SODA

Cross-lingual comparison between distributionally determined word similarity networks

Görnerup, Olof and Karlgren, Jussi (2010) Cross-lingual comparison between distributionally determined word similarity networks. In: TextGraphs-5, ACL Workshop on Graph-based Methods for Natural Language Processing , July 2010, Uppsala, Sweden.

[img]PDF - Published Version
Restricted to Repository staff only until 16 July 2010.

167Kb

Abstract

As an initial effort to identify universal and language-specific factors that influence the behavior of distributional models, we have formulated a distributionally determined word similarity network model, implemented it for eleven different languages, and compared the resulting networks. In the model, vertices constitute words and two words are linked if they occur in similar contexts. The model is found to capture clear isomorphisms across languages in terms of syntactic and semantic classes, as well as functional categories of abstract discourse markers. Language specific morphology is found to be a dominating factor for the accuracy of the model.

Item Type:Conference or Workshop Item (Paper)
ID Code:3973
Deposited By:Jussi Karlgren
Deposited On:02 Jun 2010 10:28
Last Modified:02 Jun 2010 10:28

Repository Staff Only: item control page