Cross-Lingual Induction and Transfer of Verb Classes Based on Word Vector Space Specialisation

TL;DR

This paper introduces a novel cross-lingual transfer method that leverages bilingual word embeddings to induce and classify verb classes in multiple languages, achieving state-of-the-art results without relying on extensive feature engineering.

Contribution

It presents the first application of word embedding architectures for cross-lingual verb class induction, linking target languages to English VerbNet through bilingual vector spaces.

Findings

Achieves new state-of-the-art verb classification accuracy in six languages.

Demonstrates effectiveness of cross-lingual transfer using bilingual embeddings.

Shows that embedding specialisation improves syntactic-semantic verb classification.

Abstract

Existing approaches to automatic VerbNet-style verb classification are heavily dependent on feature engineering and therefore limited to languages with mature NLP pipelines. In this work, we propose a novel cross-lingual transfer method for inducing VerbNets for multiple languages. To the best of our knowledge, this is the first study which demonstrates how the architectures for learning word embeddings can be applied to this challenging syntactic-semantic task. Our method uses cross-lingual translation pairs to tie each of the six target languages into a bilingual vector space with English, jointly specialising the representations to encode the relational information from English VerbNet. A standard clustering algorithm is then run on top of the VerbNet-specialised representations, using vector dimensions as features for learning verb classes. Our results show that the proposed cross-lingual transfer approach sets new state-of-the-art verb classification performance across all six target languages explored in this work.