A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- OA-A Simple and Robust Approach to
Final published version, 273 KB, PDF document
While rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit their training data. We observe that rule-based error generation is less sensitive to syntactic parsing errors and irregularities than error detection and explore a simple, yet efficient approach to getting the best of both worlds: We train neural sequential labelers on the combination of large volumes of silver standard data, obtained through rule-based error generation, and gold standard data. We show that our simple protocol leads to more robust detection of SVA errors on both in-domain and out-of-domain data, as well as in the context of other errors and long-distance dependencies; and across four standard benchmarks, the induced model on average achieves a new state of the art.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) |
Publisher | Association for Computational Linguistics |
Publication date | 2019 |
Pages | 2418-2427 |
DOIs | |
Publication status | Published - 2019 |
Event | 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019 - Minneapolis, United States Duration: 3 Jun 2019 → 7 Jun 2019 |
Conference
Conference | 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019 |
---|---|
Land | United States |
By | Minneapolis |
Periode | 03/06/2019 → 07/06/2019 |
Number of downloads are based on statistics from Google Scholar and www.ku.dk
No data available
ID: 240410767