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
Standard
Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics. / Hershcovich, Daniel; Schneider, Nathan; Dvir, Dotan ; Prange, Jakob ; de Lhoneux, Miryam Anne Noëlle; Abend, Omri.
Proceedings of the 28th International Conference on Computational Linguistic. Association for Computational Linguistics, 2020. p. 2947–2966.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics
AU - Hershcovich, Daniel
AU - Schneider, Nathan
AU - Dvir, Dotan
AU - Prange, Jakob
AU - de Lhoneux, Miryam Anne Noëlle
AU - Abend, Omri
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
M3 - Article in proceedings
SP - 2947
EP - 2966
BT - Proceedings of the 28th International Conference on Computational Linguistic
PB - Association for Computational Linguistics
T2 - 28th International Conference on Computational Linguistics
Y2 - 8 December 2020 through 13 December 2020
ER -
ID: 254671479