Aswanth Kumar


2023

pdf
CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation
Aswanth Kumar | Ratish Puduppully | Raj Dabre | Anoop Kunchukuttan
Findings of the Association for Computational Linguistics: EMNLP 2023

Large language models have demonstrated the capability to perform on machine translation when the input is prompted with a few examples (in-context learning). Translation quality depends on various features of the selected examples, such as their quality and relevance, but previous work has predominantly focused on individual features in isolation. In this paper, we propose a general framework for combining different features influencing example selection. We learn a regression model, CTQ Scorer (Contextual Translation Quality), that selects examples based on multiple features in order to maximize the translation quality. On multiple language pairs and language models, we show that CTQ Scorer helps significantly outperform random selection as well as strong single-factor baselines reported in the literature. We also see an improvement of over 2.5 COMET points on average with respect to a strong BM25 retrieval-based baseline.