Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints

@article{Mrksic2017SemanticSO,
  title={Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints},
  author={Nikola Mrksic and Ivan Vulic and Diarmuid {\'O} S{\'e}aghdha and Ira Leviant and Roi Reichart and Milica Gasic and Anna Korhonen and Steve J. Young},
  journal={CoRR},
  year={2017},
  volume={abs/1706.00374}
}
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 monoand crosslingual resources, yielding semantically specialised cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct highquality vector spaces for a plethora of different languages, facilitating semantic transfer from… CONTINUE READING
Highly Cited
This paper has 38 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 30 times over the past 90 days. VIEW TWEETS

10 Figures & Tables

Topics

Statistics

0204020172018
Citations per Year

Citation Velocity: 23

Averaging 23 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.