A Multi-Task Architecture on Relevance-based Neural Query Translation
This addresses the issue of vocabulary mismatch in query translation for CLIR, offering a domain-specific incremental improvement.
The paper tackled the problem of neural machine translation for cross-lingual information retrieval by introducing a multi-task learning architecture with a relevance-based auxiliary task, achieving a 16% improvement over a strong baseline on an Italian-English dataset.
We describe a multi-task learning approach to train a Neural Machine Translation (NMT) model with a Relevance-based Auxiliary Task (RAT) for search query translation. The translation process for Cross-lingual Information Retrieval (CLIR) task is usually treated as a black box and it is performed as an independent step. However, an NMT model trained on sentence-level parallel data is not aware of the vocabulary distribution of the retrieval corpus. We address this problem with our multi-task learning architecture that achieves 16% improvement over a strong NMT baseline on Italian-English query-document dataset. We show using both quantitative and qualitative analysis that our model generates balanced and precise translations with the regularization effect it achieves from multi-task learning paradigm.