Assessing the Ability of Neural Machine Translation Models to Perform Syntactic Rewriting
Abstract
We describe work in progress for evaluating performance of sequence-to-sequence neural networks on the task of syntax-based reordering for rules applicable to simultaneous machine translation. We train models that attempt to rewrite English sentences using rules that are commonly used by human interpreters. We examine the performance of these models to determine which forms of rewriting are more difficult for them to learn and which architectures are the best at learning them.- Anthology ID:
- W19-3648
- Volume:
- Proceedings of the 2019 Workshop on Widening NLP
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Amittai Axelrod, Diyi Yang, Rossana Cunha, Samira Shaikh, Zeerak Waseem
- Venue:
- WiNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 152
- Language:
- URL:
- https://aclanthology.org/W19-3648
- DOI:
- Cite (ACL):
- Jahkel Robin, Alvin Grissom II, and Matthew Roselli. 2019. Assessing the Ability of Neural Machine Translation Models to Perform Syntactic Rewriting. In Proceedings of the 2019 Workshop on Widening NLP, page 152, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Assessing the Ability of Neural Machine Translation Models to Perform Syntactic Rewriting (Robin et al., WiNLP 2019)