{"url":"/method/seq2edits","slug":"seq2edits","name":"Seq2Edits","full_name":"Seq2Edits","full_name_withheld":false,"description_markdown":"**Seq2Edits** is an open-vocabulary approach to sequence editing for natural language processing (NLP) tasks with a high degree of overlap between input and output texts. In this approach, each sequence-to-sequence transduction is represented as a sequence of edit operations, where each operation either replaces an entire source span with target tokens or keeps it unchanged. For text normalization, sentence fusion, sentence splitting & rephrasing, text simplification, and grammatical error correction, the approach improves explainability by associating each edit operation with a human-readable tag.\r\n\r\nRather than generating the target sentence as a series of tokens, the model predicts a sequence of edit operations that, when applied to the source sentence, yields the target sentence. Each edit operates on a span in the source sentence and either copies, deletes, or replaces it with one or more target tokens. Edits are generated auto-regressively from left to right using a modified [Transformer](https://paperswithcode.com/method/transformer) architecture to facilitate learning of long-range dependencies.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Seq2Edits: Sequence Transduction Using Span-level Edit Operations","paper":"/paper/seq2edits-sequence-transduction-using-span","first_author":"Felix Stahlberg","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/seq2edits-sequence-transduction-using-span"},"source":{"url":"https://arxiv.org/abs/2009.11136v1","title":"Seq2Edits: Sequence Transduction Using Span-level Edit Operations","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":"Sequence Editing Models","url":"/methods/category/sequence-editing-models","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/seq2edits-sequence-transduction-using-span","title":"Seq2Edits: Sequence Transduction Using Span-level Edit Operations","date":"2020-09-23","arxiv_id":"2009.11136","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/grammatical-error-correction","name":"Grammatical Error Correction","papers":1},{"task":"/task/sentence","name":"Sentence","papers":1},{"task":"/task/sentence-fusion","name":"Sentence Fusion","papers":1},{"task":"/task/tag","name":"TAG","papers":1},{"task":"/task/text-normalization","name":"Text Normalization","papers":1},{"task":"/task/text-simplification","name":"Text Simplification","papers":1}],"tasks_shown":6,"n_tasks":6,"usage_by_year":[{"year":"2020","papers":1}],"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/seq2edits"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}