A Large Scale Evaluation of Distributional Semantic Models: Parameters, Interactions and Model Selection

Lapesa G, Evert S (2014)

Publication Type: Journal article, Original article

Publication year: 2014

Journal

Transactions of the Association for Computational Linguistics Association for Computational Linguistics

Publisher: Association for Computational Linguistics

Book Volume: 2

Pages Range: 531–545

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

Open Access Link: https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/457

Abstract

This paper presents the results of a large-scale evaluation study of window-based Distributional Semantic Models on a wide variety of tasks. Our study combines a broad coverage of model parameters with a model selection methodology that is robust to overfitting and able to capture parameter interactions. We show that our strategy allows us to identify parameter configurations that achieve good performance across different datasets and tasks.

Authors with CRIS profile

Gabriella Lapesa Stephanie Evert Lehrstuhl für Korpus- und Computerlinguistik

How to cite

APA:

Lapesa, G., & Evert, S. (2014). A Large Scale Evaluation of Distributional Semantic Models: Parameters, Interactions and Model Selection. Transactions of the Association for Computational Linguistics, 2, 531–545.

MLA:

Lapesa, Gabriella, and Stephanie Evert. "A Large Scale Evaluation of Distributional Semantic Models: Parameters, Interactions and Model Selection." Transactions of the Association for Computational Linguistics 2 (2014): 531–545.

BibTeX: Download