UsingWord Embeddings for Query Translation for Hindi to English Cross Language Information Retrieval

TL;DR

This paper introduces a word embedding-based method for Hindi to English query translation in cross-language information retrieval, outperforming traditional dictionary methods and leveraging unaligned corpora for resource-scarce languages.

Contribution

It presents a novel approach that uses word embeddings and learned projections for query translation without requiring aligned corpora, improving CLIR performance.

Findings

Outperforms dictionary-based translation by 70%

Hybrid approach exceeds baseline by 77%

Achieves 15% improvement over English monolingual baseline

Abstract

Cross-Language Information Retrieval (CLIR) has become an important problem to solve in the recent years due to the growth of content in multiple languages in the Web. One of the standard methods is to use query translation from source to target language. In this paper, we propose an approach based on word embeddings, a method that captures contextual clues for a particular word in the source language and gives those words as translations that occur in a similar context in the target language. Once we obtain the word embeddings of the source and target language pairs, we learn a projection from source to target word embeddings, making use of a dictionary with word translation pairs.We then propose various methods of query translation and aggregation. The advantage of this approach is that it does not require the corpora to be aligned (which is difficult to obtain for resource-scarce languages), a dictionary with word translation pairs is enough to train the word vectors for translation. We experiment with Forum for Information Retrieval and Evaluation (FIRE) 2008 and 2012 datasets for Hindi to English CLIR. The proposed word embedding based approach outperforms the basic dictionary based approach by 70% and when the word embeddings are combined with the dictionary, the hybrid approach beats the baseline dictionary based method by 77%. It outperforms the English monolingual baseline by 15%, when combined with the translations obtained from Google Translate and Dictionary.