Cross-language Sentence Selection via Data Augmentation and Rationale Training

Yanda Chen, Chris Kedzie, Suraj Nair, Petra Galuscakova, Rui Zhang, Douglas Oard, Kathleen McKeown
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
This paper proposes an approach to crosslanguage sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based query relevance model. Results show that this approach performs as well as or better than multiple state-of-theart machine translation + monolingual retrieval systems trained on the same parallel data. Moreover, when a rationale training secondary objective is
more » ... lied to encourage the model to match word alignment hints from a phrase-based statistical machine translation model, consistent improvements are seen across three language pairs (English-Somali, English-Swahili and English-Tagalog) over a variety of state-of-the-art baselines.
doi:10.18653/v1/2021.acl-long.300 fatcat:2ccr75mx6rduxkqg6w4fijgygu