{"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/inverse-square-root-schedule/papers/6","list_of":"/method/inverse-square-root-schedule","method":"Inverse Square Root Schedule","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":6,"pages_in_order":8,"rows_per_page":100,"rows":[501,600],"of":702,"counts":{"archive_papers_tagged":702,"with_a_code_link":349,"where_syntology_ran_a_sample":97,"not_listed_spam_title":0,"listed":702,"listed_where_code_ran":97,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":83,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":83,"listed_every_run_a_failure_of_syntologys_instrument":14,"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/inverse-square-root-schedule","prev":"/method/inverse-square-root-schedule/papers/5","next":"/method/inverse-square-root-schedule/papers/7","papers":[{"paper":"/paper/codeattack-code-based-adversarial-attacks-for","slug":"codeattack-code-based-adversarial-attacks-for","title":"CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models","date":"2022-05-31","arxiv_id":"2206.00052","n_code_links":2,"syntology":null},{"paper":"/paper/e2s2-encoding-enhanced-sequence-to-sequence","slug":"e2s2-encoding-enhanced-sequence-to-sequence","title":"E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation","date":"2022-05-30","arxiv_id":"2205.14912","n_code_links":1,"syntology":null},{"paper":null,"slug":"conditional-set-generation-using-seq2seq-1","title":"Conditional set generation using Seq2seq models","date":"2022-05-25","arxiv_id":"2205.12485","n_code_links":0,"syntology":null},{"paper":"/paper/robustlr-evaluating-robustness-to-logical","slug":"robustlr-evaluating-robustness-to-logical","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","date":"2022-05-25","arxiv_id":"2205.12598","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":["ink-usc/robustlr"],"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/tacube-pre-computing-data-cubes-for-answering","slug":"tacube-pre-computing-data-cubes-for-answering","title":"TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data","date":"2022-05-25","arxiv_id":"2205.12682","n_code_links":1,"syntology":null},{"paper":null,"slug":"edit5-semi-autoregressive-text-editing-with","title":"EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start","date":"2022-05-24","arxiv_id":"2205.12209","n_code_links":0,"syntology":null},{"paper":"/paper/flute-figurative-language-understanding-and","slug":"flute-figurative-language-understanding-and","title":"FLUTE: Figurative Language Understanding through Textual Explanations","date":"2022-05-24","arxiv_id":"2205.12404","n_code_links":1,"syntology":null},{"paper":"/paper/geomlama-geo-diverse-commonsense-probing-on","slug":"geomlama-geo-diverse-commonsense-probing-on","title":"GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models","date":"2022-05-24","arxiv_id":"2205.12247","n_code_links":1,"syntology":null},{"paper":null,"slug":"medical-scientific-table-to-text-generation","title":"Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint","date":"2022-05-24","arxiv_id":"2205.12368","n_code_links":0,"syntology":null},{"paper":"/paper/workflow-discovery-from-dialogues-in-the-low","slug":"workflow-discovery-from-dialogues-in-the-low","title":"Workflow Discovery from Dialogues in the Low Data Regime","date":"2022-05-24","arxiv_id":"2205.11690","n_code_links":1,"syntology":null},{"paper":"/paper/a-question-answer-driven-approach-to-reveal","slug":"a-question-answer-driven-approach-to-reveal","title":"A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negations","date":"2022-05-23","arxiv_id":"2205.11467","n_code_links":1,"syntology":null},{"paper":"/paper/banglanlg-benchmarks-and-resources-for","slug":"banglanlg-benchmarks-and-resources-for","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","date":"2022-05-23","arxiv_id":"2205.11081","n_code_links":2,"syntology":null},{"paper":"/paper/life-after-bert-what-do-other-muppets-2","slug":"life-after-bert-what-do-other-muppets-2","title":"Life after BERT: What do Other Muppets Understand about Language?","date":"2022-05-21","arxiv_id":"2205.10696","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish-1","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","date":"2022-05-18","arxiv_id":"2205.08808","n_code_links":0,"syntology":null},{"paper":null,"slug":"pash-at-trec-2021-deep-learning-track","title":"PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking","date":"2022-05-18","arxiv_id":"2205.11245","n_code_links":0,"syntology":null},{"paper":null,"slug":"m6-rec-generative-pretrained-language-models","title":"M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems","date":"2022-05-17","arxiv_id":"2205.08084","n_code_links":0,"syntology":null},{"paper":null,"slug":"skill-structured-knowledge-infusion-for-large","title":"SKILL: Structured Knowledge Infusion for Large Language Models","date":"2022-05-17","arxiv_id":"2205.08184","n_code_links":0,"syntology":null},{"paper":"/paper/downstream-transformer-generation-of-question","slug":"downstream-transformer-generation-of-question","title":"Downstream Transformer Generation of Question-Answer Pairs with Preprocessing and Postprocessing Pipelines","date":"2022-05-15","arxiv_id":"2205.07387","n_code_links":1,"syntology":null},{"paper":"/paper/rasat-integrating-relational-structures-into","slug":"rasat-integrating-relational-structures-into","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","date":"2022-05-14","arxiv_id":"2205.06983","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":1,"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) · 4 unverified","official":{"repos":["lumia-group/rasat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","n_code_links":2,"syntology":{"ran":15,"of":16,"n_ran_checked":15,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 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":"vector-representations-of-idioms-in","title":"Vector Representations of Idioms in Conversational Systems","date":"2022-05-07","arxiv_id":"2205.03666","n_code_links":0,"syntology":null},{"paper":"/paper/two-new-datasets-for-italian-language","slug":"two-new-datasets-for-italian-language","title":"Two New Datasets for Italian-Language Abstractive Text Summarization","date":"2022-04-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/modern-baselines-for-sparql-semantic-parsing","slug":"modern-baselines-for-sparql-semantic-parsing","title":"Modern Baselines for SPARQL Semantic Parsing","date":"2022-04-27","arxiv_id":"2204.12793","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-arabic-sentence-simplification-via","title":"Towards Arabic Sentence Simplification via Classification and Generative Approaches","date":"2022-04-20","arxiv_id":"2204.09292","n_code_links":0,"syntology":null},{"paper":"/paper/massive-a-1m-example-multilingual-natural","slug":"massive-a-1m-example-multilingual-natural","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","date":"2022-04-18","arxiv_id":"2204.08582","n_code_links":6,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alexa/massive"],"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":["listed","official"]}}},{"paper":null,"slug":"wordalchemy-a-transformer-based-reverse","title":"WordAlchemy: A transformer-based Reverse Dictionary","date":"2022-04-16","arxiv_id":"2204.10181","n_code_links":0,"syntology":null},{"paper":null,"slug":"ml-ltu-at-semeval-2022-task-4-t5-towards","title":"ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language","date":"2022-04-15","arxiv_id":"2204.07432","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-markovian-generative-architectures","slug":"revisiting-markovian-generative-architectures","title":"Building Markovian Generative Architectures over Pretrained LM Backbones for Efficient Task-Oriented Dialog Systems","date":"2022-04-13","arxiv_id":"2204.06452","n_code_links":2,"syntology":null},{"paper":"/paper/enhance-incomplete-utterance-restoration-by","slug":"enhance-incomplete-utterance-restoration-by","title":"Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation","date":"2022-04-08","arxiv_id":"2204.03958","n_code_links":1,"syntology":null},{"paper":"/paper/mmtafrica-multilingual-machine-translation-1","slug":"mmtafrica-multilingual-machine-translation-1","title":"MMTAfrica: Multilingual Machine Translation for African Languages","date":"2022-04-08","arxiv_id":"2204.04306","n_code_links":1,"syntology":null},{"paper":"/paper/byt5-model-for-massively-multilingual","slug":"byt5-model-for-massively-multilingual","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","date":"2022-04-06","arxiv_id":"2204.03067","n_code_links":1,"syntology":null},{"paper":"/paper/example-based-hypernetworks-for-out-of","slug":"example-based-hypernetworks-for-out-of","title":"Example-based Hypernetworks for Out-of-Distribution Generalization","date":"2022-03-27","arxiv_id":"2203.14276","n_code_links":1,"syntology":null},{"paper":"/paper/ensembling-and-knowledge-distilling-of-large-1","slug":"ensembling-and-knowledge-distilling-of-large-1","title":"Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction","date":"2022-03-24","arxiv_id":"2203.13064","n_code_links":1,"syntology":null},{"paper":"/paper/recommendation-as-language-processing-rlp-a","slug":"recommendation-as-language-processing-rlp-a","title":"Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)","date":"2022-03-24","arxiv_id":"2203.13366","n_code_links":2,"syntology":null},{"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/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/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/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/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":"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":"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":"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":"/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":"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":"/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}],"record_sha256":"236a1d441dc67466ff16cc43f3c23ec486f2a5bdd8882f29f645e3f53134deca","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}