Great Service! Fine-grained Parsing of Implicit Arguments
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Great Service! Fine-grained Parsing of Implicit Arguments. / Cui, Ruixiang; Hershcovich, Daniel.
Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021). Association for Computational Linguistics, 2021. p. 65-77.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Great Service! Fine-grained Parsing of Implicit Arguments
AU - Cui, Ruixiang
AU - Hershcovich, Daniel
PY - 2021
Y1 - 2021
N2 - Broad-coverage meaning representations in NLP mostly focus on explicitly expressed content. More importantly, the scarcity of datasets annotating diverse implicit roles limits empirical studies into their linguistic nuances. For example, in the web review “Great service!”, the provider and consumer are implicit arguments of different types. We examine an annotated corpus of fine-grained implicit arguments (Cui and Hershcovich, 2020) by carefully re-annotating it, resolving several inconsistencies. Subsequently, we present the first transition-based neural parser that can handle implicit arguments dynamically, and experiment with two different transition systems on the improved dataset. We find that certain types of implicit arguments are more difficult to parse than others and that the simpler system is more accurate in recovering implicit arguments, despite having a lower overall parsing score, attesting current reasoning limitations of NLP models. This work will facilitate a better understanding of implicit and underspecified language, by incorporating it holistically into meaning representations.
AB - Broad-coverage meaning representations in NLP mostly focus on explicitly expressed content. More importantly, the scarcity of datasets annotating diverse implicit roles limits empirical studies into their linguistic nuances. For example, in the web review “Great service!”, the provider and consumer are implicit arguments of different types. We examine an annotated corpus of fine-grained implicit arguments (Cui and Hershcovich, 2020) by carefully re-annotating it, resolving several inconsistencies. Subsequently, we present the first transition-based neural parser that can handle implicit arguments dynamically, and experiment with two different transition systems on the improved dataset. We find that certain types of implicit arguments are more difficult to parse than others and that the simpler system is more accurate in recovering implicit arguments, despite having a lower overall parsing score, attesting current reasoning limitations of NLP models. This work will facilitate a better understanding of implicit and underspecified language, by incorporating it holistically into meaning representations.
U2 - 10.18653/v1/2021.iwpt-1.7
DO - 10.18653/v1/2021.iwpt-1.7
M3 - Article in proceedings
SP - 65
EP - 77
BT - Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)
PB - Association for Computational Linguistics
T2 - 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)
Y2 - 4 August 2021 through 4 August 2021
ER -
ID: 300917340