Learning to Respond to Mixed-code Queries using BilingualWord Embeddings

We present a method for learning bilingual word embeddings in order to support second language (L2) learners in finding recurring phrases and example sentences that match mixed-code queries (e.g., "sentence") composed of words in both target language and native language (L1). In our approach, mixed-code queries are transformed into target language queries aimed at maximizing the probability of retrieving relevant target language phrases and sentences. The method involves converting a given parallel corpus into mixed-code data, generating word embeddings from mixed-code data, and expanding queries in target languages based on bilingual word embeddings. We present a prototype search engine, x.Linggle, that applies the method to a linguistic search engine for a parallel corpus. Preliminary evaluation on a list of common word-translation shows that the method performs reasonably well.