Abstract
In this paper, we claim that Vector Cosine - which is generally considered one of the most efficient unsupervised measures for identifying word similarity in Vector Space Models - can be outperformed by a completely unsupervised measure that evaluates the extent of the intersection among the most associated contexts of two target words, weighting such intersection according to the rank of the shared contexts in the dependency ranked lists. This claim comes from the hypothesis that similar words do not simply occur in similar contexts, but they share a larger portion of their most relevant contexts compared to other related words. To prove it, we describe and evaluate APSyn, a variant of Average Precision that - independently of the adopted parameters - outperforms the Vector Cosine and the co-occurrence on the ESL and TOEFL test sets. In the best setting, APSyn reaches 0.73 accuracy on the ESL dataset and 0.70 accuracy in the TOEFL dataset, beating therefore the non-English US college applicants (whose average, as reported in the literature, is 64.50%) and several state-of-the-art approaches.
Original language | English |
---|---|
Title of host publication | Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016 |
Publisher | European Language Resources Association (ELRA) |
Pages | 4565-4572 |
Number of pages | 8 |
ISBN (Electronic) | 9782951740891 |
Publication status | Published - 1 Jan 2016 |
Event | 10th International Conference on Language Resources and Evaluation, LREC 2016 - Grand Hotel Bernardin Conference Center, Portoroz, Slovenia Duration: 23 May 2016 → 28 May 2016 |
Conference
Conference | 10th International Conference on Language Resources and Evaluation, LREC 2016 |
---|---|
Country/Territory | Slovenia |
City | Portoroz |
Period | 23/05/16 → 28/05/16 |
Keywords
- Distributional semantic models
- DSMs
- Semantic relations
- Vector Space Models
- VSMs
- Words similarity
ASJC Scopus subject areas
- Linguistics and Language
- Library and Information Sciences
- Language and Linguistics
- Education