Word semantic similarity for morphologically rich languages

Kalliopi Zervanou, Elias Iosif, Alexandros Potamianos

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

9 Citaten (Scopus)
24 Downloads (Pure)

Samenvatting

In this work, we investigate the role of morphology on the performance of semantic similarity for morphologically rich languages, such as German and Greek. The challenge in processing languages with richer morphology than English, lies in reducing estimation error while addressing the semantic distortion introduced by a stemmer or a lemmatiser. For this purpose, we propose a methodology for selective stemming, based on a semantic distortion metric. The proposed algorithm is tested on the task of similarity estimation between words using two types of corpus-based similarity metrics: co-occurrence-based and context-based. The performance on morphologically rich languages is boosted by stemming with the context-based metric, unlike English, where the best results are obtained by the co-occurrence-based metric. A key finding is that the estimation error reduction is different when a word is used as a feature, rather than when it is used as a target word.

Originele taal-2Engels
TitelProceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014
RedacteurenNicoletta Calzolari, Khalid Choukri, Sara Goggi, Thierry Declerck, Joseph Mariani, Bente Maegaard, Asuncion Moreno, Jan Odijk, Helene Mazo, Stelios Piperidis, Hrafn Loftsson
UitgeverijEuropean Language Resources Association (ELRA)
Pagina's1642-1648
Aantal pagina's7
ISBN van elektronische versie9782951740884
StatusGepubliceerd - 2014
Extern gepubliceerdJa
Evenement9th International Conference on Language Resources and Evaluation, LREC 2014 - Reykjavik, IJsland
Duur: 26 mei 201431 mei 2014

Congres

Congres9th International Conference on Language Resources and Evaluation, LREC 2014
Land/RegioIJsland
StadReykjavik
Periode26/05/1431/05/14

Vingerafdruk

Duik in de onderzoeksthema's van 'Word semantic similarity for morphologically rich languages'. Samen vormen ze een unieke vingerafdruk.

Citeer dit