Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- Comparison by Conversion
Final published version, 316 KB, PDF document
Building robust natural language understanding systems will require a clear characterization of whether and how various linguistic meaning representations complement each other. To perform a systematic comparative analysis, we evaluate the mapping between meaning representations from different frameworks using two complementary methods: (i) a rule-based converter, and (ii) a supervised delexicalized parser that parses to one framework using only information from the other as features. We apply these methods to convert the STREUSLE corpus (with syntactic and lexical semantic annotations) to UCCA (a graph-structured full-sentence meaning representation). Both methods yield surprisingly accurate target representations, close to fully supervised UCCA parser quality—indicating that UCCA annotations are partially redundant with STREUSLE annotations. Despite this substantial convergence between frameworks, we find several important areas of divergence.
Original language | English |
---|---|
Title of host publication | Proceedings of the 28th International Conference on Computational Linguistic |
Publisher | Association for Computational Linguistics |
Publication date | 2020 |
Pages | 2947–2966 |
Publication status | Published - 2020 |
Event | 28th International Conference on Computational Linguistics - Online, Barcelona, Spain Duration: 8 Dec 2020 → 13 Dec 2020 |
Conference
Conference | 28th International Conference on Computational Linguistics |
---|---|
Location | Online |
Land | Spain |
By | Barcelona |
Periode | 08/12/2020 → 13/12/2020 |
Number of downloads are based on statistics from Google Scholar and www.ku.dk
No data available
ID: 254671479