IITP at WAT 2021: System description for English-Hindi Multimodal Translation Task

Abstract

Neural Machine Translation (NMT) is a predominant machine translation technology nowadays because of its end-to-end trainable flexibility. However, NMT still struggles to translate properly in low-resource settings specifically on distant language pairs. One way to overcome this is to use the information from other modalities if available. The idea is that despite differences in languages, both the source and target language speakers see the same thing and the visual representation of both the source and target is the same, which can positively assist the system. Multimodal information can help the NMT system to improve the translation by removing ambiguity on some phrases or words. We participate in the 8th Workshop on Asian Translation (WAT -2021) for English-Hindi multimodal translation task and achieve 42.47 and 37.50 BLEU points for Evaluation and Challenge subset, respectively.

Experiences of Adapting Multimodal Machine Translation Techniques for Hindi

“…It was observed that using text-based pre-trained models achieved better results for Hindi VG Test set compared to the multimodal model trained only on multimodal dataset [21]. However, it obtained lower results for the Challenge set.…”

Búsqueda semántica de sentencias judiciales usando técnicas actuales del NLP y métodos de recuperación de información

“…Dentro de los modelos relacionados directamente con la búsqueda y recuperación de información tenemos el reporte de anteligencia artificial para tareas de asistencia legal compartida [16]; este trabajo basado en el sistema penal Indiano utilizando:…”