Automatic Collocation Extraction and Classification of Automatically Obtained Bigrams

Show full item record



Permalink

http://hdl.handle.net/10138/153191

Citation

Kormacheva , D , Pivovarova , L & Kopotev , M 2014 , Automatic Collocation Extraction and Classification of Automatically Obtained Bigrams . in V Henrich & E Hinrichs (eds) , Proceedings : Workshop on Computational, Cognitive, and Linguistic Approaches to the Analysis of Complex Words and Collocations (CCLCC 2014) . University of Tübingen , Tübingen , pp. 27-33 , Workshop on Computational, Cognitive, and Linguistic Approaches to the Analysis of Complex Words and Collocations , Tübingen , Germany , 11/08/2014 . < http://www.sfs.uni-tuebingen.de/~vhenrich/cclcc_2014/ >

Title: Automatic Collocation Extraction and Classification of Automatically Obtained Bigrams
Author: Kormacheva, Daria; Pivovarova, Lidia; Kopotev, Mihail
Other contributor: Henrich, Verena
Hinrichs, Erhard
Contributor organization: Department of Modern Languages 2010-2017
Department of Computer Science
Computational Linguistics research group / Roman Yangarber
Publisher: University of Tübingen
Date: 2014
Language: eng
Number of pages: 7
Belongs to series: Proceedings
URI: http://hdl.handle.net/10138/153191
Abstract: This paper focuses on automatic determination of the distributional preferences of words in Russian. We present the comparison of six different measures for collocation extraction, part of which are widely known, while others are less prominent or new. For these metrics we evaluate the semantic stability of automatically obtained bigrams beginning with single-token prepositions. Manual annotation of the first 100 bigrams and comparison with the dictionary of multi-word expressions are used as evaluation measures. Finally, in order to present error analysis, two prepositions are investigated in some details.
Subject: 6121 Languages
Peer reviewed: Yes
Usage restriction: openAccess
Self-archived version: acceptedVersion


Files in this item

Total number of downloads: Loading...

Files Size Format View
2014_cclcc_mwe.final.pdf 180.0Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record