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

Hershcovich, D, Schneider, N, Dvir, D, Prange, J, de Lhoneux, MAN & Abend, O 2020, Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics. in Proceedings of the 28th International Conference on Computational Linguistic. Association for Computational Linguistics, pp. 2947–2966, 28th International Conference on Computational Linguistics, Barcelona, Spain, 08/12/2020.

APA

Hershcovich, D., Schneider, N., Dvir, D., Prange, J., de Lhoneux, M. A. N., & Abend, O. (2020). Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics. In Proceedings of the 28th International Conference on Computational Linguistic (pp. 2947–2966). Association for Computational Linguistics.

Vancouver

Hershcovich D, Schneider N, Dvir D, Prange J, de Lhoneux MAN, Abend O. Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics. In Proceedings of the 28th International Conference on Computational Linguistic. Association for Computational Linguistics. 2020. p. 2947–2966

Author

Hershcovich, Daniel ; Schneider, Nathan ; Dvir, Dotan ; Prange, Jakob ; de Lhoneux, Miryam Anne Noëlle ; Abend, Omri. / Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics. Proceedings of the 28th International Conference on Computational Linguistic. Association for Computational Linguistics, 2020. pp. 2947–2966

Bibtex

@inproceedings{6937f183df4d4de181e1149c2702d23d,
title = "Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics",
abstract = "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.",
author = "Daniel Hershcovich and Nathan Schneider and Dotan Dvir and Jakob Prange and {de Lhoneux}, {Miryam Anne No{\"e}lle} and Omri Abend",
year = "2020",
language = "English",
pages = "2947–2966",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistic",
publisher = "Association for Computational Linguistics",
note = "28th International Conference on Computational Linguistics ; Conference date: 08-12-2020 Through 13-12-2020",

}

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