{"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/7","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":7,"pages_in_order":10,"rows_per_page":100,"rows":[601,700],"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/6","next":"/method/sentencepiece/papers/8","papers":[{"paper":null,"slug":"arabart-a-pretrained-arabic-sequence-to-1","title":"AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization","date":"2022-03-21","arxiv_id":"2203.10945","n_code_links":0,"syntology":null},{"paper":"/paper/dq-bart-efficient-sequence-to-sequence-model","slug":"dq-bart-efficient-sequence-to-sequence-model","title":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization","date":"2022-03-21","arxiv_id":"2203.11239","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":0,"n_instrument":1,"unverified":4,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["amazon-research/dq-bart"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["listed"]}}},{"paper":"/paper/coloring-the-blank-slate-pre-training-imparts-1","slug":"coloring-the-blank-slate-pre-training-imparts-1","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","date":"2022-03-17","arxiv_id":"2203.09397","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sebschu/multilingual-transformations"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/scinli-a-corpus-for-natural-language","slug":"scinli-a-corpus-for-natural-language","title":"SciNLI: A Corpus for Natural Language Inference on Scientific Text","date":"2022-03-13","arxiv_id":"2203.06728","n_code_links":1,"syntology":null},{"paper":"/paper/it5-large-scale-text-to-text-pretraining-for","slug":"it5-large-scale-text-to-text-pretraining-for","title":"IT5: Text-to-text Pretraining for Italian Language Understanding and Generation","date":"2022-03-07","arxiv_id":"2203.03759","n_code_links":3,"syntology":null},{"paper":"/paper/parameter-efficient-mixture-of-experts","slug":"parameter-efficient-mixture-of-experts","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","date":"2022-03-02","arxiv_id":"2203.01104","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rucaibox/mpo","rucaibox/mpoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"e-lang-energy-based-joint-inferencing-of-1","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","date":"2022-03-01","arxiv_id":"2203.00748","n_code_links":0,"syntology":null},{"paper":null,"slug":"hyperprompt-prompt-based-task-conditioning-of","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","date":"2022-03-01","arxiv_id":"2203.00759","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixture-of-experts-with-expert-choice-routing","title":"Mixture-of-Experts with Expert Choice Routing","date":"2022-02-18","arxiv_id":"2202.09368","n_code_links":0,"syntology":null},{"paper":"/paper/probing-pretrained-models-of-source-code","slug":"probing-pretrained-models-of-source-code","title":"Probing Pretrained Models of Source Code","date":"2022-02-16","arxiv_id":"2202.08975","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-on-the-edge-identifying-where-a","title":"Predicting on the Edge: Identifying Where a Larger Model Does Better","date":"2022-02-15","arxiv_id":"2202.07652","n_code_links":0,"syntology":null},{"paper":"/paper/a-multi-task-semi-supervised-framework-for","slug":"a-multi-task-semi-supervised-framework-for","title":"A multi-task semi-supervised framework for Text2Graph & Graph2Text","date":"2022-02-12","arxiv_id":"2202.06041","n_code_links":1,"syntology":null},{"paper":null,"slug":"hat5-hate-language-identification-using-text","title":"HaT5: Hate Language Identification using Text-to-Text Transfer Transformer","date":"2022-02-11","arxiv_id":"2202.05690","n_code_links":0,"syntology":null},{"paper":null,"slug":"logical-reasoning-for-task-oriented-dialogue","title":"Logical Reasoning for Task Oriented Dialogue Systems","date":"2022-02-08","arxiv_id":"2202.04161","n_code_links":0,"syntology":null},{"paper":"/paper/regression-transformer-concurrent-conditional","slug":"regression-transformer-concurrent-conditional","title":"Regression Transformer: Concurrent sequence regression and generation for molecular language modeling","date":"2022-02-01","arxiv_id":"2202.01338","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["ibm/regression-transformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-comparative-study-on-language-models-for-1","slug":"a-comparative-study-on-language-models-for-1","title":"A Comparative Study on Language Models for Task-Oriented Dialogue Systems","date":"2022-01-21","arxiv_id":"2201.08687","n_code_links":1,"syntology":null},{"paper":"/paper/cheating-automatic-short-answer-grading-on","slug":"cheating-automatic-short-answer-grading-on","title":"Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and Adverbs","date":"2022-01-20","arxiv_id":"2201.08318","n_code_links":1,"syntology":null},{"paper":"/paper/gap-gen-guided-automatic-python-code","slug":"gap-gen-guided-automatic-python-code","title":"GAP-Gen: Guided Automatic Python Code Generation","date":"2022-01-19","arxiv_id":"2201.08810","n_code_links":1,"syntology":null},{"paper":null,"slug":"allwoz-towards-multilingual-task-oriented-1","title":"AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"arabart-a-pretrained-arabic-sequence-to","title":"AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-pretrained-multilingual-models-equally","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-regressive-text-generation-with-pre","title":"Auto-regressive Text Generation with Pre-Trained Language Models: An Empirical Study on Question-type Short Text Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-zero-shot-semantic-parsing-with","title":"Efficient Zero-Shot Semantic Parsing with Paraphrasing from Pretrained Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-example-selection-for-few-shot-text","title":"Exploring Example Selection for Few-shot Text-to-SQL Semantic Parsing","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-low-resource-transfer-learning","title":"Exploring the Low-Resource Transfer-Learning with mT5 model","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-deduction-through-search","title":"Natural Language Deduction through Search over Statement Compositions","date":"2022-01-16","arxiv_id":"2201.06028","n_code_links":0,"syntology":null},{"paper":null,"slug":"re2g-retrieve-rerank-generate","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/unifiedskg-unifying-and-multi-tasking","slug":"unifiedskg-unifying-and-multi-tasking","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","date":"2022-01-16","arxiv_id":"2201.05966","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":1,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["hkunlp/unifiedskg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/relationship-extraction-for-knowledge-graph","slug":"relationship-extraction-for-knowledge-graph","title":"Comparison of biomedical relationship extraction methods and models for knowledge graph creation","date":"2022-01-05","arxiv_id":"2201.01647","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-university-of-texas-at-dallas-hltri-s","title":"The University of Texas at Dallas HLTRI's Participation in EPIC-QA: Searching for Entailed Questions Revealing Novel Answer Nuggets","date":"2021-12-28","arxiv_id":"2112.13946","n_code_links":0,"syntology":null},{"paper":null,"slug":"your-answer-is-incorrect-would-you-like-to","title":"Your Answer is Incorrect... Would you like to know why? Introducing a Bilingual Short Answer Feedback Dataset","date":"2021-12-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/crosssum-beyond-english-centric-cross-lingual","slug":"crosssum-beyond-english-centric-cross-lingual","title":"CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs","date":"2021-12-16","arxiv_id":"2112.08804","n_code_links":1,"syntology":null},{"paper":"/paper/dream-uncovering-mental-models-behind","slug":"dream-uncovering-mental-models-behind","title":"DREAM: Improving Situational QA by First Elaborating the Situation","date":"2021-12-16","arxiv_id":"2112.08656","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/dream"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"allwoz-towards-multilingual-task-oriented","title":"AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All","date":"2021-12-15","arxiv_id":"2112.08333","n_code_links":0,"syntology":null},{"paper":"/paper/longt5-efficient-text-to-text-transformer-for","slug":"longt5-efficient-text-to-text-transformer-for","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","date":"2021-12-15","arxiv_id":"2112.07916","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/longt5"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/named-entity-recognition-architecture","slug":"named-entity-recognition-architecture","title":"Named entity recognition architecture combining contextual and global features","date":"2021-12-15","arxiv_id":"2112.08033","n_code_links":1,"syntology":null},{"paper":"/paper/improving-compositional-generalization-with-2","slug":"improving-compositional-generalization-with-2","title":"Improving Compositional Generalization with Latent Structure and Data Augmentation","date":"2021-12-14","arxiv_id":"2112.07610","n_code_links":2,"syntology":null},{"paper":null,"slug":"do-data-based-curricula-work","title":"Do Data-based Curricula Work?","date":"2021-12-13","arxiv_id":"2112.06510","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-neural-functional-program-evaluation-1","title":"Towards Neural Functional Program Evaluation","date":"2021-12-09","arxiv_id":"2112.04630","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-token-normalization-improves-vision-1","slug":"dynamic-token-normalization-improves-vision-1","title":"Dynamic Token Normalization Improves Vision Transformers","date":"2021-12-05","arxiv_id":"2112.02624","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 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["wqshao126/dtn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/controlling-conditional-language-models-with","slug":"controlling-conditional-language-models-with","title":"Controlling Conditional Language Models without Catastrophic Forgetting","date":"2021-12-01","arxiv_id":"2112.00791","n_code_links":2,"syntology":{"ran":7,"of":8,"n_ran_checked":5,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["naver/gdc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"searching-for-efficient-transformers-for","title":"Searching for Efficient Transformers for Language Modeling","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-transformers-on-word","title":"A Comparative Study of Transformers on Word Sense Disambiguation","date":"2021-11-30","arxiv_id":"2111.15417","n_code_links":0,"syntology":null},{"paper":null,"slug":"chemical-identification-and-indexing-in","title":"Chemical Identification and Indexing in PubMed Articles via BERT and Text-to-Text Approaches","date":"2021-11-30","arxiv_id":"2111.15622","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-mining-drug-chemical-protein","title":"Text Mining Drug/Chemical-Protein Interactions using an Ensemble of BERT and T5 Based Models","date":"2021-11-30","arxiv_id":"2111.15617","n_code_links":0,"syntology":null},{"paper":"/paper/ext5-towards-extreme-multi-task-scaling-for-1","slug":"ext5-towards-extreme-multi-task-scaling-for-1","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","date":"2021-11-22","arxiv_id":"2111.10952","n_code_links":4,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["google-research/text-to-text-transfer-transformer","tensorflow/mesh"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-comparative-study-on-transfer-learning-and","title":"A Comparative Study on Transfer Learning and Distance Metrics in Semantic Clustering over the COVID-19 Tweets","date":"2021-11-16","arxiv_id":"2111.08658","n_code_links":0,"syntology":null},{"paper":null,"slug":"anna-enhanced-language-representation-for","title":"ANNA: Enhanced Language Representation for Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"coloring-the-blank-slate-pre-training-imparts","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cst5-data-augmentation-for-code-switched","title":"CST5: Data augmentation for Code-Switched Semantic Parsing","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"daml-st5-low-resource-style-transfer-via","title":"DAML-ST5: Low Resource Style Transfer via Domain Adaptive Meta Learning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"frsum-towards-faithful-abstractive","title":"FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generation-of-news-articles-from-tweets-an","title":"Generation of News Articles from Tweets : An Experiment","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"glm-general-language-model-pretraining-with","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-compositional-generalization-with-1","title":"Improving Compositional Generalization with Self-Training for Data-to-Text Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"interpreting-the-robustness-of-neural-nlp","title":"Interpreting the Robustness of Neural NLP Models to Textual Perturbations","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"life-after-bert-what-do-other-muppets","title":"Life after BERT: What do Other Muppets Understand about Language?","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-keyphrase-generation-analysis-and","title":"Neural Keyphrase Generation: Analysis and Evaluation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-power-of-prompt-tuning-for-low-resource-1","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"calculating-question-similarity-is-enough-a","title":"Calculating Question Similarity is Enough: A New Method for KBQA Tasks","date":"2021-11-15","arxiv_id":"2111.07658","n_code_links":0,"syntology":null},{"paper":null,"slug":"say-what-collaborative-pop-lyric-generation","title":"Say What? Collaborative Pop Lyric Generation Using Multitask Transfer Learning","date":"2021-11-15","arxiv_id":"2111.07592","n_code_links":0,"syntology":null},{"paper":"/paper/automated-question-generation-and-question","slug":"automated-question-generation-and-question","title":"Automated question generation and question answering from Turkish texts","date":"2021-11-11","arxiv_id":"2111.06476","n_code_links":1,"syntology":null},{"paper":null,"slug":"ibert-idiom-cloze-style-reading-comprehension","title":"IBERT: Idiom Cloze-style reading comprehension with Attention","date":"2021-11-05","arxiv_id":"2112.02994","n_code_links":0,"syntology":null},{"paper":"/paper/backdoor-pre-trained-models-can-transfer-to","slug":"backdoor-pre-trained-models-can-transfer-to","title":"Backdoor Pre-trained Models Can Transfer to All","date":"2021-10-30","arxiv_id":"2111.00197","n_code_links":1,"syntology":null},{"paper":"/paper/ask-me-in-your-own-words-paraphrasing-for","slug":"ask-me-in-your-own-words-paraphrasing-for","title":"Ask me in your own words: paraphrasing for multitask question answering","date":"2021-10-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fast-model-editing-at-scale-1","slug":"fast-model-editing-at-scale-1","title":"Fast Model Editing at Scale","date":"2021-10-21","arxiv_id":"2110.11309","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["eric-mitchell/mend"],"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/enct5-fine-tuning-t5-encoder-for-non","slug":"enct5-fine-tuning-t5-encoder-for-non","title":"EncT5: A Framework for Fine-tuning T5 as Non-autoregressive Models","date":"2021-10-16","arxiv_id":"2110.08426","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish","title":"Evaluation of Transfer Learning for Polish with a text-to-text model","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-compositional-generalization-with","slug":"improving-compositional-generalization-with","title":"Improving Compositional Generalization with Self-Training for Data-to-Text Generation","date":"2021-10-16","arxiv_id":"2110.08467","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-end-to-end-training-improves","title":"Multi-Task End-to-End Training Improves Conversational Recommendation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-tokenizer-for-enhanced-natural","title":"Semantic Tokenizer for Enhanced Natural Language Processing","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sharpness-aware-minimization-improves","title":"Sharpness-Aware Minimization Improves Language Model Generalization","date":"2021-10-16","arxiv_id":"2110.08529","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-power-of-prompt-tuning-for-low-resource","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","date":"2021-10-16","arxiv_id":"2110.08525","n_code_links":0,"syntology":null},{"paper":null,"slug":"causally-estimating-the-sensitivity-of-neural-1","title":"Interpreting the Robustness of Neural NLP Models to Textual Perturbations","date":"2021-10-14","arxiv_id":"2110.07159","n_code_links":0,"syntology":null},{"paper":"/paper/lfpt5-a-unified-framework-for-lifelong-few-1","slug":"lfpt5-a-unified-framework-for-lifelong-few-1","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","date":"2021-10-14","arxiv_id":"2110.07298","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["qcwthu/lifelong-fewshot-language-learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/speecht5-unified-modal-encoder-decoder-pre","slug":"speecht5-unified-modal-encoder-decoder-pre","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","date":"2021-10-14","arxiv_id":"2110.07205","n_code_links":6,"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":["microsoft/speecht5"],"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":"kg-fid-infusing-knowledge-graph-in-fusion-in-1","title":"KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering","date":"2021-10-08","arxiv_id":"2110.04330","n_code_links":0,"syntology":null},{"paper":"/paper/deepa2-a-modular-framework-for-deep-argument","slug":"deepa2-a-modular-framework-for-deep-argument","title":"DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models","date":"2021-10-04","arxiv_id":"2110.01509","n_code_links":1,"syntology":null},{"paper":null,"slug":"perhaps-ptlms-should-go-to-school-a-task-to","title":"Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA","date":"2021-10-04","arxiv_id":"2110.01552","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-frequency-names-exhibit-bias-and","title":"Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models","date":"2021-10-01","arxiv_id":"2110.00672","n_code_links":0,"syntology":null},{"paper":null,"slug":"scale-efficiently-insights-from-pretraining","title":"Scale Efficiently: Insights from Pretraining and Finetuning Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transslowdown-efficiency-attacks-on-neural","title":"TransSlowDown: Efficiency Attacks on Neural Machine Translation Systems","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"what-to-prioritize-natural-language","title":"What to Prioritize? Natural Language Processing for the Development of a Modern Bug Tracking Solution in Hardware Development","date":"2021-09-28","arxiv_id":"2109.13825","n_code_links":0,"syntology":null},{"paper":"/paper/scale-efficiently-insights-from-pre-training","slug":"scale-efficiently-insights-from-pre-training","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","date":"2021-09-22","arxiv_id":"2109.10686","n_code_links":3,"syntology":{"ran":12,"of":12,"n_ran_checked":12,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/google-research"],"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":"hierarchy-aware-t5-with-path-adaptive-mask","title":"Hierarchy-Aware T5 with Path-Adaptive Mask Mechanism for Hierarchical Text Classification","date":"2021-09-17","arxiv_id":"2109.08585","n_code_links":0,"syntology":null},{"paper":"/paper/primer-searching-for-efficient-transformers","slug":"primer-searching-for-efficient-transformers","title":"Primer: Searching for Efficient Transformers for Language Modeling","date":"2021-09-17","arxiv_id":"2109.08668","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/google-research"],"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":null,"slug":"remixers-a-mixer-transformer-architecture","title":"Remixers: A Mixer-Transformer Architecture with Compositional Operators for Natural Language Understanding","date":"2021-09-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-few-shot-multilingual","slug":"language-models-are-few-shot-multilingual","title":"Language Models are Few-shot Multilingual Learners","date":"2021-09-16","arxiv_id":"2109.07684","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["gentaiscool/few-shot-lm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/attention-is-indeed-all-you-need-semantically","slug":"attention-is-indeed-all-you-need-semantically","title":"Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG","date":"2021-09-15","arxiv_id":"2109.07043","n_code_links":1,"syntology":null},{"paper":null,"slug":"prefix-to-sql-text-to-sql-generation-from","title":"Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions","date":"2021-09-15","arxiv_id":"2109.13066","n_code_links":0,"syntology":null},{"paper":"/paper/topic-transferable-table-question-answering","slug":"topic-transferable-table-question-answering","title":"Topic Transferable Table Question Answering","date":"2021-09-15","arxiv_id":"2109.07377","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-a-unified-sequence-to-sequence","slug":"exploring-a-unified-sequence-to-sequence","title":"Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media","date":"2021-09-13","arxiv_id":"2109.05815","n_code_links":1,"syntology":null},{"paper":null,"slug":"not-all-models-localize-linguistic-knowledge","title":"Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations","date":"2021-09-13","arxiv_id":"2109.05958","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-numeracy-learning-ability-of-a","slug":"investigating-numeracy-learning-ability-of-a","title":"Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model","date":"2021-09-10","arxiv_id":"2109.04672","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kuntalkumarpal/t5numeracy"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/picard-parsing-incrementally-for-constrained","slug":"picard-parsing-incrementally-for-constrained","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","date":"2021-09-10","arxiv_id":"2109.05093","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ElementAI/picard"],"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/zero-shot-dialogue-state-tracking-via-cross","slug":"zero-shot-dialogue-state-tracking-via-cross","title":"Zero-Shot Dialogue State Tracking via Cross-Task Transfer","date":"2021-09-10","arxiv_id":"2109.04655","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrieve-caption-generate-visual-grounding","title":"Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models","date":"2021-09-08","arxiv_id":"2109.03892","n_code_links":0,"syntology":null},{"paper":"/paper/general-purpose-question-answering-with-macaw","slug":"general-purpose-question-answering-with-macaw","title":"General-Purpose Question-Answering with Macaw","date":"2021-09-06","arxiv_id":"2109.02593","n_code_links":2,"syntology":null},{"paper":"/paper/codet5-identifier-aware-unified-pre-trained","slug":"codet5-identifier-aware-unified-pre-trained","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","date":"2021-09-02","arxiv_id":"2109.00859","n_code_links":5,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["salesforce/codet5"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/arat5-text-to-text-transformers-for-arabic","slug":"arat5-text-to-text-transformers-for-arabic","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","date":"2021-08-31","arxiv_id":"2109.12068","n_code_links":1,"syntology":null}],"record_sha256":"60f31b090e6d75ee8341ed0c6c6b7e1ef691eb52e405421c59e6500148394a82","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}