Bilingual Tests with Swedish, Finnish, and German Queries: Dealing with Morphology, Compound Words, and Query Structure
Author(s) -
Turid Hedlund,
Heikki Keskustalo,
Ari Pirkola,
Mikko Sepponen,
Kalervo Järvelin
Publication year - 2001
Publication title -
lecture notes in computer science
Language(s) - English
Resource type - Book series
SCImago Journal Rank - 0.249
H-Index - 400
eISSN - 1611-3349
pISSN - 0302-9743
ISBN - 3-540-42446-6
DOI - 10.1007/3-540-44645-1_20
Subject(s) - computer science , clef , natural language processing , german , artificial intelligence , query expansion , compound , bilingual dictionary , word (group theory) , normalization (sociology) , linguistics , information retrieval , philosophy , management , sociology , anthropology , task (project management) , economics
We designed, implemented and evaluated an automated method for query construction for CLIR from Finnish, Swedish and German to English. This method seeks to automatically extract topical information from request sentences written in one of the source languages and to create a target language query, based on translations given by a translation dictionary. We paid particular attention to morphology, compound words and query structure. we tested this approach in the bilingual track of CLEF. All the source languages are compound languages, i.e., languages rich in compound words. A compound word refers to a multi-word expression where the component words are written together. Because source language request words may appear in various inflected forms not included in a translation dictionary, morphological normalization was used to aid dictionary translation. The query resulting from this process may be structured according to the translation alternatives of each source language word or remain as an unstructured word list.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom