Heterogeneous Knowledge Sources in Graph-Based Expansion of the Polish Wordnet

Piasecki, Maciej; Kurc, Roman; Broda, Bartosz

doi:10.1007/978-3-642-20039-7_31

Cited by 2 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extracted relations were validated, then added to the Arabic wordnet data base. Piasecki et al (2011) proposed an algorithm for automatically expanding the Polish wordnet. This method uses heterogeneous knowledge sources, which are extracted from a large corpus, and combines them based on a weighted voting scheme.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Wordnet Development for Low-Resource Languages using Cross-Lingual WSD

Taghizadeh

Faili

2016

jair

View full text Add to dashboard Cite

Wordnets are an effective resource for natural language processing and information retrieval, especially for semantic processing and meaning related tasks. So far, wordnets have been constructed for many languages. However, the automatic development of wordnets for low-resource languages has not been well studied. In this paper, an ExpectationMaximization algorithm is used to create high quality and large scale wordnets for poorresource languages. The proposed method benefits from possessing cross-lingual word sense disambiguation and develops a wordnet by only using a bi-lingual dictionary and a monolingual corpus. The proposed method has been executed with Persian language and the resulting wordnet has been evaluated through several experiments. The results show that the induced wordnet has a precision score of 90% and a recall score of 35%.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Large wordnets may have tens of thousands of sysnsets (Miller, 1995;Patanakul & Charnyote, 2005;Black et al, 2006;Piasecki et al, 2011). On the other hand, wordnets with more polysemic words are more useful in NLP and IR tasks.…”

Section: Size and Polysemy Rate Of The Wordnetmentioning

confidence: 99%