TY - GEN
T1 - Measuring thematic fit with distributional feature overlap
AU - Santus, Enrico
AU - Chersoni, Emmanuele
AU - Lenci, Alessandro
AU - Blache, Philippe
N1 - Publisher Copyright:
© 2017 Association for Computational Linguistics.
PY - 2017/9
Y1 - 2017/9
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85063164117
U2 - 10.18653/v1/d17-1068
DO - 10.18653/v1/d17-1068
M3 - Conference article published in proceeding or book
AN - SCOPUS:85063164117
T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 648
EP - 658
BT - Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
A2 - Palmer, Martha
A2 - Hwa, Rebecca
A2 - Riedel, Sebastian
PB - Association for Computational Linguistics (ACL)
T2 - 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
Y2 - 9 September 2017 through 11 September 2017
ER -