Improving Vector Space Word Representations Using Multilingual Correlation
Manaal Faruqui, Chris Dyer · Conference of the European Chapter of the Association for Computational Linguistics · 2014
The distributional hypothesis of Harris (1954), according to which the meaning of words is evidenced by the contexts they occur in, has motivated several effective techniques for obtaining vector space semantic representations of words using unannotated text corpora. This paper argues that lexico-semantic content should additionally be invariant across languages and proposes a simple technique based on canonical correlation analysis (CCA) for incorporating multilingual evidence into vectors generated monolingually. We evaluate the resulting word representations on standard lexical semantic evaluation tasks and show that our method produces substantially better semantic representations than monolingual techniques.
Cited by 618 works. doi:10.3115/v1/e14-1049
Authors
References
- Indexing by latent semantic analysis
- Efficient Estimation of Word Representations in Vector Space
- Visualizing Data using t-SNE
- A unified architecture for natural language processing
- Matrix computations (3rd ed.)
- Contextual correlates of semantic similarity
- Word association norms, mutual information, and lexicography
- Word Representations: A Simple and General Method for Semi-Supervised Learning
- A Scalable Hierarchical Distributed Language Model
- Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms