transparent gif

 

Ej inloggad.

Göteborgs universitets publikationer

Embedding Senses for Efficient Graph-based Word Sense Disambiguation

Författare och institution:
Luis Nieto Piña (Institutionen för svenska språket); Richard Johansson (Institutionen för data- och informationsteknik (GU))
Publicerad i:
Proceedings of TextGraphs-10: the Workshop on Graph-based Methods for Natural Language Processing, s. 1-5
Publikationstyp:
Artikel, refereegranskad vetenskaplig
Publiceringsår:
2016
Språk:
engelska
Fulltextlänk:
Sammanfattning (abstract):
We propose a simple graph-based method for word sense disambiguation (WSD) where sense and context embeddings are constructed by applying the Skip-gram method to random walks over the sense graph. We used this method to build a WSD system for Swedish using the SALDO lexicon, and evaluated it on six different annotated test sets. In all cases, our system was several orders of magnitude faster than a state-of-the-art PageRank-based system, while outperforming a random baseline soundly.
Ämne (baseras på Högskoleverkets indelning av forskningsämnen):
TEKNIK OCH TEKNOLOGIER ->
Elektroteknik och elektronik ->
Datorsystem
Nyckelord:
language technology, lt, natural language processing, nlp, machine learning, ml, word sense disambiguation, wsd, graphs
Postens nummer:
241139
Posten skapad:
2016-09-01 18:37

Visa i Endnote-format

Göteborgs universitet • Tel. 031-786 0000
© Göteborgs universitet 2007