Modeling","date":"2021-04-14","arxiv_id":"2104.07078","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/udalm-unsupervised-domain-adaptation-through#ran","syntology_url":"https://syntology.ai/paper/2104.07078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07078"}},"official":{"repos":["ckarouzos/slp_daptmlm"],"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/eat-enhanced-asr-tts-for-self-supervised","slug":"eat-enhanced-asr-tts-for-self-supervised","title":"EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition","date":"2021-04-13","arxiv_id":"2104.07474","repositories_listed":1,"syntology":null},{"url":"/paper/building-a-swedish-open-domain-conversational","slug":"building-a-swedish-open-domain-conversational","title":"Building a Swedish Open-Domain Conversational Language Model","date":"2021-04-12","arxiv_id":"2104.05277","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-inductive-bias-of-masked-language","slug":"on-the-inductive-bias-of-masked-language","title":"On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies","date":"2021-04-12","arxiv_id":"2104.05694","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/on-the-inductive-bias-of-masked-language#ran","syntology_url":"https://syntology.ai/paper/2104.05694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05694"}},"official":{"repos":["tatsu-lab/mlm_inductive_bias"],"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/paragraph-level-simplification-of-medical","slug":"paragraph-level-simplification-of-medical","title":"Paragraph-level Simplification of Medical Texts","date":"2021-04-12","arxiv_id":"2104.05767","repositories_listed":1,"syntology":null},{"url":"/paper/meta-tuning-language-models-to-answer-prompts","slug":"meta-tuning-language-models-to-answer-prompts","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","date":"2021-04-10","arxiv_id":"2104.04670","repositories_listed":1,"syntology":null},{"url":"/paper/fill-in-the-blank-as-a-challenging-video","slug":"fill-in-the-blank-as-a-challenging-video","title":"FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework","date":"2021-04-09","arxiv_id":"2104.04182","repositories_listed":1,"syntology":null},{"url":"/paper/deep-indexed-active-learning-for-matching","slug":"deep-indexed-active-learning-for-matching","title":"Deep Indexed Active Learning for Matching Heterogeneous Entity Representations","date":"2021-04-08","arxiv_id":"2104.03986","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-simple-neural-probabilistic","slug":"revisiting-simple-neural-probabilistic","title":"Revisiting Simple Neural Probabilistic Language Models","date":"2021-04-08","arxiv_id":"2104.03474","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/revisiting-simple-neural-probabilistic#ran","syntology_url":"https://syntology.ai/paper/2104.03474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03474"}},"official":{"repos":["SimengSun/revisit-nplm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-evaluation-of-word-embedding","slug":"an-empirical-evaluation-of-word-embedding","title":"An Empirical Evaluation of Word Embedding Models for Subjectivity Analysis Tasks","date":"2021-04-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lt-lm-a-novel-non-autoregressive-language","slug":"lt-lm-a-novel-non-autoregressive-language","title":"LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring","date":"2021-04-06","arxiv_id":"2104.02526","repositories_listed":1,"syntology":null},{"url":"/paper/recam-iitk-at-semeval-2021-task-4-bert-and","slug":"recam-iitk-at-semeval-2021-task-4-bert-and","title":"ReCAM@IITK at SemEval-2021 Task 4: BERT and ALBERT based Ensemble for Abstract Word Prediction","date":"2021-04-04","arxiv_id":"2104.01563","repositories_listed":1,"syntology":null},{"url":"/paper/mmbert-multimodal-bert-pretraining-for","slug":"mmbert-multimodal-bert-pretraining-for","title":"MMBERT: Multimodal BERT Pretraining for Improved Medical VQA","date":"2021-04-03","arxiv_id":"2104.01394","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-fly-aligned-data-augmentation-for","slug":"on-the-fly-aligned-data-augmentation-for","title":"On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR","date":"2021-04-03","arxiv_id":"2104.01393","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-pre-trained-language-models-for","slug":"benchmarking-pre-trained-language-models-for","title":"Benchmarking Pre-trained Language Models for Multilingual NER: TraSpaS at the BSNLP2021 Shared Task","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/canonical-and-surface-morphological","slug":"canonical-and-surface-morphological","title":"Canonical and Surface Morphological Segmentation for Nguni Languages","date":"2021-04-01","arxiv_id":"2104.00767","repositories_listed":1,"syntology":null},{"url":"/paper/curie-an-iterative-querying-approach-for","slug":"curie-an-iterative-querying-approach-for","title":"CURIE: An Iterative Querying Approach for Reasoning About Situations","date":"2021-04-01","arxiv_id":"2104.00814","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-cloze-questions-for-few-shot-text-1","slug":"exploiting-cloze-questions-for-few-shot-text-1","title":"Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/low-resource-language-modelling-of-south","slug":"low-resource-language-modelling-of-south","title":"Low-Resource Language Modelling of South African Languages","date":"2021-04-01","arxiv_id":"2104.00772","repositories_listed":1,"syntology":null},{"url":"/paper/newsmtsc-a-dataset-for-multi-target-dependent","slug":"newsmtsc-a-dataset-for-multi-target-dependent","title":"NewsMTSC: A Dataset for (Multi-)Target-dependent Sentiment Classification in Political News Articles","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/punktuator-a-multilingual-punctuation","slug":"punktuator-a-multilingual-punctuation","title":"PunKtuator: A Multilingual Punctuation Restoration System for Spoken and Written Text","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-learning-through-contextual-data","slug":"few-shot-learning-through-contextual-data","title":"Few-shot learning through contextual data augmentation","date":"2021-03-31","arxiv_id":"2103.16911","repositories_listed":1,"syntology":null}],"record_sha256":"4a9fcc140789e8ac423b40a570890b485ef3e9fe61250da32a2d8add37f12b25","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}