Timezone: »

A Novel Two-Step Method for Cross Language Representation Learning
Min Xiao · Yuhong Guo

Sun Dec 08 02:00 PM -- 06:00 PM (PST) @ Harrah's Special Events Center, 2nd Floor #None

Cross language text classification is an important learning task in natural language processing. A critical challenge of cross language learning lies in that words of different languages are in disjoint feature spaces. In this paper, we propose a two-step representation learning method to bridge the feature spaces of different languages by exploiting a set of parallel bilingual documents. Specifically, we first formulate a matrix completion problem to produce a complete parallel document-term matrix for all documents in two languages, and then induce a cross-lingual document representation by applying latent semantic indexing on the obtained matrix. We use a projected gradient descent algorithm to solve the formulated matrix completion problem with convergence guarantees. The proposed approach is evaluated by conducting a set of experiments with cross language sentiment classification tasks on Amazon product reviews. The experimental results demonstrate that the proposed learning approach outperforms a number of comparison cross language representation learning methods, especially when the number of parallel bilingual documents is small.

Author Information

Min Xiao (Temple University)
Yuhong Guo (Carleton University)

More from the Same Authors