Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
We show that a set of real-valued word vectors formed by right singular vectors of a transformed co-occurrence matrix are meaningful for determining different types of dependency relations between words. Our experimental results on the task of dependency parsing confirm the superiority of the word vectors to the other sets of word vectors generated by popular methods of word embedding. We also study the effect of using these vectors on the accuracy of dependency parsing in different languages versus using more complex parsing architectures.
Originalsprog | Engelsk |
---|---|
Tidsskrift | NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference |
Sider (fra-til) | 20-28 |
Antal sider | 9 |
Status | Udgivet - 2017 |
Eksternt udgivet | Ja |
Begivenhed | 21st Nordic Conference of Computational Linguistics, NoDaLiDa 2017 - Gothenburg, Sverige Varighed: 23 maj 2017 → 24 maj 2017 |
Konference
Konference | 21st Nordic Conference of Computational Linguistics, NoDaLiDa 2017 |
---|---|
Land | Sverige |
By | Gothenburg |
Periode | 23/05/2017 → 24/05/2017 |
Bibliografisk note
Publisher Copyright:
© 2017 Linköping University Electronic Press.
ID: 366047396