{"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/9","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":9,"pages_in_order":10,"rows_per_page":100,"rows":[801,900],"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/8","next":"/method/sentencepiece/papers/10","papers":[{"paper":null,"slug":"ssn-nlp-at-semeval-2020-task-4-text","title":"SSN-NLP at SemEval-2020 Task 4: Text Classification and Generation on Common Sense Context Using Neural Networks","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multitask-learning-of-negation-and","slug":"multitask-learning-of-negation-and","title":"Multitask Learning of Negation and Speculation using Transformers","date":"2020-11-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"reassert-deep-learning-for-assert-generation","title":"ReAssert: Deep Learning for Assert Generation","date":"2020-11-19","arxiv_id":"2011.09784","n_code_links":0,"syntology":null},{"paper":"/paper/learning-from-task-descriptions","slug":"learning-from-task-descriptions","title":"Learning from Task Descriptions","date":"2020-11-16","arxiv_id":"2011.08115","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/seqgensql-a-robust-sequence-generation-model","slug":"seqgensql-a-robust-sequence-generation-model","title":"SeqGenSQL -- A Robust Sequence Generation Model for Structured Query Language","date":"2020-11-07","arxiv_id":"2011.03836","n_code_links":2,"syntology":null},{"paper":"/paper/bionerflair-biomedical-named-entity","slug":"bionerflair-biomedical-named-entity","title":"BioNerFlair: biomedical named entity recognition using flair embedding and sequence tagger","date":"2020-11-03","arxiv_id":"2011.01504","n_code_links":1,"syntology":null},{"paper":"/paper/abnirml-analyzing-the-behavior-of-neural-ir","slug":"abnirml-analyzing-the-behavior-of-neural-ir","title":"ABNIRML: Analyzing the Behavior of Neural IR Models","date":"2020-11-02","arxiv_id":"2011.00696","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["allenai/abnirml"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/chime-cross-passage-hierarchical-memory","slug":"chime-cross-passage-hierarchical-memory","title":"CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering","date":"2020-11-01","arxiv_id":"2011.00519","n_code_links":1,"syntology":null},{"paper":"/paper/towards-zero-shot-conditional-summarization","slug":"towards-zero-shot-conditional-summarization","title":"Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-unknot","title":"Learning to Unknot","date":"2020-10-28","arxiv_id":"2010.16263","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-association-between-labels-and-free","slug":"measuring-association-between-labels-and-free","title":"Measuring Association Between Labels and Free-Text Rationales","date":"2020-10-24","arxiv_id":"2010.12762","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["allenai/label_rationale_association"],"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"]}}},{"paper":null,"slug":"unsupervised-paraphrase-generation-via","title":"Unsupervised Paraphrasing with Pretrained Language Models","date":"2020-10-24","arxiv_id":"2010.12885","n_code_links":0,"syntology":null},{"paper":"/paper/ernie-gram-pre-training-with-explicitly-n","slug":"ernie-gram-pre-training-with-explicitly-n","title":"ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding","date":"2020-10-23","arxiv_id":"2010.12148","n_code_links":2,"syntology":null},{"paper":"/paper/mt5-a-massively-multilingual-pre-trained-text","slug":"mt5-a-massively-multilingual-pre-trained-text","title":"mT5: A massively multilingual pre-trained text-to-text transformer","date":"2020-10-22","arxiv_id":"2010.11934","n_code_links":8,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["google-research/multilingual-t5"],"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":["listed","official"]}}},{"paper":null,"slug":"scientific-claim-verification-with-vert5erini","title":"Scientific Claim Verification with VERT5ERINI","date":"2020-10-22","arxiv_id":"2010.11930","n_code_links":0,"syntology":null},{"paper":"/paper/automets-the-autocomplete-for-medical-text","slug":"automets-the-autocomplete-for-medical-text","title":"AutoMeTS: The Autocomplete for Medical Text Simplification","date":"2020-10-20","arxiv_id":"2010.10573","n_code_links":1,"syntology":null},{"paper":null,"slug":"performance-of-transfer-learning-model-vs","title":"Performance of Transfer Learning Model vs. Traditional Neural Network in Low System Resource Environment","date":"2020-10-20","arxiv_id":"2011.07962","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-norm-growth-during-training-of","slug":"parameter-norm-growth-during-training-of","title":"Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent","date":"2020-10-19","arxiv_id":"2010.09697","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":1,"n_instrument":5,"unverified":1,"pointer_only":7,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["viking-sudo-rm/norm-growth"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nuig-shubhanker-dravidian-codemix-fire2020","title":"NUIG-Shubhanker@Dravidian-CodeMix-FIRE2020: Sentiment Analysis of Code-Mixed Dravidian text using XLNet","date":"2020-10-15","arxiv_id":"2010.07773","n_code_links":0,"syntology":null},{"paper":"/paper/aspect-based-document-similarity-for-research","slug":"aspect-based-document-similarity-for-research","title":"Aspect-based Document Similarity for Research Papers","date":"2020-10-13","arxiv_id":"2010.06395","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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","official":{"repos":["malteos/aspect-document-similarity"],"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"]}}},{"paper":null,"slug":"interpreting-attention-models-with-human","title":"Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension","date":"2020-10-13","arxiv_id":"2010.06396","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatbot-interaction-with-artificial","title":"Chatbot Interaction with Artificial Intelligence: Human Data Augmentation with T5 and Language Transformer Ensemble for Text Classification","date":"2020-10-12","arxiv_id":"2010.05990","n_code_links":0,"syntology":null},{"paper":"/paper/automated-concatenation-of-embeddings-for-1","slug":"automated-concatenation-of-embeddings-for-1","title":"Automated Concatenation of Embeddings for Structured Prediction","date":"2020-10-10","arxiv_id":"2010.05006","n_code_links":2,"syntology":null},{"paper":"/paper/textsettr-label-free-text-style-extraction-1","slug":"textsettr-label-free-text-style-extraction-1","title":"TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling","date":"2020-10-08","arxiv_id":"2010.03802","n_code_links":1,"syntology":null},{"paper":"/paper/analyzing-individual-neurons-in-pre-trained","slug":"analyzing-individual-neurons-in-pre-trained","title":"Analyzing Individual Neurons in Pre-trained Language Models","date":"2020-10-06","arxiv_id":"2010.02695","n_code_links":1,"syntology":null},{"paper":"/paper/converting-the-point-of-view-of-messages","slug":"converting-the-point-of-view-of-messages","title":"Converting the Point of View of Messages Spoken to Virtual Assistants","date":"2020-10-06","arxiv_id":"2010.02600","n_code_links":2,"syntology":null},{"paper":null,"slug":"how-effective-is-task-agnostic-data","title":"How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers?","date":"2020-10-05","arxiv_id":"2010.01764","n_code_links":0,"syntology":null},{"paper":null,"slug":"pum-at-semeval-2020-task-12-aggregation-of","title":"PUM at SemEval-2020 Task 12: Aggregation of Transformer-based models' features for offensive language recognition","date":"2020-10-05","arxiv_id":"2010.01897","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-rhetorical-capacities-of-neural","title":"Examining the rhetorical capacities of neural language models","date":"2020-10-01","arxiv_id":"2010.00153","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-multi-model-inference-by-merging","title":"Accelerating Multi-Model Inference by Merging DNNs of Different Weights","date":"2020-09-28","arxiv_id":"2009.13062","n_code_links":0,"syntology":null},{"paper":"/paper/bet-a-backtranslation-approach-for-easy-data","slug":"bet-a-backtranslation-approach-for-easy-data","title":"BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification Context","date":"2020-09-25","arxiv_id":"2009.12452","n_code_links":1,"syntology":null},{"paper":"/paper/mintl-minimalist-transfer-learning-for-task","slug":"mintl-minimalist-transfer-learning-for-task","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","date":"2020-09-25","arxiv_id":"2009.12005","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zlinao/MinTL"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"weird-ai-yankovic-generating-parody-lyrics","title":"Weird AI Yankovic: Generating Parody Lyrics","date":"2020-09-25","arxiv_id":"2009.12240","n_code_links":0,"syntology":null},{"paper":null,"slug":"robustification-of-segmentation-models","title":"Robustification of Segmentation Models Against Adversarial Perturbations In Medical Imaging","date":"2020-09-23","arxiv_id":"2009.11090","n_code_links":0,"syntology":null},{"paper":"/paper/ucd-cs-at-w-nut-2020-shared-task-3-a-text-to","slug":"ucd-cs-at-w-nut-2020-shared-task-3-a-text-to","title":"UCD-CS at W-NUT 2020 Shared Task-3: A Text to Text Approach for COVID-19 Event Extraction on Social Media","date":"2020-09-21","arxiv_id":"2009.10047","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-transformers-a-survey","title":"Efficient Transformers: A Survey","date":"2020-09-14","arxiv_id":"2009.06732","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-pre-trained-contextual-embeddings","title":"Fine-tuning Pre-trained Contextual Embeddings for Citation Content Analysis in Scholarly Publication","date":"2020-09-12","arxiv_id":"2009.05836","n_code_links":0,"syntology":null},{"paper":"/paper/compressed-deep-networks-goodbye-svd-hello","slug":"compressed-deep-networks-goodbye-svd-hello","title":"Compressed Deep Networks: Goodbye SVD, Hello Robust Low-Rank Approximation","date":"2020-09-11","arxiv_id":"2009.05647","n_code_links":1,"syntology":null},{"paper":"/paper/upb-at-semeval-2020-task-6-pretrained","slug":"upb-at-semeval-2020-task-6-pretrained","title":"UPB at SemEval-2020 Task 6: Pretrained Language Models for Definition Extraction","date":"2020-09-11","arxiv_id":"2009.05603","n_code_links":3,"syntology":null},{"paper":null,"slug":"edinburghnlp-at-wnut-2020-task-2-leveraging","title":"EdinburghNLP at WNUT-2020 Task 2: Leveraging Transformers with Generalized Augmentation for Identifying Informativeness in COVID-19 Tweets","date":"2020-09-06","arxiv_id":"2009.06375","n_code_links":0,"syntology":null},{"paper":null,"slug":"qiaoning-at-semeval-2020-task-4-commonsense","title":"QiaoNing at SemEval-2020 Task 4: Commonsense Validation and Explanation system based on ensemble of language model","date":"2020-09-06","arxiv_id":"2009.02645","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multitask-deep-learning-approach-for-user","title":"A Multitask Deep Learning Approach for User Depression Detection on Sina Weibo","date":"2020-08-26","arxiv_id":"2008.11708","n_code_links":0,"syntology":null},{"paper":"/paper/lite-training-strategies-for-portuguese","slug":"lite-training-strategies-for-portuguese","title":"Lite Training Strategies for Portuguese-English and English-Portuguese Translation","date":"2020-08-20","arxiv_id":"2008.08769","n_code_links":1,"syntology":null},{"paper":"/paper/parade-passage-representation-aggregation-for","slug":"parade-passage-representation-aggregation-for","title":"PARADE: Passage Representation Aggregation for Document Reranking","date":"2020-08-20","arxiv_id":"2008.09093","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["canjiali/PARADE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/ptt5-pretraining-and-validating-the-t5-model","slug":"ptt5-pretraining-and-validating-the-t5-model","title":"PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data","date":"2020-08-20","arxiv_id":"2008.09144","n_code_links":3,"syntology":null},{"paper":"/paper/kr-bert-a-small-scale-korean-specific","slug":"kr-bert-a-small-scale-korean-specific","title":"KR-BERT: A Small-Scale Korean-Specific Language Model","date":"2020-08-10","arxiv_id":"2008.03979","n_code_links":1,"syntology":null},{"paper":"/paper/designing-the-business-conversation-corpus-1","slug":"designing-the-business-conversation-corpus-1","title":"Designing the Business Conversation Corpus","date":"2020-08-05","arxiv_id":"2008.01940","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-node-bert-pretraining-cost-efficient","title":"Multi-node Bert-pretraining: Cost-efficient Approach","date":"2020-08-01","arxiv_id":"2008.00177","n_code_links":0,"syntology":null},{"paper":"/paper/neural-machine-translation-with-error","slug":"neural-machine-translation-with-error","title":"Neural Machine Translation with Error Correction","date":"2020-07-21","arxiv_id":"2007.10681","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-pretrained-language-models-for","slug":"investigating-pretrained-language-models-for","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","date":"2020-07-16","arxiv_id":"2007.08426","n_code_links":3,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["UKPLab/plms-graph2text"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hypergrid-efficient-multi-task-transformers","title":"HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections","date":"2020-07-12","arxiv_id":"2007.05891","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-transformer-approach-to-contextual-sarcasm","title":"A Transformer Approach to Contextual Sarcasm Detection in Twitter","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-sarcasm-in-conversation-context","title":"Detecting Sarcasm in Conversation Context Using Transformer-Based Models","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"metaphor-detection-using-contextual-word","title":"Metaphor Detection Using Contextual Word Embeddings From Transformers","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-and-multiresolution-speech","title":"Multimodal and Multiresolution Speech Recognition with Transformers","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"normalizador-neural-de-datas-e-enderecos","title":"Normalizador Neural de Datas e Endereços","date":"2020-06-27","arxiv_id":"2007.04300","n_code_links":0,"syntology":null},{"paper":null,"slug":"transferring-monolingual-model-to-low","title":"Transferring Monolingual Model to Low-Resource Language: The Case of Tigrinya","date":"2020-06-13","arxiv_id":"2006.07698","n_code_links":0,"syntology":null},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","n_code_links":14,"syntology":{"ran":4,"of":13,"n_ran_checked":3,"n_instrument":1,"unverified":9,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["microsoft/DeBERTa"],"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":["listed","named_in_paper","unlocated"]}}},{"paper":null,"slug":"a-comparative-study-of-lexical-substitution","title":"A Comparative Study of Lexical Substitution Approaches based on Neural Language Models","date":"2020-05-29","arxiv_id":"2006.00031","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-pretrained-language-models-for","title":"Using Large Pretrained Language Models for Answering User Queries from Product Specifications","date":"2020-05-29","arxiv_id":"2005.14613","n_code_links":0,"syntology":null},{"paper":"/paper/text-to-text-pre-training-for-data-to-text","slug":"text-to-text-pre-training-for-data-to-text","title":"Text-to-Text Pre-Training for Data-to-Text Tasks","date":"2020-05-21","arxiv_id":"2005.10433","n_code_links":2,"syntology":null},{"paper":"/paper/impactcite-an-xlnet-based-method-for-citation","slug":"impactcite-an-xlnet-based-method-for-citation","title":"ImpactCite: An XLNet-based method for Citation Impact Analysis","date":"2020-05-05","arxiv_id":"2005.06611","n_code_links":1,"syntology":null},{"paper":"/paper/deformer-decomposing-pre-trained-transformers","slug":"deformer-decomposing-pre-trained-transformers","title":"DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering","date":"2020-05-02","arxiv_id":"2005.00697","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"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) · 3 unverified","official":{"repos":["StonyBrookNLP/deformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-the-impact-of-sub-word-information","title":"Evaluating the Impact of Sub-word Information and Cross-lingual Word Embeddings on Mi'kmaq Language Modelling","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/sibert-enhanced-chinese-pre-trained-language","slug":"sibert-enhanced-chinese-pre-trained-language","title":"SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion","date":"2020-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/r-3-reverse-retrieve-and-rank-for-sarcasm","slug":"r-3-reverse-retrieve-and-rank-for-sarcasm","title":"$R^3$: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge","date":"2020-04-28","arxiv_id":"2004.13248","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":null}},{"paper":"/paper/cross-lingual-information-retrieval-with-bert","slug":"cross-lingual-information-retrieval-with-bert","title":"Cross-lingual Information Retrieval with BERT","date":"2020-04-24","arxiv_id":"2004.13005","n_code_links":1,"syntology":null},{"paper":"/paper/mpnet-masked-and-permuted-pre-training-for","slug":"mpnet-masked-and-permuted-pre-training-for","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","date":"2020-04-20","arxiv_id":"2004.09297","n_code_links":7,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/MPNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/stereoset-measuring-stereotypical-bias-in","slug":"stereoset-measuring-stereotypical-bias-in","title":"StereoSet: Measuring stereotypical bias in pretrained language models","date":"2020-04-20","arxiv_id":"2004.09456","n_code_links":3,"syntology":null},{"paper":"/paper/exploiting-redundancy-in-pre-trained-language","slug":"exploiting-redundancy-in-pre-trained-language","title":"Analyzing Redundancy in Pretrained Transformer Models","date":"2020-04-08","arxiv_id":"2004.04010","n_code_links":1,"syntology":null},{"paper":"/paper/poor-man-s-bert-smaller-and-faster","slug":"poor-man-s-bert-smaller-and-faster","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","date":"2020-04-08","arxiv_id":"2004.03844","n_code_links":4,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hsajjad/transformers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/evaluating-machines-by-their-real-world","slug":"evaluating-machines-by-their-real-world","title":"TuringAdvice: A Generative and Dynamic Evaluation of Language Use","date":"2020-04-07","arxiv_id":"2004.03607","n_code_links":1,"syntology":null},{"paper":"/paper/electra-pre-training-text-encoders-as-1","slug":"electra-pre-training-text-encoders-as-1","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","date":"2020-03-23","arxiv_id":"2003.10555","n_code_links":19,"syntology":{"ran":31,"of":40,"n_ran_checked":18,"n_instrument":13,"unverified":9,"pointer_only":10,"phrase":"31 ran (of which 7 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 2 violated, 14 with no contract checked; 13 where Syntology's instrument failed) · 9 unverified","official":{"repos":["google-research/electra"],"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":["listed","unlocated"]}}},{"paper":"/paper/pairwise-multi-class-document-classification","slug":"pairwise-multi-class-document-classification","title":"Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles","date":"2020-03-22","arxiv_id":"2003.09881","n_code_links":4,"syntology":null},{"paper":"/paper/tttttackling-winogrande-schemas","slug":"tttttackling-winogrande-schemas","title":"TTTTTackling WinoGrande Schemas","date":"2020-03-18","arxiv_id":"2003.08380","n_code_links":0,"syntology":null},{"paper":"/paper/neural-machine-translation-with-joint","slug":"neural-machine-translation-with-joint","title":"Neural Machine Translation with Joint Representation","date":"2020-02-16","arxiv_id":"2002.06546","n_code_links":1,"syntology":null},{"paper":null,"slug":"stress-test-evaluation-of-transformer-based","title":"Stress Test Evaluation of Transformer-based Models in Natural Language Understanding Tasks","date":"2020-02-14","arxiv_id":"2002.06261","n_code_links":0,"syntology":null},{"paper":"/paper/reformer-the-efficient-transformer-1","slug":"reformer-the-efficient-transformer-1","title":"Reformer: The Efficient Transformer","date":"2020-01-13","arxiv_id":"2001.04451","n_code_links":10,"syntology":{"ran":6,"of":8,"n_ran_checked":1,"n_instrument":5,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google/trax"],"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/resolving-the-scope-of-speculation-and","slug":"resolving-the-scope-of-speculation-and","title":"Resolving the Scope of Speculation and Negation using Transformer-Based Architectures","date":"2020-01-09","arxiv_id":"2001.02885","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-al-bert-for-arbitrarily-long-document","title":"BERT-AL: BERT for Arbitrarily Long Document Understanding","date":"2020-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/clinical-xlnet-modeling-sequential-clinical","slug":"clinical-xlnet-modeling-sequential-clinical","title":"Clinical XLNet: Modeling Sequential Clinical Notes and Predicting Prolonged Mechanical Ventilation","date":"2019-12-27","arxiv_id":"1912.11975","n_code_links":3,"syntology":null},{"paper":null,"slug":"make-lead-bias-in-your-favor-a-simple-and-2","title":"Leveraging Lead Bias for Zero-shot Abstractive News Summarization","date":"2019-12-25","arxiv_id":"1912.11602","n_code_links":0,"syntology":null},{"paper":null,"slug":"waldorf-wasteless-language-model-distillation","title":"WaLDORf: Wasteless Language-model Distillation On Reading-comprehension","date":"2019-12-13","arxiv_id":"1912.06638","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploration-of-data-augmentation-and-1","title":"An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering","date":"2019-12-04","arxiv_id":"1912.02145","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-commonsense-in-pre-trained","slug":"evaluating-commonsense-in-pre-trained","title":"Evaluating Commonsense in Pre-trained Language Models","date":"2019-11-27","arxiv_id":"1911.11931","n_code_links":1,"syntology":null},{"paper":"/paper/low-rank-factorization-for-compact-multi-head","slug":"low-rank-factorization-for-compact-multi-head","title":"Low Rank Factorization for Compact Multi-Head Self-Attention","date":"2019-11-26","arxiv_id":"1912.00835","n_code_links":1,"syntology":null},{"paper":null,"slug":"attending-to-entities-for-better-text","title":"Attending to Entities for Better Text Understanding","date":"2019-11-11","arxiv_id":"1911.04361","n_code_links":0,"syntology":null},{"paper":"/paper/faspell-a-fast-adaptable-simple-powerful","slug":"faspell-a-fast-adaptable-simple-powerful","title":"FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"generalizing-question-answering-system-with","title":"Generalizing Question Answering System with Pre-trained Language Model Fine-tuning","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"iit-kgp-at-coin-2019-using-pre-trained","title":"IIT-KGP at COIN 2019: Using pre-trained Language Models for modeling Machine Comprehension","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/pingan-smart-health-and-sjtu-at-coin-shared","slug":"pingan-smart-health-and-sjtu-at-coin-shared","title":"Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-from-transformers-to-fake","title":"Transfer Learning from Transformers to Fake News Challenge Stance Detection (FNC-1) Task","date":"2019-10-31","arxiv_id":"1910.14353","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-inter-speaker-relationship-in-xlnet","title":"Modeling Inter-Speaker Relationship in XLNet for Contextual Spoken Language Understanding","date":"2019-10-28","arxiv_id":"1910.12531","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","n_code_links":57,"syntology":{"ran":21,"of":31,"n_ran_checked":20,"n_instrument":1,"unverified":10,"pointer_only":0,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","official":null}},{"paper":null,"slug":"speech-xlnet-unsupervised-acoustic-model","title":"Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks","date":"2019-10-23","arxiv_id":"1910.10387","n_code_links":0,"syntology":null},{"paper":null,"slug":"xl-editor-post-editing-sentences-with-xlnet","title":"XL-Editor: Post-editing Sentences with XLNet","date":"2019-10-19","arxiv_id":"1910.10479","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-question-answering-from","title":"Multilingual Question Answering from Formatted Text applied to Conversational Agents","date":"2019-10-10","arxiv_id":"1910.04659","n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-language-model-compression-with-1","title":"Extremely Small BERT Models from Mixed-Vocabulary Training","date":"2019-09-25","arxiv_id":"1909.11687","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-and-automated-essay-scoring","slug":"language-models-and-automated-essay-scoring","title":"Language models and Automated Essay Scoring","date":"2019-09-18","arxiv_id":"1909.09482","n_code_links":1,"syntology":null},{"paper":"/paper/frustratingly-easy-natural-question-answering","slug":"frustratingly-easy-natural-question-answering","title":"Frustratingly Easy Natural Question Answering","date":"2019-09-11","arxiv_id":"1909.05286","n_code_links":0,"syntology":null}],"record_sha256":"cd0e2be7f6c0cb8c761a6c447cea5c7e639f199a49f321d0797c18606d9b09fc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}