Indowordnets help in Indian Language Machine Translation

TL;DR

This study demonstrates that augmenting statistical machine translation models with Indowordnet synset entries significantly improves translation quality for resource-poor Indian languages, as shown by various evaluation metrics.

Contribution

The paper introduces a method of enhancing Indian language machine translation systems by integrating Indowordnet lexical database, leading to notable performance improvements.

Findings

Significant BLEU, METEOR, and TER score improvements after using Indowordnet.

Lexical database augmentation helps handle lexical ambiguity effectively.

Resource-efficient approach for improving translation in low-resource languages.

Abstract

Being less resource languages, Indian-Indian and English-Indian language MT system developments faces the difficulty to translate various lexical phenomena. In this paper, we present our work on a comparative study of 440 phrase-based statistical trained models for 110 language pairs across 11 Indian languages. We have developed 110 baseline Statistical Machine Translation systems. Then we have augmented the training corpus with Indowordnet synset word entries of lexical database and further trained 110 models on top of the baseline system. We have done a detailed performance comparison using various evaluation metrics such as BLEU score, METEOR and TER. We observed significant improvement in evaluations of translation quality across all the 440 models after using the Indowordnet. These experiments give a detailed insight in two ways : (1) usage of lexical database with synset mapping for resource poor languages (2) efficient usage of Indowordnet sysnset mapping. More over, synset mapped lexical entries helped the SMT system to handle the ambiguity to a great extent during the translation.