Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts
Article Status
Published
Authors/contributors
- Clark, Elizabeth (Author)
- Celikyilmaz, Asli (Author)
- Smith, Noah A. (Author)
Title
Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts
Proceedings Title
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Conference Name
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Publisher
Association for Computational Linguistics
Place
Florence, Italy
Date
2019
Pages
2748-2760
Citation Key
clark2019
Accessed
27/10/2023, 17:09
Short Title
Sentence Mover’s Similarity
Language
en
Library Catalogue
DOI.org (Crossref)
Extra
<AI Smry>: This work introduces methods based on sentence mover’s similarity, and finds that sentence-based metrics correlate with human judgments significantly better than ROUGE, both on machine-generated summaries and human-authored essays.
Read_Status: New
Read_Status_Date: 2026-01-26T11:33:20.825Z
Citation
Clark, E., Celikyilmaz, A., & Smith, N. A. (2019). Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2748–2760. https://doi.org/10.18653/v1/P19-1264
Link to this record