Skip to content
conftrace_
2019 EMNLP EMNLP 2019

CVIT’s submissions to WAT-2019

Abstract

AbstractThis paper describes the Neural Machine Translation systems used by IIIT Hyderabad (CVIT-MT) for the translation tasks part of WAT-2019. We participated in tasks pertaining to Indian languages and submitted results for English-Hindi, Hindi-English, English-Tamil and Tamil-English language pairs. We employ Transformer architecture experimenting with multilingual models and methods for low-resource languages.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - multilingual model

Authors

Jerin Philip, Shashank Siripragada, Upendra Kumar, Vinay Namboodiri, C V Jawahar

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation

Keywords

transformer architecture neural machine translation low-resource language indian language multilingual model
Download PDF

More from EMNLP 2019

All EMNLP 2019 papers →
Neural Machine Translation System using a Content-equivalently Translated Parallel Corpus for the Newswire Translation Tasks at WAT 2019
Facebook AI’s WAT19 Myanmar-English Translation Task Submission
Combining Translation Memory with Neural Machine Translation
LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019
Long Warm-up and Self-Training: Training Strategies of NICT-2 NMT System at WAT-2019
Supervised neural machine translation based on data augmentation and improved training & inference process