Learning to Translate for Multilingual Question Answering

Ferhan Ture1 and Elizabeth Boschee2
1Comcast Labs, 2Raytheon BBN Technologies


Abstract

In multilingual question answering, either the question needs to be translated into the document language, or vice versa. In addition to direction, there are multiple ways to perform the translation, four of which we explore in this paper: word-based, 10-best, context-based, and grammar-based. We build a feature for each combination of translation direction and method, and train a model that learns optimal feature weights. On a large forum dataset consisting of posts in English, Arabic, and Chinese, our novel learn-to-translate approach was more effective than a typical approach (p<0.05): translating all text into English, then training a classifier based only on English (original or translated) text.