Machine Translation for Machines: the Sentiment Classification Use Case

TL;DR

This paper introduces a machine-oriented neural machine translation approach optimized for sentiment analysis tasks, using reinforcement learning to improve downstream classifier performance on Twitter data in German and Italian.

Contribution

It presents a novel reinforcement learning method with a candidate sampling strategy that tailors translations for specific NLP tasks, outperforming general-purpose NMT models.

Findings

Machine-oriented translations improve sentiment classification accuracy.

Reinforcement learning with weak feedback enhances task-specific translation quality.

Results approach gold standard English tweet classification accuracy.

Abstract

We propose a neural machine translation (NMT) approach that, instead of pursuing adequacy and fluency ("human-oriented" quality criteria), aims to generate translations that are best suited as input to a natural language processing component designed for a specific downstream task (a "machine-oriented" criterion). Towards this objective, we present a reinforcement learning technique based on a new candidate sampling strategy, which exploits the results obtained on the downstream task as weak feedback. Experiments in sentiment classification of Twitter data in German and Italian show that feeding an English classifier with machine-oriented translations significantly improves its performance. Classification results outperform those obtained with translations produced by general-purpose NMT models as well as by an approach based on reinforcement learning. Moreover, our results on both languages approximate the classification accuracy computed on gold standard English tweets.