{"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","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":0,"of":4,"unverified":4,"pointer_only":4}},{"paper":null,"title":"Exploring Speaker Diarization with Mixture of Experts","date":"2025-06-17","arxiv_id":"2506.14750","n_code_links":0,"syntology":null},{"paper":null,"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,"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,"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","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,"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","title":"Minimal Time Series Transformer","date":"2025-03-12","arxiv_id":"2503.09791","n_code_links":1,"syntology":null},{"paper":null,"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,"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","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,"unverified":0,"pointer_only":0}},{"paper":null,"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","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","title":"AfriHG: News headline generation for African Languages","date":"2024-12-28","arxiv_id":"2412.20223","n_code_links":1,"syntology":{"ran":2,"of":5,"unverified":3,"pointer_only":0}},{"paper":null,"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,"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","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","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","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","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,"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","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,"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","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","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,"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","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","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,"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,"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}],"papers_shown":30,"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":"2026-09-24T18:15:14+00:00"}