{"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/seq2seq/papers/3","list_of":"/method/seq2seq","method":"Seq2Seq","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":3,"pages_in_order":7,"rows_per_page":100,"rows":[201,300],"of":700,"counts":{"archive_papers_tagged":700,"with_a_code_link":318,"where_syntology_ran_a_sample":68,"not_listed_spam_title":0,"listed":700,"listed_where_code_ran":68,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":59,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":59,"listed_every_run_a_failure_of_syntologys_instrument":9,"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/seq2seq","prev":"/method/seq2seq/papers/2","next":"/method/seq2seq/papers/4","papers":[{"paper":null,"slug":"mqretnn-multi-horizon-time-series-forecasting","title":"MQRetNN: Multi-Horizon Time Series Forecasting with Retrieval Augmentation","date":"2022-07-21","arxiv_id":"2207.10517","n_code_links":0,"syntology":null},{"paper":"/paper/a-general-contextualized-rewriting-framework","slug":"a-general-contextualized-rewriting-framework","title":"A General Contextualized Rewriting Framework for Text Summarization","date":"2022-07-13","arxiv_id":"2207.05948","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowda-all-in-one-knowledge-mixture-model-for","title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","date":"2022-06-21","arxiv_id":"2206.10265","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-generation-with-text-editing-models","title":"Text Generation with Text-Editing Models","date":"2022-06-14","arxiv_id":"2206.07043","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-in-social-media-an-approach-to","title":"Grounding in social media: An approach to building a chit-chat dialogue model","date":"2022-06-12","arxiv_id":"2206.05696","n_code_links":0,"syntology":null},{"paper":null,"slug":"mmtm-multi-tasking-multi-decoder-transformer","title":"MMTM: Multi-Tasking Multi-Decoder Transformer for Math Word Problems","date":"2022-06-02","arxiv_id":"2206.01268","n_code_links":0,"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":"/paper/the-impact-of-memory-on-learning-sequence-to","slug":"the-impact-of-memory-on-learning-sequence-to","title":"The impact of memory on learning sequence-to-sequence tasks","date":"2022-05-29","arxiv_id":"2205.14683","n_code_links":1,"syntology":null},{"paper":null,"slug":"clinical-dialogue-transcription-error","title":"Clinical Dialogue Transcription Error Correction using Seq2Seq Models","date":"2022-05-26","arxiv_id":"2205.13572","n_code_links":0,"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":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/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":null,"slug":"sequence-to-action-grammatical-error","title":"Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generation","date":"2022-05-22","arxiv_id":"2205.10884","n_code_links":0,"syntology":null},{"paper":"/paper/lossless-acceleration-for-seq2seq-generation","slug":"lossless-acceleration-for-seq2seq-generation","title":"Lossless Acceleration for Seq2seq Generation with Aggressive Decoding","date":"2022-05-20","arxiv_id":"2205.10350","n_code_links":2,"syntology":null},{"paper":"/paper/lagr-label-aligned-graphs-for-better-2","slug":"lagr-label-aligned-graphs-for-better-2","title":"LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing","date":"2022-05-19","arxiv_id":"2205.09607","n_code_links":1,"syntology":null},{"paper":null,"slug":"it-isn-t-sh-tposting-it-s-my-cat-posting","title":"It Isn't Sh!tposting, It's My CAT Posting","date":"2022-05-18","arxiv_id":"2205.08710","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-alignment-bias-in-neural-seq2seq","slug":"measuring-alignment-bias-in-neural-seq2seq","title":"Measuring Alignment Bias in Neural Seq2Seq Semantic Parsers","date":"2022-05-17","arxiv_id":"2205.08288","n_code_links":1,"syntology":null},{"paper":null,"slug":"tackling-math-word-problems-with-fine-to","title":"Tackling Math Word Problems with Fine-to-Coarse Abstracting and Reasoning","date":"2022-05-17","arxiv_id":"2205.08274","n_code_links":0,"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":null,"slug":"open-vocabulary-extreme-classification-using","title":"Open Vocabulary Extreme Classification Using Generative Models","date":"2022-05-12","arxiv_id":"2205.05812","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-cause-and-effect-relationships-of","title":"Identifying Cause-and-Effect Relationships of Manufacturing Errors using Sequence-to-Sequence Learning","date":"2022-05-05","arxiv_id":"2205.02827","n_code_links":0,"syntology":null},{"paper":"/paper/compositional-task-oriented-parsing-as","slug":"compositional-task-oriented-parsing-as","title":"Compositional Task-Oriented Parsing as Abstractive Question Answering","date":"2022-05-04","arxiv_id":"2205.02068","n_code_links":1,"syntology":null},{"paper":"/paper/training-naturalized-semantic-parsers-with","slug":"training-naturalized-semantic-parsers-with","title":"Training Naturalized Semantic Parsers with Very Little Data","date":"2022-04-29","arxiv_id":"2204.14243","n_code_links":1,"syntology":null},{"paper":null,"slug":"g-2-enhance-knowledge-grounded-dialogue-via","title":"Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modeling","date":"2022-04-27","arxiv_id":"2204.12681","n_code_links":0,"syntology":null},{"paper":"/paper/dialogue-meaning-representation-for-task","slug":"dialogue-meaning-representation-for-task","title":"Dialogue Meaning Representation for Task-Oriented Dialogue Systems","date":"2022-04-23","arxiv_id":"2204.10989","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":null,"slug":"pict-dravidianlangtech-acl2022-neural-machine","title":"PICT@DravidianLangTech-ACL2022: Neural Machine Translation On Dravidian Languages","date":"2022-04-19","arxiv_id":"2204.09098","n_code_links":0,"syntology":null},{"paper":null,"slug":"itakuroso-exploiting-cross-lingual","title":"AfriWOZ: Corpus for Exploiting Cross-Lingual Transferability for Generation of Dialogues in Low-Resource, African Languages","date":"2022-04-17","arxiv_id":"2204.08083","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-cross-lingual-gaps-during-leveraging","slug":"bridging-cross-lingual-gaps-during-leveraging","title":"Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding","date":"2022-04-16","arxiv_id":"2204.07834","n_code_links":1,"syntology":null},{"paper":null,"slug":"strata-word-boundaries-phoneme-recognition","title":"STRATA: Word Boundaries & Phoneme Recognition From Continuous Urdu Speech using Transfer Learning, Attention, & Data Augmentation","date":"2022-04-16","arxiv_id":"2204.07848","n_code_links":0,"syntology":null},{"paper":null,"slug":"survival-seq2seq-a-survival-model-based-on","title":"Survival Seq2Seq: A Survival Model based on Sequence to Sequence Architecture","date":"2022-04-09","arxiv_id":"2204.04542","n_code_links":0,"syntology":null},{"paper":"/paper/grounding-hindsight-instructions-in-multi","slug":"grounding-hindsight-instructions-in-multi","title":"Grounding Hindsight Instructions in Multi-Goal Reinforcement Learning for Robotics","date":"2022-04-08","arxiv_id":"2204.04308","n_code_links":2,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["knowledgetechnologyuhh/hipss"],"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":null,"slug":"show-don-t-tell-demonstrations-outperform-1","title":"Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue","date":"2022-04-08","arxiv_id":"2204.04327","n_code_links":0,"syntology":null},{"paper":null,"slug":"quick-starting-dialog-systems-with-paraphrase","title":"Quick Starting Dialog Systems with Paraphrase Generation","date":"2022-04-06","arxiv_id":"2204.02546","n_code_links":0,"syntology":null},{"paper":"/paper/a-sequence-to-sequence-approach-for-document","slug":"a-sequence-to-sequence-approach-for-document","title":"A sequence-to-sequence approach for document-level relation extraction","date":"2022-04-03","arxiv_id":"2204.01098","n_code_links":2,"syntology":null},{"paper":"/paper/metaphorical-user-simulators-for-evaluating","slug":"metaphorical-user-simulators-for-evaluating","title":"Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems","date":"2022-04-02","arxiv_id":"2204.00763","n_code_links":2,"syntology":{"ran":7,"of":9,"n_ran_checked":4,"n_instrument":3,"unverified":2,"pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["superbooming/simtester","sunnweiwei/metasim"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/lossless-speedup-of-autoregressive","slug":"lossless-speedup-of-autoregressive","title":"Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation","date":"2022-03-30","arxiv_id":"2203.16487","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hemingkx/gad","hemingkx/specdec"],"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":["community","official","unlocated"]}}},{"paper":"/paper/towards-few-shot-entity-recognition-in-1","slug":"towards-few-shot-entity-recognition-in-1","title":"Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework","date":"2022-03-30","arxiv_id":"2204.05819","n_code_links":1,"syntology":null},{"paper":"/paper/few-shot-named-entity-recognition-with-self","slug":"few-shot-named-entity-recognition-with-self","title":"Few-shot Named Entity Recognition with Self-describing Networks","date":"2022-03-23","arxiv_id":"2203.12252","n_code_links":1,"syntology":null},{"paper":null,"slug":"mitigating-gender-bias-in-machine-translation-2","title":"Mitigating Gender Bias in Machine Translation through Adversarial Learning","date":"2022-03-20","arxiv_id":"2203.10675","n_code_links":0,"syntology":null},{"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/multilingual-pre-training-with-language-and-1","slug":"multilingual-pre-training-with-language-and-1","title":"Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer","date":"2022-03-16","arxiv_id":"2203.08552","n_code_links":1,"syntology":null},{"paper":null,"slug":"transforming-sequence-tagging-into-a-seq2seq","title":"Transforming Sequence Tagging Into A Seq2Seq Task","date":"2022-03-16","arxiv_id":"2203.08378","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-and-improving-sequence-to-1","title":"Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation","date":"2022-03-16","arxiv_id":"2203.08442","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-evaluation-of-answer-agnostic","slug":"on-the-evaluation-of-answer-agnostic","title":"On the Evaluation of Answer-Agnostic Paragraph-level Multi-Question Generation","date":"2022-03-09","arxiv_id":"2203.04464","n_code_links":1,"syntology":null},{"paper":"/paper/lane-detection-with-versatile-atrousformer","slug":"lane-detection-with-versatile-atrousformer","title":"Lane Detection with Versatile AtrousFormer and Local Semantic Guidance","date":"2022-03-08","arxiv_id":"2203.04067","n_code_links":0,"syntology":null},{"paper":"/paper/ecmg-exemplar-based-commit-message-generation","slug":"ecmg-exemplar-based-commit-message-generation","title":"RACE: Retrieval-Augmented Commit Message Generation","date":"2022-03-05","arxiv_id":"2203.02700","n_code_links":2,"syntology":null},{"paper":"/paper/the-impact-of-lexical-and-grammatical-1","slug":"the-impact-of-lexical-and-grammatical-1","title":"The impact of lexical and grammatical processing on generating code from natural language","date":"2022-02-28","arxiv_id":"2202.13972","n_code_links":2,"syntology":null},{"paper":null,"slug":"compositional-generalization-requires-1","title":"Compositional Generalization Requires Compositional Parsers","date":"2022-02-24","arxiv_id":"2202.11937","n_code_links":0,"syntology":null},{"paper":"/paper/edgeformer-a-parameter-efficient-transformer","slug":"edgeformer-a-parameter-efficient-transformer","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","date":"2022-02-16","arxiv_id":"2202.07959","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":["microsoft/unilm"],"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":["found_in_text"]}}},{"paper":null,"slug":"benchmarking-online-sequence-to-sequence-and","title":"Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens","date":"2022-02-14","arxiv_id":"2202.07036","n_code_links":0,"syntology":null},{"paper":null,"slug":"correcting-diacritics-and-typos-with-byt5","title":"Correcting diacritics and typos with a ByT5 transformer model","date":"2022-01-31","arxiv_id":"2201.13242","n_code_links":0,"syntology":null},{"paper":null,"slug":"recursive-decoding-a-situated-cognition","title":"Recursive Decoding: A Situated Cognition Approach to Compositional Generation in Grounded Language Understanding","date":"2022-01-27","arxiv_id":"2201.11766","n_code_links":0,"syntology":null},{"paper":null,"slug":"focus-driven-contrastive-learning-for-medical","title":"Focus-Driven Contrastive Learning for Medical Question Summarization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transferring-knowledge-from-structure-aware","title":"Transferring Knowledge from Structure-aware Self-attention Language Model to Sequence-to-Sequence Semantic Parsing","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-a-generic-sequence-to-sequence-model","title":"Applying a Generic Sequence-to-Sequence Model for Simple and Effective Keyphrase Generation","date":"2022-01-14","arxiv_id":"2201.05302","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-and-few-shot-classification-of","title":"Zero-Shot and Few-Shot Classification of Biomedical Articles in Context of the COVID-19 Pandemic","date":"2022-01-09","arxiv_id":"2201.03017","n_code_links":0,"syntology":null},{"paper":"/paper/continuous-offline-handwriting-recognition","slug":"continuous-offline-handwriting-recognition","title":"Continuous Offline Handwriting Recognition using Deep Learning Models","date":"2021-12-26","arxiv_id":"2112.13328","n_code_links":1,"syntology":null},{"paper":null,"slug":"iterative-decoding-for-compositional-1","title":"Iterative Decoding for Compositional Generalization in Transformers","date":"2021-12-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-level-self-learning-with-multiple","title":"Sequence-level self-learning with multiple hypotheses","date":"2021-12-10","arxiv_id":"2112.05826","n_code_links":0,"syntology":null},{"paper":"/paper/spinning-language-models-for-propaganda-as-a","slug":"spinning-language-models-for-propaganda-as-a","title":"Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures","date":"2021-12-09","arxiv_id":"2112.05224","n_code_links":1,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ebagdasa/propaganda_as_a_service"],"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":null,"slug":"data-processing-matters-srph-konvergen-ai-s","title":"Data Processing Matters: SRPH-Konvergen AI's Machine Translation System for WMT'21","date":"2021-11-20","arxiv_id":"2111.10513","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-non-stationary-time-series-with","title":"Learning Non-Stationary Time-Series with Dynamic Pattern Extractions","date":"2021-11-20","arxiv_id":"2111.10559","n_code_links":0,"syntology":null},{"paper":null,"slug":"ufo-a-unified-transformer-for-vision-language","title":"UFO: A UniFied TransfOrmer for Vision-Language Representation Learning","date":"2021-11-19","arxiv_id":"2111.10023","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-neural-approach-to-kgqa-via-sparql","title":"A Neural Approach to KGQA via SPARQL Silhouette Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-simple-hash-based-early-exiting-approach","title":"A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation","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":"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":"how-do-seq2seq-models-perform-on-end-to-end","title":"How Do Seq2Seq Models Perform on End-to-End Data-to-Text Generation?","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lagr-label-aligned-graphs-for-better","title":"LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-uni-modal-self-supervised-learning","title":"Leveraging Uni-Modal Self-Supervised Learning for Multimodal Audio-visual Speech Recognition","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-gender-bias-in-machine-translation-1","title":"Mitigating Gender Bias in Machine Translation through Adversarial Learning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-pre-training-with-language-and","title":"Multilingual pre-training with Language and Task Adaptation for Multilingual Text Style Transfer","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"text-to-table-a-new-way-of-information-1","title":"Text-to-Table: A New Way of Information Extraction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-lexical-and-grammatical","title":"The impact of lexical and grammatical processing on generating code from natural language","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-asking-clarification-questions-in","title":"Towards Asking Clarification Questions in Task-Oriented Dialogue","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-few-shot-entity-recognition-in","title":"Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-and-improving-sequence-to","title":"Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-bengali-chatbot-using","title":"Transformer Based Bengali Chatbot Using General Knowledge Dataset","date":"2021-11-06","arxiv_id":"2111.03937","n_code_links":0,"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":null,"slug":"text-classification-for-task-based-source","title":"Text Classification for Task-based Source Code Related Questions","date":"2021-10-31","arxiv_id":"2111.00580","n_code_links":0,"syntology":null},{"paper":"/paper/rebel-relation-extraction-by-end-to-end","slug":"rebel-relation-extraction-by-end-to-end","title":"REBEL: Relation Extraction By End-to-end Language generation","date":"2021-10-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"mixseq-connecting-macroscopic-time-series","title":"MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data","date":"2021-10-27","arxiv_id":"2110.14354","n_code_links":0,"syntology":null},{"paper":"/paper/improving-non-autoregressive-generation-with","slug":"improving-non-autoregressive-generation-with","title":"Improving Non-autoregressive Generation with Mixup Training","date":"2021-10-21","arxiv_id":"2110.11115","n_code_links":1,"syntology":null},{"paper":"/paper/controllable-semantic-parsing-via-retrieval","slug":"controllable-semantic-parsing-via-retrieval","title":"Controllable Semantic Parsing via Retrieval Augmentation","date":"2021-10-16","arxiv_id":"2110.08458","n_code_links":1,"syntology":null},{"paper":"/paper/lagr-labeling-aligned-graphs-for-improving","slug":"lagr-labeling-aligned-graphs-for-improving","title":"LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing","date":"2021-10-14","arxiv_id":"2110.07572","n_code_links":1,"syntology":null},{"paper":"/paper/solving-aspect-category-sentiment-analysis-as","slug":"solving-aspect-category-sentiment-analysis-as","title":"Solving Aspect Category Sentiment Analysis as a Text Generation Task","date":"2021-10-14","arxiv_id":"2110.07310","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-follow-language-instructions-with","title":"Learning to Follow Language Instructions with Compositional Policies","date":"2021-10-09","arxiv_id":"2110.04647","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-decoding-for-compositional","title":"Iterative Decoding for Compositional Generalization in Transformers","date":"2021-10-08","arxiv_id":"2110.04169","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-character-tagger-for-short-text","title":"Hierarchical Character Tagger for Short Text Spelling Error Correction","date":"2021-09-29","arxiv_id":"2109.14259","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-fact-linking","slug":"multilingual-fact-linking","title":"Multilingual Fact Linking","date":"2021-09-29","arxiv_id":"2109.14364","n_code_links":1,"syntology":null},{"paper":null,"slug":"naspy-automated-extraction-of-automated","title":"NASPY: Automated Extraction of Automated Machine Learning Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sketchode-learning-neural-sketch","title":"SketchODE: Learning neural sketch representation in continuous time","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"variational-component-decoder-for-source","title":"Variational Component Decoder for Source Extraction from Nonlinear Mixture","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"biocopy-a-plug-and-play-span-copy-mechanism","title":"BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Models","date":"2021-09-26","arxiv_id":"2109.12533","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-latent-space-clustering-in-multi","title":"Self-Enhancing Multi-filter Sequence-to-Sequence Model","date":"2021-09-25","arxiv_id":"2109.12399","n_code_links":0,"syntology":null},{"paper":null,"slug":"smart-home-energy-management-sequence-to","title":"Smart Home Energy Management: Sequence-to-Sequence Load Forecasting and Q-Learning","date":"2021-09-25","arxiv_id":"2109.12440","n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-dialogue-generation-with","title":"Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward","date":"2021-09-14","arxiv_id":"2109.06717","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-premise-generation-with-discourse","slug":"implicit-premise-generation-with-discourse","title":"Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models","date":"2021-09-11","arxiv_id":"2109.05358","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-translation-via-grafting-pre","slug":"multilingual-translation-via-grafting-pre","title":"Multilingual Translation via Grafting Pre-trained Language Models","date":"2021-09-11","arxiv_id":"2109.05256","n_code_links":1,"syntology":null}],"record_sha256":"79897efcd4eb34030f55d2555ab61eb897ed2a0857d9307675e4f5bade5919c2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}