Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Comparison by Conversion
Forlagets udgivne version, 316 KB, PDF-dokument
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.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the 28th International Conference on Computational Linguistic |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2020 |
Sider | 2947–2966 |
Status | Udgivet - 2020 |
Begivenhed | 28th International Conference on Computational Linguistics - Online, Barcelona, Spanien Varighed: 8 dec. 2020 → 13 dec. 2020 |
Konference
Konference | 28th International Conference on Computational Linguistics |
---|---|
Lokation | Online |
Land | Spanien |
By | Barcelona |
Periode | 08/12/2020 → 13/12/2020 |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 254671479