{"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":"/method/sentencepiece/papers/8","list_of":"/method/sentencepiece","method":"SentencePiece","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":8,"pages_in_order":10,"rows_per_page":100,"rows":[701,800],"of":908,"counts":{"archive_papers_tagged":908,"with_a_code_link":438,"where_syntology_ran_a_sample":111,"not_listed_spam_title":0,"listed":908,"listed_where_code_ran":111,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":96,"every_run_a_failure_of_syntologys_instrument":15,"listed_with_a_run_with_no_instrument_failure":96,"listed_every_run_a_failure_of_syntologys_instrument":15,"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":"/method/sentencepiece","prev":"/method/sentencepiece/papers/7","next":"/method/sentencepiece/papers/9","papers":[{"paper":"/paper/automated-mining-of-leaderboards-for","slug":"automated-mining-of-leaderboards-for","title":"Automated Mining of Leaderboards for Empirical AI Research","date":"2021-08-31","arxiv_id":"2109.13089","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-robustness-of-neural-language","slug":"evaluating-the-robustness-of-neural-language","title":"Evaluating the Robustness of Neural Language Models to Input Perturbations","date":"2021-08-27","arxiv_id":"2108.12237","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["mmoradi-iut/nlp-perturbation"],"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"]}}},{"paper":"/paper/sentence-t5-scalable-sentence-encoders-from","slug":"sentence-t5-scalable-sentence-encoders-from","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","date":"2021-08-19","arxiv_id":"2108.08877","n_code_links":2,"syntology":null},{"paper":"/paper/table-caption-generation-in-scholarly","slug":"table-caption-generation-in-scholarly","title":"Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models","date":"2021-08-18","arxiv_id":"2108.08111","n_code_links":1,"syntology":null},{"paper":null,"slug":"enct5-fine-tuning-t5-encoder-for","title":"EncT5: Fine-tuning T5 Encoder for Discriminative Tasks","date":"2021-08-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/misleading-the-covid-19-vaccination-discourse","slug":"misleading-the-covid-19-vaccination-discourse","title":"Misleading the Covid-19 vaccination discourse on Twitter: An exploratory study of infodemic around the pandemic","date":"2021-08-16","arxiv_id":"2108.10735","n_code_links":1,"syntology":null},{"paper":null,"slug":"sapphire-approaches-for-enhanced-concept-to","title":"SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation","date":"2021-08-15","arxiv_id":"2108.06643","n_code_links":0,"syntology":null},{"paper":"/paper/how-optimal-is-greedy-decoding-for-extractive","slug":"how-optimal-is-greedy-decoding-for-extractive","title":"How Optimal is Greedy Decoding for Extractive Question Answering?","date":"2021-08-12","arxiv_id":"2108.05857","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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","official":{"repos":["ocastel/exact-extract"],"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"]}}},{"paper":"/paper/variable-length-music-score-infilling-via","slug":"variable-length-music-score-infilling-via","title":"Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding","date":"2021-08-11","arxiv_id":"2108.05064","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-user-behavior-retrieval-in-click","slug":"end-to-end-user-behavior-retrieval-in-click","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","date":"2021-08-10","arxiv_id":"2108.04468","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-listwise-evidence-reasoning-with-t5","title":"Exploring Listwise Evidence Reasoning with T5 for Fact Verification","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nmt5-is-parallel-data-still-relevant-for-pre-1","title":"nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/youngsheldon-at-semeval-2021-task-5-fine","slug":"youngsheldon-at-semeval-2021-task-5-fine","title":"YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/emailsum-abstractive-email-thread","slug":"emailsum-abstractive-email-thread","title":"EmailSum: Abstractive Email Thread Summarization","date":"2021-07-30","arxiv_id":"2107.14691","n_code_links":1,"syntology":null},{"paper":"/paper/reformer-the-relational-transformer-for-image","slug":"reformer-the-relational-transformer-for-image","title":"ReFormer: The Relational Transformer for Image Captioning","date":"2021-07-29","arxiv_id":"2107.14178","n_code_links":1,"syntology":null},{"paper":"/paper/clinical-relation-extraction-using","slug":"clinical-relation-extraction-using","title":"Clinical Relation Extraction Using Transformer-based Models","date":"2021-07-19","arxiv_id":"2107.08957","n_code_links":1,"syntology":null},{"paper":"/paper/turning-tables-generating-examples-from-semi","slug":"turning-tables-generating-examples-from-semi","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","date":"2021-07-15","arxiv_id":"2107.07261","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-with-multi-modal-features-and","slug":"transformers-with-multi-modal-features-and","title":"Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendation","date":"2021-07-11","arxiv_id":"2107.05124","n_code_links":0,"syntology":null},{"paper":"/paper/ernie-3-0-large-scale-knowledge-enhanced-pre","slug":"ernie-3-0-large-scale-knowledge-enhanced-pre","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","date":"2021-07-05","arxiv_id":"2107.02137","n_code_links":2,"syntology":null},{"paper":"/paper/what-helps-transformers-recognize","slug":"what-helps-transformers-recognize","title":"What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition","date":"2021-07-05","arxiv_id":"2107.02294","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-factual-consistency-of-abstractive-1","title":"Improving Factual Consistency of Abstractive Summarization on Customer Feedback","date":"2021-06-30","arxiv_id":"2106.16188","n_code_links":0,"syntology":null},{"paper":"/paper/xl-sum-large-scale-multilingual-abstractive","slug":"xl-sum-large-scale-multilingual-abstractive","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","date":"2021-06-25","arxiv_id":"2106.13822","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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","official":{"repos":["csebuetnlp/xl-sum"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"winner-team-mia-at-textvqa-challenge-2021","title":"Winner Team Mia at TextVQA Challenge 2021: Vision-and-Language Representation Learning with Pre-trained Sequence-to-Sequence Model","date":"2021-06-24","arxiv_id":"2106.15332","n_code_links":0,"syntology":null},{"paper":"/paper/cpm-2-large-scale-cost-effective-pre-trained","slug":"cpm-2-large-scale-cost-effective-pre-trained","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","date":"2021-06-20","arxiv_id":"2106.10715","n_code_links":2,"syntology":null},{"paper":"/paper/jointgt-graph-text-joint-representation","slug":"jointgt-graph-text-joint-representation","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","date":"2021-06-19","arxiv_id":"2106.10502","n_code_links":1,"syntology":null},{"paper":"/paper/incorporating-word-sense-disambiguation-in","slug":"incorporating-word-sense-disambiguation-in","title":"Incorporating Word Sense Disambiguation in Neural Language Models","date":"2021-06-15","arxiv_id":"2106.07967","n_code_links":2,"syntology":null},{"paper":"/paper/improving-paraphrase-detection-with-the","slug":"improving-paraphrase-detection-with-the","title":"Improving Paraphrase Detection with the Adversarial Paraphrasing Task","date":"2021-06-14","arxiv_id":"2106.07691","n_code_links":1,"syntology":null},{"paper":"/paper/memory-efficient-transformers-via-top-k","slug":"memory-efficient-transformers-via-top-k","title":"Memory-efficient Transformers via Top-$k$ Attention","date":"2021-06-13","arxiv_id":"2106.06899","n_code_links":2,"syntology":null},{"paper":null,"slug":"target-model-agnostic-adversarial-attacks","title":"Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models","date":"2021-06-13","arxiv_id":"2106.07047","n_code_links":0,"syntology":null},{"paper":"/paper/neural-combinatory-constituency-parsing","slug":"neural-combinatory-constituency-parsing","title":"Neural Combinatory Constituency Parsing","date":"2021-06-12","arxiv_id":"2106.06689","n_code_links":1,"syntology":null},{"paper":"/paper/fastseq-make-sequence-generation-faster","slug":"fastseq-make-sequence-generation-faster","title":"FastSeq: Make Sequence Generation Faster","date":"2021-06-08","arxiv_id":"2106.04718","n_code_links":1,"syntology":null},{"paper":"/paper/timedial-temporal-commonsense-reasoning-in","slug":"timedial-temporal-commonsense-reasoning-in","title":"TIMEDIAL: Temporal Commonsense Reasoning in Dialog","date":"2021-06-08","arxiv_id":"2106.04571","n_code_links":1,"syntology":null},{"paper":null,"slug":"nmt5-is-parallel-data-still-relevant-for-pre","title":"nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?","date":"2021-06-03","arxiv_id":"2106.02171","n_code_links":0,"syntology":null},{"paper":"/paper/evidence-based-factual-error-correction","slug":"evidence-based-factual-error-correction","title":"Evidence-based Factual Error Correction","date":"2021-06-02","arxiv_id":"2106.01072","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextualized-and-generalized-sentence","title":"Contextualized and Generalized Sentence Representations by Contrastive Self-Supervised Learning: A Case Study on Discourse Relation Analysis","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/implicit-representations-of-meaning-in-neural","slug":"implicit-representations-of-meaning-in-neural","title":"Implicit Representations of Meaning in Neural Language Models","date":"2021-06-01","arxiv_id":"2106.00737","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-grained-knowledge-distillation-for","title":"Multi-Grained Knowledge Distillation for Named Entity Recognition","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-comprehensive-understanding-and","title":"Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-transfer-learning-impacts-linguistic","title":"How transfer learning impacts linguistic knowledge in deep NLP models?","date":"2021-05-31","arxiv_id":"2105.15179","n_code_links":0,"syntology":null},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","slug":"byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","n_code_links":5,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["google-research/byt5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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","official":{"repos":["justinphan3110/SciFive"],"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"]}}},{"paper":null,"slug":"killing-two-birds-with-one-stone-stealing","title":"Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs","date":"2021-05-23","arxiv_id":"2105.10909","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-as-inference-via-fenchel-duality","title":"Attention as Inference via Fenchel Duality","date":"2021-05-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/explainable-tsetlin-machine-framework-for","slug":"explainable-tsetlin-machine-framework-for","title":"Explainable Tsetlin Machine framework for fake news detection with credibility score assessment","date":"2021-05-19","arxiv_id":"2105.09114","n_code_links":6,"syntology":null},{"paper":null,"slug":"exploring-text-to-text-transformers-for","title":"Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing","date":"2021-05-18","arxiv_id":"2105.08807","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-busters-outlier-layernorm-dimensions","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","date":"2021-05-14","arxiv_id":"2105.06990","n_code_links":0,"syntology":null},{"paper":null,"slug":"which-transformer-architecture-fits-my-data-a","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","date":"2021-05-09","arxiv_id":"2105.03928","n_code_links":0,"syntology":null},{"paper":"/paper/mt6-multilingual-pretrained-text-to-text","slug":"mt6-multilingual-pretrained-text-to-text","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","date":"2021-04-18","arxiv_id":"2104.08692","n_code_links":2,"syntology":null},{"paper":"/paper/the-power-of-scale-for-parameter-efficient","slug":"the-power-of-scale-for-parameter-efficient","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","date":"2021-04-18","arxiv_id":"2104.08691","n_code_links":12,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-research/prompt-tuning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/decrypting-cryptic-crosswords-semantically","slug":"decrypting-cryptic-crosswords-semantically","title":"Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP","date":"2021-04-17","arxiv_id":"2104.08620","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-survey-of-recent-abstract-summarization","title":"A Survey of Recent Abstract Summarization Techniques","date":"2021-04-15","arxiv_id":"2105.00824","n_code_links":0,"syntology":null},{"paper":"/paper/explagraphs-an-explanation-graph-generation","slug":"explagraphs-an-explanation-graph-generation","title":"ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning","date":"2021-04-15","arxiv_id":"2104.07644","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["swarnaHub/ExplaGraphs"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/nt5-training-t5-to-perform-numerical","slug":"nt5-training-t5-to-perform-numerical","title":"NT5?! Training T5 to Perform Numerical Reasoning","date":"2021-04-15","arxiv_id":"2104.07307","n_code_links":1,"syntology":null},{"paper":"/paper/nareor-the-narrative-reordering-problem","slug":"nareor-the-narrative-reordering-problem","title":"NAREOR: The Narrative Reordering Problem","date":"2021-04-14","arxiv_id":"2104.06669","n_code_links":1,"syntology":null},{"paper":null,"slug":"ki-bert-infusing-knowledge-context-for-better","title":"KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding","date":"2021-04-09","arxiv_id":"2104.08145","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-the-end-of-history-for-nlp","title":"Transformers: \"The End of History\" for NLP?","date":"2021-04-09","arxiv_id":"2105.00813","n_code_links":0,"syntology":null},{"paper":"/paper/codetrans-towards-cracking-the-language-of","slug":"codetrans-towards-cracking-the-language-of","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","date":"2021-04-06","arxiv_id":"2104.02443","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-transformers-in-emotion-recognition","title":"Exploring Transformers in Emotion Recognition: a comparison of BERT, DistillBERT, RoBERTa, XLNet and ELECTRA","date":"2021-04-05","arxiv_id":"2104.02041","n_code_links":0,"syntology":null},{"paper":"/paper/russian-paraphrasers-paraphrase-with","slug":"russian-paraphrasers-paraphrase-with","title":"Russian Paraphrasers: Paraphrase with Transformers","date":"2021-04-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"through-the-looking-glass-learning-to","title":"Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models","date":"2021-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-graph-partitioning-for-very-large","title":"Automatic Graph Partitioning for Very Large-scale Deep Learning","date":"2021-03-30","arxiv_id":"2103.16063","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-practical-survey-on-faster-and-lighter","title":"A Practical Survey on Faster and Lighter Transformers","date":"2021-03-26","arxiv_id":"2103.14636","n_code_links":0,"syntology":null},{"paper":null,"slug":"k-xlnet-a-general-method-for-combining","title":"K-XLNet: A General Method for Combining Explicit Knowledge with Language Model Pretraining","date":"2021-03-25","arxiv_id":"2104.10649","n_code_links":0,"syntology":null},{"paper":"/paper/all-nlp-tasks-are-generation-tasks-a-general","slug":"all-nlp-tasks-are-generation-tasks-a-general","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-03-18","arxiv_id":"2103.10360","n_code_links":8,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["THUDM/GLM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"comparing-the-performance-of-nlp-toolkits-and","title":"Comparing the Performance of NLP Toolkits and Evaluation measures in Legal Tech","date":"2021-03-12","arxiv_id":"2103.11792","n_code_links":0,"syntology":null},{"paper":null,"slug":"orthogonal-attention-a-cloze-style-approach","title":"Orthogonal Attention: A Cloze-Style Approach to Negation Scope Resolution","date":"2021-03-07","arxiv_id":"2103.04294","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-bert-improving-pre-trained","slug":"syntax-bert-improving-pre-trained","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","date":"2021-03-07","arxiv_id":"2103.04350","n_code_links":1,"syntology":null},{"paper":null,"slug":"nlp-cuet-dravidianlangtech-eacl2021","title":"NLP-CUET@DravidianLangTech-EACL2021: Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes","date":"2021-02-28","arxiv_id":"2103.00466","n_code_links":0,"syntology":null},{"paper":"/paper/nlp-cuet-lt-edi-eacl2021-multilingual-code","slug":"nlp-cuet-lt-edi-eacl2021-multilingual-code","title":"NLP-CUET@LT-EDI-EACL2021: Multilingual Code-Mixed Hope Speech Detection using Cross-lingual Representation Learner","date":"2021-02-28","arxiv_id":"2103.00464","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-transfer-learning-for-finding","title":"Multi-task transfer learning for finding actionable information from crisis-related messages on social media","date":"2021-02-26","arxiv_id":"2102.13395","n_code_links":0,"syntology":null},{"paper":"/paper/pada-a-prompt-based-autoregressive-approach","slug":"pada-a-prompt-based-autoregressive-approach","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","date":"2021-02-24","arxiv_id":"2102.12206","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-learning-for-information","title":"Few Shot Learning for Information Verification","date":"2021-02-22","arxiv_id":"2102.10956","n_code_links":0,"syntology":null},{"paper":"/paper/quiz-style-question-generation-for-news","slug":"quiz-style-question-generation-for-news","title":"Quiz-Style Question Generation for News Stories","date":"2021-02-18","arxiv_id":"2102.09094","n_code_links":2,"syntology":null},{"paper":"/paper/exploring-transformers-in-natural-language","slug":"exploring-transformers-in-natural-language","title":"Exploring Transformers in Natural Language Generation: GPT, BERT, and XLNet","date":"2021-02-16","arxiv_id":"2102.08036","n_code_links":1,"syntology":null},{"paper":"/paper/wangchanberta-pretraining-transformer-based","slug":"wangchanberta-pretraining-transformer-based","title":"WangchanBERTa: Pretraining transformer-based Thai Language Models","date":"2021-01-24","arxiv_id":"2101.09635","n_code_links":2,"syntology":null},{"paper":null,"slug":"transformer-based-models-for-question","title":"Transformer-Based Models for Question Answering on COVID19","date":"2021-01-16","arxiv_id":"2101.11432","n_code_links":0,"syntology":null},{"paper":null,"slug":"fake-news-detection-system-using-xlnet-model","title":"Fake News Detection System using XLNet model with Topic Distributions: CONSTRAINT@AAAI2021 Shared Task","date":"2021-01-12","arxiv_id":"2101.11425","n_code_links":0,"syntology":null},{"paper":"/paper/cisco-at-aaai-cad21-shared-task-predicting","slug":"cisco-at-aaai-cad21-shared-task-predicting","title":"Cisco at AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides using Contextualized Embeddings","date":"2021-01-10","arxiv_id":"2101.11422","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-approach-towards-music","slug":"transformer-based-approach-towards-music","title":"Transformer-based approach towards music emotion recognition from lyrics","date":"2021-01-06","arxiv_id":"2101.02051","n_code_links":1,"syntology":null},{"paper":"/paper/improving-sequence-to-sequence-pre-training","slug":"improving-sequence-to-sequence-pre-training","title":"Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting","date":"2021-01-02","arxiv_id":"2101.00416","n_code_links":1,"syntology":null},{"paper":null,"slug":"pre-training-text-to-text-transformers-to","title":"Pre-training Text-to-Text Transformers to Write and Reason with Concepts","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"syntactic-relevance-xlnet-word-embedding","title":"Syntactic Relevance XLNet Word Embedding Generation in Low-Resource Machine Translation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/earlybert-efficient-bert-training-via-early-1","slug":"earlybert-efficient-bert-training-via-early-1","title":"EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets","date":"2020-12-31","arxiv_id":"2101.00063","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["VITA-Group/EarlyBERT"],"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","unlocated"]}}},{"paper":"/paper/factual-error-correction-of-claims","slug":"factual-error-correction-of-claims","title":"Evidence-based Factual Error Correction","date":"2020-12-31","arxiv_id":"2012.15788","n_code_links":3,"syntology":null},{"paper":"/paper/leveraging-parsbert-and-pretrained-mt5-for","slug":"leveraging-parsbert-and-pretrained-mt5-for","title":"Leveraging ParsBERT and Pretrained mT5 for Persian Abstractive Text Summarization","date":"2020-12-21","arxiv_id":"2012.11204","n_code_links":1,"syntology":null},{"paper":"/paper/dialogxl-all-in-one-xlnet-for-multi-party","slug":"dialogxl-all-in-one-xlnet-for-multi-party","title":"DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition","date":"2020-12-16","arxiv_id":"2012.08695","n_code_links":4,"syntology":null},{"paper":null,"slug":"discriminative-pre-training-for-low-resource","title":"Discriminative Pre-training for Low Resource Title Compression in Conversational Grocery","date":"2020-12-13","arxiv_id":"2012.06943","n_code_links":0,"syntology":null},{"paper":"/paper/yelp-review-rating-prediction-machine","slug":"yelp-review-rating-prediction-machine","title":"Yelp Review Rating Prediction: Machine Learning and Deep Learning Models","date":"2020-12-12","arxiv_id":"2012.06690","n_code_links":1,"syntology":null},{"paper":"/paper/how-can-we-know-when-language-models-know","slug":"how-can-we-know-when-language-models-know","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","date":"2020-12-02","arxiv_id":"2012.00955","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-at-semeval-2020-task-8-using-bert-to","title":"BERT at SemEval-2020 Task 8: Using BERT to Analyse Meme Emotions","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-probabilistic-distributional-and","title":"Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-unsupervised-representation","title":"Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/flight-of-the-pegasus-comparing-transformers","slug":"flight-of-the-pegasus-comparing-transformers","title":"Flight of the PEGASUS? Comparing Transformers on Few-shot and Zero-shot Multi-document Abstractive Summarization","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-11-an-empirical","title":"Hitachi at SemEval-2020 Task 11: An Empirical Study of Pre-Trained Transformer Family for Propaganda Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hy-nli-a-hybrid-system-for-natural-language","slug":"hy-nli-a-hybrid-system-for-natural-language","title":"Hy-NLI: a Hybrid system for Natural Language Inference","date":"2020-12-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"label-representations-in-modeling","title":"Label Representations in Modeling Classification as Text Generation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-language-models-for-text","title":"Neural language models for text classification in evidence-based medicine","date":"2020-12-01","arxiv_id":"2012.00584","n_code_links":0,"syntology":null},{"paper":null,"slug":"nlp-just-at-semeval-2020-task-4-ensemble","title":"NLP@JUST at SemEval-2020 Task 4: Ensemble Technique for BERT and Roberta to Evaluate Commonsense Validation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sinai-at-semeval-2020-task-12-offensive","title":"SINAI at SemEval-2020 Task 12: Offensive Language Identification Exploring Transfer Learning Models","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"b7c5665f8388ec9e5a0288571527677aa9b216335b25496f7c2529863242e368","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}