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

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 specialized 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 highto lower-resource ones. The effectiveness of our approach is demonstrated with state-ofthe-art results on semantic similarity datasets in six languages. We next show that ATTRACTREPEL-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.