PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Automated Translation of Semantic Relationships.
Dmitry Davidov and Ari Rappoport
COLING 2010 2010.

Abstract

We present a method for translating semantic relationships between languages where relationships are defined as pattern clusters. Given a pattern set which represents a semantic relationship, we use the web to extract sample term pairs of this relationship. We automatically translate the obtained term pairs using multilingual dictionaries and disambiguate the translated pairs using web counts. Finally we discover the set of most relevant target language patterns for the given relationship. The obtained pattern set can be utilized for extraction of new relationship examples for the target language. We evaluate our method on 11 diverse target languages. To assess the quality of the discovered relationships, we use an automatically generated cross-lingual SAT analogy test, WordNet relationships, and concept-specific relationships, achieving high precision. The proposed framework allows fully automated cross-lingual relationship mining and construction of multilingual pattern dictionaries without relying on parallel corpora.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
Information Retrieval & Textual Information Access
ID Code:7072
Deposited By:Ari Rappoport
Deposited On:27 February 2011