Title | ||
---|---|---|
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints. |
Abstract | ||
---|---|---|
We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-lingual resources, yielding semantically specialized cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct high-quality vector spaces for a plethora of different languages, facilitating semantic transfer from high- to lower-resource ones. The effectiveness of our approach is demonstrated with state-of-the-art results on semantic similarity datasets in six languages. We next show that Attract-Repel-specialized vectors boost performance in the downstream task of dialogue state tracking (DST) across multiple languages. Finally, we show that cross-lingual vector spaces produced by our algorithm facilitate the training of multilingual DST models, which brings further performance improvements. |
Year | Venue | DocType |
---|---|---|
2017 | TACL | Journal |
Volume | Citations | PageRank |
abs/1706.00374 | 2 | 0.35 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nikola Mrksic | 1 | 407 | 21.11 |
Ivan Vulic | 2 | 462 | 52.59 |
Diarmuid Ó. Séaghdha | 3 | 587 | 28.29 |
Ira Leviant | 4 | 2 | 0.35 |
Roi Reichart | 5 | 760 | 53.53 |
Milica Gasic | 6 | 1085 | 60.44 |
Anna Korhonen | 7 | 1336 | 92.50 |
S. J. Young | 8 | 1174 | 193.63 |