Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model
TL
TL;DR
The proposed model can transfer the prediction of lexico-semantic relations to a resource-lean target language without any training data and outperforms more complex state-of-the-art architectures on two benchmark datasets and exhibits stable performance across languages.
Abstract
We present a simple and effective feed-forward neural architecture for discriminating between lexico-semantic relations (synonymy, antonymy, hypernymy, and meronymy). Our Specialization Tensor Model (STM) simultaneously produces multiple different specializations of input distributional word vectors, tailored for predicting lexico-semantic relations for word pairs. STM outperforms more complex state-of-the-art architectures on two benchmark datasets and exhibits stable performance across languages. We also show that, if coupled with a bilingual distributional space, the proposed model can transfer the prediction of lexico-semantic relations to a resource-lean target language without any training data.
References28 items
1
Natural Language Inference with External Knowledge
2
Specialising Word Vectors for Lexical Entailment
3
Dual Tensor Model for Detecting Asymmetric Lexico-Semantic Relations
4
Large-scale taxonomy induction using entity and word embeddings
5