Abstract
We propose a novel task of native-like expression identification by contrasting texts written by native speakers and those by proficient second language speakers. This task is highly challenging mainly because 1) the combinatorial nature of expressions prevents us from choosing candidate expressions a priori and 2) the distributions of the two types of texts overlap considerably. Our solution to the first problem is to combine a powerful neural network-based classifier of sentence-level nativeness with an explainability method that measures an approximate contribution of a given expression to the classifier’s prediction. To address the second problem, we introduce a special label neutral and reformulate the classification task as complementary-label learning. Our crowdsourcing-based evaluation and in-depth analysis suggest that our method successfully uncovers linguistically interesting usages distinctive of native speech.- Anthology ID:
- 2020.coling-main.514
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 5843–5854
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.514
- DOI:
- 10.18653/v1/2020.coling-main.514
- Cite (ACL):
- Oleksandr Harust, Yugo Murawaki, and Sadao Kurohashi. 2020. Native-like Expression Identification by Contrasting Native and Proficient Second Language Speakers. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5843–5854, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- Native-like Expression Identification by Contrasting Native and Proficient Second Language Speakers (Harust et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.514.pdf