Title
Exploiting translational correspondences for pattern-independent MWE identification
Abstract
Based on a study of verb translations in the Europarl corpus, we argue that a wide range of MWE patterns can be identified in translations that exhibit a correspondence between a single lexical item in the source language and a group of lexical items in the target language. We show that these correspondences can be reliably detected on dependency-parsed, word-aligned sentences. We propose an extraction method that combines word alignment with syntactic filters and is independent of the structural pattern of the translation.
Year
Venue
Keywords
2009
MWE@IJCNLP
extraction method,single lexical item,lexical item,source language,structural pattern,translational correspondence,target language,verb translation,europarl corpus,syntactic filter,pattern-independent mwe identification,mwe pattern,dependency parsing
Field
DocType
Citations 
Verb,Lexical item,Computer science,Speech recognition,Natural language processing,Artificial intelligence,Syntax
Conference
9
PageRank 
References 
Authors
0.61
10
2
Name
Order
Citations
PageRank
Sina Zarrieß1358.65
Jonas Kuhn29712.14