Result Details
Automatic Acquisition of Semantics-Extraction Patterns
This paper examines the use of parallel andcomparable corpora for automatic acquisition of semantics-extraction patterns.It presents a new method of the pattern extraction which takes advantage ofparallel texts to "port" text mining solutions from a source language to atarget language. It is shown that the technique can help in situations when theextraction procedure is to be applied in a language (languages) with a limitedset of available resources, e.g. domain-specific thesauri. The primarymotivation of our work lies in a particular multilingual e-learning system. Fortesting purposes, other applications of the given approach were implemented.They include pattern extraction from general texts (tested on wordnetrelations), acquisition of domain-specific patterns from large parallel corpusof legal EU documents, and mining of subjectivity expressions for multilingualopinion extraction system.
parallel corpus, lexico-semantic patterns
@inproceedings{BUT22422,
author="Pavel {Smrž}",
title="Automatic Acquisition of Semantics-Extraction Patterns",
booktitle="Proceedings of the 5th International Conference on Language Resources and Evaluation",
year="2006",
pages="1--4",
publisher="European Language Resources Association",
address="Paris",
isbn="2-9517408-2-4"
}