Projects per year
Abstract / Description of output
Sentence simplification aims to make sentences easier to read and understand. Recent approaches have shown promising results with encoder-decoder models trained on large amounts of parallel data which often only exists in English. We propose a zero-shot modeling framework which transfers simplification knowledge from English to another language (for which no parallel simplification corpus exists) while generalizing across languages and tasks. A shared transformer encoder constructs language-agnostic representations, with a combination of task-specific encoder layers added on top (e.g., for translation and simplification). Empirical results using both human and automatic metrics show that our approach produces better simplifications than unsupervised and pivot-based methods.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 5109-5126 |
Number of pages | 18 |
ISBN (Print) | 978-1-952148-60-6 |
DOIs | |
Publication status | Published - 16 Nov 2020 |
Event | The 2020 Conference on Empirical Methods in Natural Language Processing - Online Duration: 16 Nov 2020 → 20 Nov 2020 https://2020.emnlp.org/ |
Conference
Conference | The 2020 Conference on Empirical Methods in Natural Language Processing |
---|---|
Abbreviated title | EMNLP 2020 |
Period | 16/11/20 → 20/11/20 |
Internet address |
Fingerprint
Dive into the research topics of 'Zero-Shot Crosslingual Sentence Simplification'. Together they form a unique fingerprint.Projects
- 1 Finished