Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/71889
Title: | Testing APSyn against vector cosine on similarity estimation | Authors: | Santus, E Chersoni, E Lenci, A Huang, CR Blache, P |
Issue Date: | Oct-2016 | Source: | In Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Oral Papers, p. 229-238 | Abstract: | In Distributional Semantic Models (DSMs), Vector Cosine is widely used to estimate similarity between word vectors, although this measure was noticed to suffer from several shortcomings. The recent lit ENGLerature has proposed other methods which attempt to mitigate such biases. In this paper, we intend to investigate APSyn, a measure that computes the extent of the intersection between the most associated contexts of two target words, weighting it by context relevance. We evaluated this metric in a similarity estimation task on several popular test sets, and our results show that APSyn is in fact highly competitive, even with respect to the results reported in the lit ENGLerature for word embeddings. On top of it, APSyn addresses some of the weaknesses of Vector Cosine, performing well also on genuine similarity estimation. | ISBN: | 9788968174285 | Description: | 30th Pacific Asia Conference on Language, Information and Computation, Oct. 2016, Seoul, South Korea | Rights: | Copyright of contributed papers reserved by respective authors. Posted with permission of the author. The following publication Santus, E., Chersoni, E., Lenci, A., Huang, C. R., & Blache, P. (2016). Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Oral Papers (pp. 229-238) is available at https://aclanthology.org/Y16-2021 |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Y16-2021.pdf | 360.45 kB | Adobe PDF | View/Open |
Page views
93
Last Week
0
0
Last month
Citations as of Sep 22, 2024
Downloads
22
Citations as of Sep 22, 2024
SCOPUSTM
Citations
9
Citations as of Jun 21, 2024
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.