Translations as Additional Contexts for Sentence Classification

TL;DR

This paper introduces a novel method called MCFA that uses translations as domain-independent context for sentence classification, improving accuracy by fixing noisy translation vectors.

Contribution

The paper proposes MCFA, a new module that enhances translation-based context for sentence classification, outperforming previous models and being the first to utilize translations as domain-free context.

Findings

MCFA improves classification accuracy across multiple datasets.

Using translations as context is effective and domain-independent.

Naive translation features can decrease performance due to noise.

Abstract

In sentence classification tasks, additional contexts, such as the neighboring sentences, may improve the accuracy of the classifier. However, such contexts are domain-dependent and thus cannot be used for another classification task with an inappropriate domain. In contrast, we propose the use of translated sentences as context that is always available regardless of the domain. We find that naive feature expansion of translations gains only marginal improvements and may decrease the performance of the classifier, due to possible inaccurate translations thus producing noisy sentence vectors. To this end, we present multiple context fixing attachment (MCFA), a series of modules attached to multiple sentence vectors to fix the noise in the vectors using the other sentence vectors as context. We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets. We are the first to use translations as domain-free contexts for sentence classification.