Abstract
We propose Seq2Edits, 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. We evaluate our method on five NLP tasks (text normalization, sentence fusion, sentence splitting & rephrasing, text simplification, and grammatical error correction) and report competitive results across the board. For grammatical error correction, our method speeds up inference by up to 5.2x compared to full sequence models because inference time depends on the number of edits rather than the number of target tokens. For text normalization, sentence fusion, and grammatical error correction, our approach improves explainability by associating each edit operation with a human-readable tag.- Anthology ID:
- 2020.emnlp-main.418
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5147–5159
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.418
- DOI:
- 10.18653/v1/2020.emnlp-main.418
- Cite (ACL):
- Felix Stahlberg and Shankar Kumar. 2020. Seq2Edits: Sequence Transduction Using Span-level Edit Operations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5147–5159, Online. Association for Computational Linguistics.
- Cite (Informal):
- Seq2Edits: Sequence Transduction Using Span-level Edit Operations (Stahlberg & Kumar, EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.418.pdf
- Code
- tensorflow/tensor2tensor
- Data
- DiscoFuse, FCE, JFLEG, WikiLarge, WikiSplit