Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing
Research output: Contribution to journal › Conference article › Research › peer-review
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.
Original language | English |
---|---|
Journal | NoDaLiDa 2017 - 21st Nordic Conference of Computational Linguistics, Proceedings of the Conference |
Pages (from-to) | 20-28 |
Number of pages | 9 |
Publication status | Published - 2017 |
Externally published | Yes |
Event | 21st Nordic Conference of Computational Linguistics, NoDaLiDa 2017 - Gothenburg, Sweden Duration: 23 May 2017 → 24 May 2017 |
Conference
Conference | 21st Nordic Conference of Computational Linguistics, NoDaLiDa 2017 |
---|---|
Country | Sweden |
City | Gothenburg |
Period | 23/05/2017 → 24/05/2017 |
Bibliographical note
Publisher Copyright:
© 2017 Linköping University Electronic Press.
ID: 366047396