Measuring Thematic Fit with Distributional Feature Overlap
Enrico Santus, Emmanuele Chersoni, Alessandro Lenci, Philippe Blache
Abstract
In this paper, we introduce a new distributional method for modeling predicate-argument thematic fit judgments. We use a syntax-based DSM to build a prototypical representation of verb-specific roles: for every verb, we extract the most salient second order contexts for each of its roles (i.e. the most salient dimensions of typical role fillers), and then we compute thematic fit as a weighted overlap between the top features of candidate fillers and role prototypes. Our experiments show that our method consistently outperforms a baseline re-implementing a state-of-the-art system, and achieves better or comparable results to those reported in the literature for the other unsupervised systems. Moreover, it provides an explicit representation of the features characterizing verb-specific semantic roles.- Anthology ID:
- D17-1068
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 648–658
- Language:
- URL:
- https://aclanthology.org/D17-1068
- DOI:
- 10.18653/v1/D17-1068
- Cite (ACL):
- Enrico Santus, Emmanuele Chersoni, Alessandro Lenci, and Philippe Blache. 2017. Measuring Thematic Fit with Distributional Feature Overlap. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 648–658, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Measuring Thematic Fit with Distributional Feature Overlap (Santus et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/naacl24-info/D17-1068.pdf
- Code
- esantus/Thematic_Fit