{"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","slug":"seq2seq","name":"Seq2Seq","full_name":"Sequence to Sequence","full_name_withheld":false,"description_markdown":"**Seq2Seq**, or **Sequence To Sequence**, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one [LSTM](https://paperswithcode.com/method/lstm), the *encoder*, to read the input sequence one timestep at a time, to obtain a large fixed dimensional vector representation (a context vector), and then to use another LSTM, the *decoder*, to extract the output sequence\r\nfrom that vector. The second LSTM is essentially a recurrent neural network language model except that it is conditioned on the input sequence.\r\n\r\n(Note that this page refers to the original seq2seq not general sequence-to-sequence models)","description_state":"present","introduced_year":null,"introduced_by":{"title":"Sequence to Sequence Learning with Neural Networks","paper":"/paper/sequence-to-sequence-learning-with-neural","first_author":"Ilya Sutskever","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/sequence-to-sequence-learning-with-neural"},"source":{"url":"http://arxiv.org/abs/1409.3215v3","title":"Sequence to Sequence Learning with Neural Networks","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Machine Translation Models","url":"/methods/category/machine-translation-models","pwc_aliases":[]},{"area":"Sequential","area_id":"sequential","collection":"Sequence To Sequence Models","url":"/methods/category/sequence-to-sequence-models","pwc_aliases":[]}],"n_papers_tagged":700,"archive_num_papers":700,"papers_newest_first":[{"paper":"/paper/cove-compressed-vocabulary-expansion-makes","slug":"cove-compressed-vocabulary-expansion-makes","title":"CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems","date":"2025-06-24","arxiv_id":"2506.19993","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["haochenzhang717/cove-official-repo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-speaker-diarization-with-mixture-of","title":"Exploring Speaker Diarization with Mixture of Experts","date":"2025-06-17","arxiv_id":"2506.14750","n_code_links":0,"syntology":null},{"paper":null,"slug":"transforming-chatbot-text-a-sequence-to","title":"Transforming Chatbot Text: A Sequence-to-Sequence Approach","date":"2025-06-15","arxiv_id":"2506.12843","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-bangla-linguistics-advanced-lstm-bi","title":"Improving Bangla Linguistics: Advanced LSTM, Bi-LSTM, and Seq2Seq Models for Translating Sylheti to Modern Bangla","date":"2025-05-24","arxiv_id":"2505.18709","n_code_links":0,"syntology":null},{"paper":null,"slug":"dense-communication-between-language-models","title":"Dense Communication between Language Models","date":"2025-05-19","arxiv_id":"2505.12741","n_code_links":0,"syntology":null},{"paper":"/paper/diverse-in-context-example-selection-after","slug":"diverse-in-context-example-selection-after","title":"Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsing","date":"2025-04-04","arxiv_id":"2504.03541","n_code_links":1,"syntology":null},{"paper":null,"slug":"non-monotonic-attention-based-read-write","title":"Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation","date":"2025-03-28","arxiv_id":"2503.22051","n_code_links":0,"syntology":null},{"paper":"/paper/minimal-time-series-transformer","slug":"minimal-time-series-transformer","title":"Minimal Time Series Transformer","date":"2025-03-12","arxiv_id":"2503.09791","n_code_links":1,"syntology":null},{"paper":null,"slug":"controllablegpt-a-ground-up-designed","title":"ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization","date":"2025-02-15","arxiv_id":"2502.10631","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-differentiable-alignment-framework-for","title":"A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport","date":"2025-02-03","arxiv_id":"2502.01588","n_code_links":0,"syntology":null},{"paper":"/paper/cove-context-and-veracity-prediction-for-out","slug":"cove-context-and-veracity-prediction-for-out","title":"COVE: COntext and VEracity prediction for out-of-context images","date":"2025-02-03","arxiv_id":"2502.01194","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ukplab/naacl2025-cove"],"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":null,"slug":"development-of-an-inclusive-educational","title":"Development of an Inclusive Educational Platform Using Open Technologies and Machine Learning: A Case Study on Accessibility Enhancement","date":"2025-01-22","arxiv_id":"2503.15501","n_code_links":0,"syntology":null},{"paper":"/paper/a-diversity-enhanced-knowledge-distillation","slug":"a-diversity-enhanced-knowledge-distillation","title":"A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving","date":"2025-01-07","arxiv_id":"2501.03670","n_code_links":1,"syntology":null},{"paper":"/paper/afrihg-news-headline-generation-for-african","slug":"afrihg-news-headline-generation-for-african","title":"AfriHG: News headline generation for African Languages","date":"2024-12-28","arxiv_id":"2412.20223","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dadelani/AfriHG"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"seq2seq-model-based-chatbot-with-lstm-and","title":"Seq2Seq Model-Based Chatbot with LSTM and Attention Mechanism for Enhanced User Interaction","date":"2024-12-27","arxiv_id":"2501.00049","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusionattacker-diffusion-driven-prompt","title":"DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak","date":"2024-12-23","arxiv_id":"2412.17522","n_code_links":0,"syntology":null},{"paper":"/paper/compositional-generalization-across","slug":"compositional-generalization-across","title":"Compositional Generalization Across Distributional Shifts with Sparse Tree Operations","date":"2024-12-18","arxiv_id":"2412.14076","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-role-of-surrogates-in-conformal","slug":"on-the-role-of-surrogates-in-conformal","title":"On the Role of Surrogates in Conformal Inference of Individual Causal Effects","date":"2024-12-16","arxiv_id":"2412.12365","n_code_links":1,"syntology":null},{"paper":"/paper/fedpaw-federated-learning-with-personalized","slug":"fedpaw-federated-learning-with-personalized","title":"FedPAW: Federated Learning with Personalized Aggregation Weights for Urban Vehicle Speed Prediction","date":"2024-12-02","arxiv_id":"2412.01281","n_code_links":1,"syntology":null},{"paper":"/paper/nushurescue-revitalization-of-the-endangered","slug":"nushurescue-revitalization-of-the-endangered","title":"NushuRescue: Revitalization of the Endangered Nushu Language with AI","date":"2024-11-29","arxiv_id":"2412.00218","n_code_links":1,"syntology":null},{"paper":null,"slug":"ezsql-an-sql-intermediate-representation-for","title":"EzSQL: An SQL intermediate representation for improving SQL-to-text Generation","date":"2024-11-28","arxiv_id":"2411.18923","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-machine-translation-with-a-bilstm","slug":"efficient-machine-translation-with-a-bilstm","title":"Efficient Machine Translation with a BiLSTM-Attention Approach","date":"2024-10-29","arxiv_id":"2410.22335","n_code_links":2,"syntology":null},{"paper":null,"slug":"melody-construction-for-persian-lyrics-using","title":"Melody Construction for Persian lyrics using LSTM recurrent neural networks","date":"2024-10-23","arxiv_id":"2410.18203","n_code_links":0,"syntology":null},{"paper":"/paper/multi-head-sequence-tagging-model-for","slug":"multi-head-sequence-tagging-model-for","title":"Multi-head Sequence Tagging Model for Grammatical Error Correction","date":"2024-10-21","arxiv_id":"2410.16473","n_code_links":2,"syntology":null},{"paper":"/paper/meta-diffub-a-contextualized-sequence-to","slug":"meta-diffub-a-contextualized-sequence-to","title":"Meta-DiffuB: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration","date":"2024-10-17","arxiv_id":"2410.13201","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-real-time-fluorescence-lifetime","title":"Unlocking Real-Time Fluorescence Lifetime Imaging: Multi-Pixel Parallelism for FPGA-Accelerated Processing","date":"2024-10-09","arxiv_id":"2410.07364","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-parsing-with-candidate-expressions","slug":"semantic-parsing-with-candidate-expressions","title":"Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering","date":"2024-10-01","arxiv_id":"2410.00414","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-the-negative-impact-of-over","slug":"mitigating-the-negative-impact-of-over","title":"Mitigating the Negative Impact of Over-association for Conversational Query Production","date":"2024-09-29","arxiv_id":"2409.19572","n_code_links":1,"syntology":null},{"paper":null,"slug":"time-and-tokens-benchmarking-end-to-end","title":"Time and Tokens: Benchmarking End-to-End Speech Dysfluency Detection","date":"2024-09-20","arxiv_id":"2409.13582","n_code_links":0,"syntology":null},{"paper":null,"slug":"american-sign-language-to-text-translation","title":"American Sign Language to Text Translation using Transformer and Seq2Seq with LSTM","date":"2024-09-17","arxiv_id":"2409.10874","n_code_links":0,"syntology":null},{"paper":null,"slug":"acquiring-pronunciation-knowledge-from","title":"Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning","date":"2024-09-15","arxiv_id":"2409.09891","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-the-songwriting-process-genre","title":"Optimizing the Songwriting Process: Genre-Based Lyric Generation Using Deep Learning Models","date":"2024-09-15","arxiv_id":"2409.13758","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-text-to-cypher-using-combination-of","title":"Robust Text-to-Cypher Using Combination of BERT, GraphSAGE, and Transformer (CoBGT) Model","date":"2024-09-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-to-sequence-reward-modeling","title":"Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback","date":"2024-08-30","arxiv_id":"2409.00162","n_code_links":0,"syntology":null},{"paper":"/paper/positive-text-reframing-under-multi-strategy","slug":"positive-text-reframing-under-multi-strategy","title":"Positive Text Reframing under Multi-strategy Optimization","date":"2024-07-25","arxiv_id":"2407.17940","n_code_links":1,"syntology":null},{"paper":null,"slug":"ancient-korean-archive-translation-comparison","title":"Ancient Korean Archive Translation: Comparison Analysis on Statistical phrase alignment, LLM in-context learning, and inter-methodological approach","date":"2024-07-16","arxiv_id":"2407.11368","n_code_links":0,"syntology":null},{"paper":"/paper/reactaivate-a-deep-learning-approach-to","slug":"reactaivate-a-deep-learning-approach-to","title":"ReactAIvate: A Deep Learning Approach to Predicting Reaction Mechanisms and Unmasking Reactivity Hotspots","date":"2024-07-14","arxiv_id":"2407.10090","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-low-resource-nmt-with-a","title":"Enhancing Low-Resource NMT with a Multilingual Encoder and Knowledge Distillation: A Case Study","date":"2024-07-09","arxiv_id":"2407.06538","n_code_links":0,"syntology":null},{"paper":"/paper/strengthening-structural-inductive-biases-by","slug":"strengthening-structural-inductive-biases-by","title":"Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations","date":"2024-07-05","arxiv_id":"2407.04543","n_code_links":1,"syntology":null},{"paper":"/paper/scope-enhanced-compositional-semantic-parsing","slug":"scope-enhanced-compositional-semantic-parsing","title":"Scope-enhanced Compositional Semantic Parsing for DRT","date":"2024-07-02","arxiv_id":"2407.01899","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-correct-for-qa-reasoning-with","slug":"learning-to-correct-for-qa-reasoning-with","title":"Learning to Correct for QA Reasoning with Black-box LLMs","date":"2024-06-26","arxiv_id":"2406.18695","n_code_links":1,"syntology":null},{"paper":"/paper/cove-unleashing-the-diffusion-feature","slug":"cove-unleashing-the-diffusion-feature","title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","date":"2024-06-13","arxiv_id":"2406.08850","n_code_links":1,"syntology":null},{"paper":null,"slug":"robust-multi-modal-speech-in-painting-a","title":"Robust Multi-Modal Speech In-Painting: A Sequence-to-Sequence Approach","date":"2024-06-02","arxiv_id":"2406.00901","n_code_links":0,"syntology":null},{"paper":null,"slug":"asi-towards-distributionally-balanced-end-to","title":"ASI++: Towards Distributionally Balanced End-to-End Generative Retrieval","date":"2024-05-23","arxiv_id":"2405.14280","n_code_links":0,"syntology":null},{"paper":null,"slug":"signllm-sign-languages-production-large","title":"SignLLM: Sign Language Production Large Language Models","date":"2024-05-17","arxiv_id":"2405.10718","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-of-generative-techniques-for-spatial","title":"A Survey of Generative Techniques for Spatial-Temporal Data Mining","date":"2024-05-15","arxiv_id":"2405.09592","n_code_links":0,"syntology":null},{"paper":"/paper/araspell-a-deep-learning-approach-for-arabic","slug":"araspell-a-deep-learning-approach-for-arabic","title":"AraSpell: A Deep Learning Approach for Arabic Spelling Correction","date":"2024-05-11","arxiv_id":"2405.06981","n_code_links":1,"syntology":null},{"paper":null,"slug":"sequence-to-sequence-models-in-peer-to-peer","title":"Sequence-to-sequence models in peer-to-peer learning: A practical application","date":"2024-05-02","arxiv_id":"2406.02565","n_code_links":0,"syntology":null},{"paper":null,"slug":"gemquad-generating-multilingual-question","title":"GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning","date":"2024-04-14","arxiv_id":"2404.09163","n_code_links":0,"syntology":null},{"paper":"/paper/oovs-in-the-spotlight-how-to-inflect-them","slug":"oovs-in-the-spotlight-how-to-inflect-them","title":"OOVs in the Spotlight: How to Inflect them?","date":"2024-04-13","arxiv_id":"2404.08974","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-sequence-to-sequence-models-for","title":"Improving Sequence-to-Sequence Models for Abstractive Text Summarization Using Meta Heuristic Approaches","date":"2024-03-24","arxiv_id":"2403.16247","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-linguistically-enhanced-embeddings","title":"Leveraging Linguistically Enhanced Embeddings for Open Information Extraction","date":"2024-03-20","arxiv_id":"2403.13903","n_code_links":0,"syntology":null},{"paper":"/paper/intent-conditioned-and-non-toxic","slug":"intent-conditioned-and-non-toxic","title":"Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF","date":"2024-03-15","arxiv_id":"2403.10088","n_code_links":0,"syntology":{"ran":9,"of":10,"n_ran_checked":6,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 4 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"p2lhap-wearable-sensor-based-human-activity","title":"P2LHAP:Wearable sensor-based human activity recognition, segmentation and forecast through Patch-to-Label Seq2Seq Transformer","date":"2024-03-13","arxiv_id":"2403.08214","n_code_links":0,"syntology":null},{"paper":"/paper/spa-towards-a-computational-friendly-cloud","slug":"spa-towards-a-computational-friendly-cloud","title":"SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation with Casual Inference","date":"2024-03-11","arxiv_id":"2403.07088","n_code_links":1,"syntology":null},{"paper":null,"slug":"as-es-learning-towards-efficient-cot-learning","title":"AS-ES Learning: Towards Efficient CoT Learning in Small Models","date":"2024-03-04","arxiv_id":"2403.01969","n_code_links":0,"syntology":null},{"paper":"/paper/on-leveraging-encoder-only-pre-trained","slug":"on-leveraging-encoder-only-pre-trained","title":"On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generation","date":"2024-02-21","arxiv_id":"2402.14052","n_code_links":1,"syntology":null},{"paper":"/paper/internlm-math-open-math-large-language-models","slug":"internlm-math-open-math-large-language-models","title":"InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning","date":"2024-02-09","arxiv_id":"2402.06332","n_code_links":1,"syntology":null},{"paper":"/paper/alirector-alignment-enhanced-chinese","slug":"alirector-alignment-enhanced-chinese","title":"Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector","date":"2024-02-07","arxiv_id":"2402.04601","n_code_links":1,"syntology":null},{"paper":null,"slug":"aligner-achieving-efficient-alignment-through","title":"Aligner: Efficient Alignment by Learning to Correct","date":"2024-02-04","arxiv_id":"2402.02416","n_code_links":0,"syntology":null},{"paper":null,"slug":"lions-1-and-tigers-2-and-bears-3-oh-my","title":"[Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs","date":"2024-01-31","arxiv_id":"2401.17922","n_code_links":0,"syntology":null},{"paper":null,"slug":"maple-micro-analysis-of-pairwise-language","title":"MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification","date":"2024-01-29","arxiv_id":"2401.16282","n_code_links":0,"syntology":null},{"paper":"/paper/chem-finese-validating-fine-grained-few-shot-1","slug":"chem-finese-validating-fine-grained-few-shot-1","title":"Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction","date":"2024-01-18","arxiv_id":"2401.10189","n_code_links":1,"syntology":null},{"paper":null,"slug":"simple-and-effective-data-augmentation-for","title":"Simple and effective data augmentation for compositional generalization","date":"2024-01-18","arxiv_id":"2401.09815","n_code_links":0,"syntology":null},{"paper":"/paper/a-comprehensive-survey-of-hallucination","slug":"a-comprehensive-survey-of-hallucination","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","date":"2024-01-02","arxiv_id":"2401.01313","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"from-text-to-multimodal-a-comprehensive","title":"From text to multimodal: a survey of adversarial example generation in question answering systems","date":"2023-12-26","arxiv_id":"2312.16156","n_code_links":0,"syntology":null},{"paper":"/paper/data-generation-for-post-ocr-correction-of","slug":"data-generation-for-post-ocr-correction-of","title":"Data Generation for Post-OCR correction of Cyrillic handwriting","date":"2023-11-27","arxiv_id":"2311.15896","n_code_links":2,"syntology":null},{"paper":null,"slug":"untargeted-code-authorship-evasion-with","title":"Untargeted Code Authorship Evasion with Seq2Seq Transformation","date":"2023-11-26","arxiv_id":"2311.15366","n_code_links":0,"syntology":null},{"paper":null,"slug":"grammatical-error-correction-via-mixed","title":"Grammatical Error Correction via Mixed-Grained Weighted Training","date":"2023-11-23","arxiv_id":"2311.13848","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-textual-normalization-for-hate","slug":"automatic-textual-normalization-for-hate","title":"Automatic Textual Normalization for Hate Speech Detection","date":"2023-11-12","arxiv_id":"2311.06851","n_code_links":1,"syntology":null},{"paper":null,"slug":"legal-hnet-mixing-legal-long-context-tokens","title":"Legal-HNet: Mixing Legal Long-Context Tokens with Hartley Transform","date":"2023-11-09","arxiv_id":"2311.05089","n_code_links":0,"syntology":null},{"paper":"/paper/calibrated-seq2seq-models-for-efficient-and","slug":"calibrated-seq2seq-models-for-efficient-and","title":"Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity Typing","date":"2023-11-01","arxiv_id":"2311.00835","n_code_links":1,"syntology":null},{"paper":null,"slug":"s2f-ner-exploring-sequence-to-forest","title":"S2F-NER: Exploring Sequence-to-Forest Generation for Complex Entity Recognition","date":"2023-10-29","arxiv_id":"2310.18944","n_code_links":0,"syntology":null},{"paper":"/paper/improving-seq2seq-grammatical-error","slug":"improving-seq2seq-grammatical-error","title":"Improving Seq2Seq Grammatical Error Correction via Decoding Interventions","date":"2023-10-23","arxiv_id":"2310.14534","n_code_links":1,"syntology":null},{"paper":"/paper/qa-natver-question-answering-for-natural","slug":"qa-natver-question-answering-for-natural","title":"QA-NatVer: Question Answering for Natural Logic-based Fact Verification","date":"2023-10-22","arxiv_id":"2310.14198","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["raldir/qa-natver"],"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":"aita-generating-moral-judgements-of-the-crowd","title":"AITA Generating Moral Judgements of the Crowd with Reasoning","date":"2023-10-21","arxiv_id":"2310.18336","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-optimized-joint-generative-and","title":"Meta-optimized Joint Generative and Contrastive Learning for Sequential Recommendation","date":"2023-10-21","arxiv_id":"2310.13925","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-abstractiveness-of-summarization","title":"Enhancing Abstractiveness of Summarization Models through Calibrated Distillation","date":"2023-10-20","arxiv_id":"2310.13760","n_code_links":0,"syntology":null},{"paper":"/paper/seq2seq-is-all-you-need-for-coreference","slug":"seq2seq-is-all-you-need-for-coreference","title":"Seq2seq is All You Need for Coreference Resolution","date":"2023-10-20","arxiv_id":"2310.13774","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":10,"n_instrument":1,"unverified":3,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["wenzhengzhang/seq2seqcoref"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/non-autoregressive-text-editing-with-copy","slug":"non-autoregressive-text-editing-with-copy","title":"Non-autoregressive Text Editing with Copy-aware Latent Alignments","date":"2023-10-11","arxiv_id":"2310.07821","n_code_links":1,"syntology":null},{"paper":"/paper/cot3dref-chain-of-thoughts-data-efficient-3d","slug":"cot3dref-chain-of-thoughts-data-efficient-3d","title":"CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding","date":"2023-10-10","arxiv_id":"2310.06214","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eslambakr/CoT3D_VG"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"get-the-gist-using-large-language-models-for","title":"Get the gist? Using large language models for few-shot decontextualization","date":"2023-10-10","arxiv_id":"2310.06254","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-model-selection-and-decoding-for","slug":"rethinking-model-selection-and-decoding-for","title":"Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models","date":"2023-10-10","arxiv_id":"2310.06374","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-logiglue-a-brief-survey-and-a","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","date":"2023-10-02","arxiv_id":"2310.00836","n_code_links":0,"syntology":null},{"paper":"/paper/injecting-a-structural-inductive-bias-into-a","slug":"injecting-a-structural-inductive-bias-into-a","title":"SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation","date":"2023-10-01","arxiv_id":"2310.00796","n_code_links":1,"syntology":null},{"paper":"/paper/supersonic-learning-to-generate-source-code","slug":"supersonic-learning-to-generate-source-code","title":"Supersonic: Learning to Generate Source Code Optimizations in C/C++","date":"2023-09-26","arxiv_id":"2309.14846","n_code_links":1,"syntology":null},{"paper":"/paper/chain-of-verification-reduces-hallucination","slug":"chain-of-verification-reduces-hallucination","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","date":"2023-09-20","arxiv_id":"2309.11495","n_code_links":1,"syntology":null},{"paper":"/paper/openba-an-open-sourced-15b-bilingual","slug":"openba-an-open-sourced-15b-bilingual","title":"OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch","date":"2023-09-19","arxiv_id":"2309.10706","n_code_links":1,"syntology":null},{"paper":"/paper/glancing-future-for-simultaneous-machine","slug":"glancing-future-for-simultaneous-machine","title":"Glancing Future for Simultaneous Machine Translation","date":"2023-09-12","arxiv_id":"2309.06179","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["ictnlp/glance-simt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sage-structured-attribute-value-generation","title":"SAGE: Structured Attribute Value Generation for Billion-Scale Product Catalogs","date":"2023-09-12","arxiv_id":"2309.05920","n_code_links":0,"syntology":null},{"paper":"/paper/discrete-denoising-diffusion-approach-to","slug":"discrete-denoising-diffusion-approach-to","title":"Discrete Denoising Diffusion Approach to Integer Factorization","date":"2023-09-11","arxiv_id":"2309.05295","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-methods-for-ground-truth-free","slug":"evaluating-methods-for-ground-truth-free","title":"Evaluating Methods for Ground-Truth-Free Foreign Accent Conversion","date":"2023-09-05","arxiv_id":"2309.02133","n_code_links":2,"syntology":null},{"paper":"/paper/co-evolving-vector-quantization-for-id-based","slug":"co-evolving-vector-quantization-for-id-based","title":"Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector Quantization","date":"2023-08-31","arxiv_id":"2308.16761","n_code_links":2,"syntology":null},{"paper":"/paper/fully-embedded-time-series-generative","slug":"fully-embedded-time-series-generative","title":"Fully Embedded Time-Series Generative Adversarial Networks","date":"2023-08-30","arxiv_id":"2308.15730","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-variational-autoencoder-for","slug":"diffusion-variational-autoencoder-for","title":"Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction","date":"2023-08-18","arxiv_id":"2309.00073","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":9,"n_instrument":2,"unverified":3,"pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["koa-fin/dva"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploiting-the-potential-of-seq2seq-models-as","title":"Exploiting the Potential of Seq2Seq Models as Robust Few-Shot Learners","date":"2023-07-27","arxiv_id":"2307.14856","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-conversational-shaping-for","title":"Adversarial Conversational Shaping for Intelligent Agents","date":"2023-07-20","arxiv_id":"2307.11785","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-graph-for-nlg-in-the-context-of","title":"Knowledge Graph for NLG in the context of conversational agents","date":"2023-07-04","arxiv_id":"2307.01548","n_code_links":0,"syntology":null},{"paper":"/paper/transformed-protoform-reconstruction","slug":"transformed-protoform-reconstruction","title":"Transformed Protoform Reconstruction","date":"2023-07-04","arxiv_id":"2307.01896","n_code_links":1,"syntology":null},{"paper":"/paper/intercode-standardizing-and-benchmarking","slug":"intercode-standardizing-and-benchmarking","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","date":"2023-06-26","arxiv_id":"2306.14898","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["princeton-nlp/intercode"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_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":58,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":58,"listed_every_run_a_failure_of_syntologys_instrument":10,"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"},"papers_where_code_ran":68,"papers_where_code_ran_first_page":"/method/seq2seq/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":7,"url":"/method/seq2seq/papers/2","json":"/method/seq2seq/papers/2.json","rows":100},{"order":"archive","page":3,"of":7,"url":"/method/seq2seq/papers/3","json":"/method/seq2seq/papers/3.json","rows":100},{"order":"archive","page":4,"of":7,"url":"/method/seq2seq/papers/4","json":"/method/seq2seq/papers/4.json","rows":100},{"order":"archive","page":5,"of":7,"url":"/method/seq2seq/papers/5","json":"/method/seq2seq/papers/5.json","rows":100},{"order":"archive","page":6,"of":7,"url":"/method/seq2seq/papers/6","json":"/method/seq2seq/papers/6.json","rows":100},{"order":"archive","page":7,"of":7,"url":"/method/seq2seq/papers/7","json":"/method/seq2seq/papers/7.json","rows":100},{"order":"ran","page":1,"of":1,"url":"/method/seq2seq/papers/ran/1","json":"/method/seq2seq/papers/ran/1.json","rows":68}],"tasks":[{"task":"/task/machine-translation","name":"Machine Translation","papers":114},{"task":"/task/decoder","name":"Decoder","papers":111},{"task":"/task/translation","name":"Translation","papers":107},{"task":"/task/sentence","name":"Sentence","papers":96},{"task":"/task/text-generation","name":"Text Generation","papers":63},{"task":"/task/language-modelling","name":"Language Modelling","papers":61},{"task":"/task/language-modeling","name":"Language Modeling","papers":50},{"task":"/task/semantic-parsing","name":"Semantic Parsing","papers":50},{"task":"/task/speech-recognition","name":"Speech Recognition","papers":34},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":33},{"task":"/task/abstractive-text-summarization","name":"Abstractive Text Summarization","papers":32},{"task":"/task/question-answering","name":"Question Answering","papers":31},{"task":"/task/text-summarization","name":"Text Summarization","papers":30},{"task":"/task/diversity","name":"Diversity","papers":24},{"task":"/task/retrieval","name":"Retrieval","papers":24},{"task":"/task/response-generation","name":"Response Generation","papers":22},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":20},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":19},{"task":"/task/grammatical-error-correction","name":"Grammatical Error Correction","papers":18},{"task":"/task/nmt","name":"NMT","papers":18}],"tasks_shown":20,"n_tasks":453,"usage_by_year":[{"year":"2014","papers":1},{"year":"2015","papers":1},{"year":"2016","papers":11},{"year":"2017","papers":24},{"year":"2018","papers":78},{"year":"2019","papers":108},{"year":"2020","papers":104},{"year":"2021","papers":116},{"year":"2022","papers":103},{"year":"2023","papers":89},{"year":"2024","papers":52},{"year":"2025","papers":13}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/seq2seq"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Seq2Seq","read_at":"2026-10-05T01:01:49+00:00","query":"Seq2Seq","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1409.3215","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Seq2Seq' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["distilled LSTM-based seq2seq","seq2seq pre-training approach","Seq2Seq models for session-based parsing","seq2seq model with phraseness and informativeness module","SEQ2SEQ NLG approach with Syntactic Transformations (STs)"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"8e09fab0cca62f7aa6daf69432a6a68249944aa237d1795c355f382b7e4e6d54","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}