Embedding Learning Through Multilingual Concept Induction
arXiv:1801.06807
Abstract
We present a new method for estimating vector space representations of words: embedding learning by concept induction. We test this method on a highly parallel corpus and learn semantic representations of words in 1259 different languages in a single common space. An extensive experimental evaluation on crosslingual word similarity and sentiment analysis indicates that concept-based multilingual embedding learning performs better than previous approaches.
arXiv commentACL 2018
References in corpus (7)
- Efficient Estimation of Word Representations in Vector Space
- Exploiting Similarities among Languages for Machine Translation
- An Autoencoder Approach to Learning Bilingual Word Representations
- BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
- Massively Multilingual Word Embeddings
- Cross-lingual Models of Word Embeddings: An Empirical Comparison
- A Word-to-Word Model of Translational Equivalence