Corpus-Driven Thematic Hierarchy Induction

Ilia Kuznetsov, Iryna Gurevych


Abstract
Thematic role hierarchy is a widely used linguistic tool to describe interactions between semantic roles and their syntactic realizations. Despite decades of dedicated research and numerous thematic hierarchy suggestions in the literature, this concept has not been used in NLP so far due to incompatibility and limited scope of existing hierarchies. We introduce an empirical framework for thematic hierarchy induction and evaluate several role ranking strategies on English and German full-text corpus data. We hypothesize that global thematic hierarchy induction is feasible, that a hierarchy can be induced from just fractions of training data and that resulting hierarchies apply cross-lingually. We evaluate these assumptions empirically.
Anthology ID:
K18-1006
Volume:
Proceedings of the 22nd Conference on Computational Natural Language Learning
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Anna Korhonen, Ivan Titov
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
54–64
Language:
URL:
https://aclanthology.org/K18-1006
DOI:
10.18653/v1/K18-1006
Bibkey:
Cite (ACL):
Ilia Kuznetsov and Iryna Gurevych. 2018. Corpus-Driven Thematic Hierarchy Induction. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 54–64, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Corpus-Driven Thematic Hierarchy Induction (Kuznetsov & Gurevych, CoNLL 2018)
Copy Citation:
PDF:
https://aclanthology.org/K18-1006.pdf
Data
Universal Dependencies