Creating a Bilingual Psychology Lexikon for Cross Lingual Question Answering - A Pilot Study

• This paper introduces a pilot study aimed at investigating the extraction of word relations from a sample of a medical parallel corpus in the field of Psychology. Word relations are extracted in order to create a bilingual lexicon for cross lingual question answering between Swedish and English. Four different variants of the sample corpus were utilized: word inflections with and without POS tagging, lemmas with and without POS tagging. The purpose of the study was to analyze the quality of the word relations obtained from the different versions of the corpus and to understand which version of the corpus was more suitable for extracting a bilingual lexicon in the field of psychology. The word alignments were evaluated with the help of reference data (gold standards), which were constructed before the word alignment process.

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences (hsv//eng)

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Nyckelord

Internet services

Natural Language Interfaces

Data Mining

Cross Lingual Question Answering

Computer and Systems Sciences

data- och systemvetenskap

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)