Large-scale evaluation of dependency-based DSMs: Are they worth the effort?

Lapesa G, Evert S (2017)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2017

City/Town: Valencia, Spain

Pages Range: 394-400

Conference Proceedings Title: Proceedings of the 15th Annual Meeting of the European Association for Computational Linguistics (EACL 2017): Volume 2, Short Papers

URI: http://www.linguistik.fau.de/dsmeval/

Open Access Link: https://www.aclweb.org/anthology/E/E17/E17-2063.pdf

Abstract

This paper presents a large-scale evaluation study of dependency-based distributional semantic models. We evaluate dependency-filtered and dependency-structured DSMs in a number of standard semantic similarity tasks, systematically exploring their parameter space in order to give them a “fair shot” against window-based models. Our results show that properly tuned window-based DSMs still outperform the dependency-based models in most tasks. There appears to be little need for the language-dependent resources and computational cost associated with syntactic analysis.

Authors with CRIS profile

How to cite

APA:

Lapesa, G., & Evert, S. (2017). Large-scale evaluation of dependency-based DSMs: Are they worth the effort? In Proceedings of the 15th Annual Meeting of the European Association for Computational Linguistics (EACL 2017): Volume 2, Short Papers (pp. 394-400). Valencia, Spain.

MLA:

Lapesa, Gabriella, and Stephanie Evert. "Large-scale evaluation of dependency-based DSMs: Are they worth the effort?" Proceedings of the Proceedings of the 15th Annual Meeting of the European Association for Computational Linguistics (EACL 2017): Volume 2, Short Papers Valencia, Spain, 2017. 394-400.

BibTeX: Download