Enhancing Entertainment Translation for Indian Languages using Adaptive Context, Style and LLMs

TL;DR

This paper introduces a novel, language-agnostic framework for entertainment translation that leverages context and style estimation to guide LLMs, significantly improving translation quality in Indian languages.

Contribution

It presents the first framework to incorporate context and style estimation into LLM-based entertainment translation, enhancing translation relevance and engagement.

Findings

Significant improvement in COMET scores over state-of-the-art LLMs

Consistent outperformance of baseline LLMs in win-ratio

Effective algorithm for estimating session context and style

Abstract

We address the challenging task of neural machine translation (NMT) in the entertainment domain, where the objective is to automatically translate a given dialogue from a source language content to a target language. This task has various applications, particularly in automatic dubbing, subtitling, and other content localization tasks, enabling source content to reach a wider audience. Traditional NMT systems typically translate individual sentences in isolation, without facilitating knowledge transfer of crucial elements such as the context and style from previously encountered sentences. In this work, we emphasize the significance of these fundamental aspects in producing pertinent and captivating translations. We demonstrate their significance through several examples and propose a novel framework for entertainment translation, which, to our knowledge, is the first of its kind. Furthermore, we introduce an algorithm to estimate the context and style of the current session and use these estimations to generate a prompt that guides a Large Language Model (LLM) to generate high-quality translations. Our method is both language and LLM-agnostic, making it a general-purpose tool. We demonstrate the effectiveness of our algorithm through various numerical studies and observe significant improvement in the COMET scores over various state-of-the-art LLMs. Moreover, our proposed method consistently outperforms baseline LLMs in terms of win-ratio.