Automatic Extraction of Synonyms from an Easy-to-Read Corpus

• This paper presents two novel methods aimed at extracting comprehensible synonyms to regular words, as a step towards automatic text simplification. The methods are inspired by previous work on synonym extraction and make use of bilingual dictionaries, as well as distributional semantic similarity between words. Human layman knowledge was used to evaluate the synonym candidates extracted by the methods, which proved to be perceived as synonymous to a high degree. Both methods showed promising results and qualities, and have potential to be used to further improve automatic text simplification.

Ämnesord

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

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

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)