A Novel Bilingual Word Embedding Method for Lexical Translation Using Bilingual Sense Clique

Abstract

Most of the existing methods for bilingual word embedding only consider shallow context or simple co-occurrence information. In this paper, we propose a latent bilingual sense unit (Bilingual Sense Clique, BSC), which is derived from a maximum complete sub-graph of pointwise mutual information based graph over bilingual corpus. In this way, we treat source and target words equally and a separated bilingual projection processing that have to be used in most existing works is not necessary any more. Several dimension reduction methods are evaluated to summarize the BSC-word relationship. The proposed method is evaluated on bilingual lexicon translation tasks and empirical results show that bilingual sense embedding methods outperform existing bilingual word embedding methods.

under review by COLING-2016

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• Offline bilingual word vectors, orthogonal transformations and the inverted softmax
• Cross-lingual Models of Word Embeddings: An Empirical Comparison
• A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings
• Learning Bilingual Word Representations by Marginalizing Alignments

Cited by in corpus (3)

• Filtered Inner Product Projection for Crosslingual Embedding Alignment
• Effective Subword Segmentation for Text Comprehension
• Code-switching Language Modeling With Bilingual Word Embeddings: A Case Study for Egyptian Arabic-English