QANom: Question-Answer driven SRL for Nominalizations

Ayal Klein, Jonathan Mamou, Valentina Pyatkin, Daniela Stepanov, Hangfeng He, Dan Roth, Luke Zettlemoyer, Ido Dagan


Abstract
We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom. This scheme extends the QA-SRL formalism (He et al., 2015), modeling the relations between nominalizations and their arguments via natural language question-answer pairs. We construct the first QANom dataset using controlled crowdsourcing, analyze its quality and compare it to expertly annotated nominal-SRL annotations, as well as to other QA-driven annotations. In addition, we train a baseline QANom parser for identifying nominalizations and labeling their arguments with question-answer pairs. Finally, we demonstrate the extrinsic utility of our annotations for downstream tasks using both indirect supervision and zero-shot settings.
Anthology ID:
2020.coling-main.274
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
3069–3083
Language:
URL:
https://aclanthology.org/2020.coling-main.274
DOI:
10.18653/v1/2020.coling-main.274
Bibkey:
Cite (ACL):
Ayal Klein, Jonathan Mamou, Valentina Pyatkin, Daniela Stepanov, Hangfeng He, Dan Roth, Luke Zettlemoyer, and Ido Dagan. 2020. QANom: Question-Answer driven SRL for Nominalizations. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3069–3083, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
QANom: Question-Answer driven SRL for Nominalizations (Klein et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2020.coling-main.274.pdf
Code
 kleinay/QANom