Preparation of Sentiment tagged Parallel Corpus and Testing its effect on Machine Translation

TL;DR

This paper presents the creation of a sentiment-tagged English-Bengali parallel corpus and evaluates its impact on neural machine translation quality using automated and manual metrics.

Contribution

It introduces a sentiment-annotated parallel corpus and demonstrates its effect on improving neural machine translation performance.

Findings

Sentiment tagging enhances translation quality

Character-based NMT benefits from sentiment information

Automated and manual evaluations show improved results

Abstract

In the current work, we explore the enrichment in the machine translation output when the training parallel corpus is augmented with the introduction of sentiment analysis. The paper discusses the preparation of the same sentiment tagged English-Bengali parallel corpus. The preparation of raw parallel corpus, sentiment analysis of the sentences and the training of a Character Based Neural Machine Translation model using the same has been discussed extensively in this paper. The output of the translation model has been compared with a base-line translation model using automated metrics such as BLEU and TER as well as manually.