IITP-MT at CALCS2021: English to Hinglish Neural Machine Translation using Unsupervised Synthetic Code-Mixed Parallel Corpus

no code implementations • NAACL (CALCS) 2021 • Ramakrishna Appicharla, Kamal Kumar Gupta, Asif Ekbal, Pushpak Bhattacharyya

We submit a neural machine translation (NMT) system which is trained on the synthetic code-mixed (cm) English-Hinglish parallel corpus.

Machine Translation NMT +1

IITP-MT at WAT2021: Indic-English Multilingual Neural Machine Translation using Romanized Vocabulary

no code implementations • ACL (WAT) 2021 • Ramakrishna Appicharla, Kamal Kumar Gupta, Asif Ekbal, Pushpak Bhattacharyya

This paper describes the systems submitted to WAT 2021 MultiIndicMT shared task by IITP-MT team.

Machine Translation NMT +1

Product Review Translation: Parallel Corpus Creation and Robustness towards User-generated Noisy Text

no code implementations • ACL (ECNLP) 2021 • Kamal Kumar Gupta, Soumya Chennabasavaraj, Nikesh Garera, Asif Ekbal

We train an English–to–Hindi neural machine translation (NMT) system to translate the product reviews available on e-commerce websites.

Language Modelling Machine Translation +2

Modelling Source- and Target- Language Syntactic Information as Conditional Context in Interactive Neural Machine Translation

no code implementations • EAMT 2020 • Kamal Kumar Gupta, Rejwanul Haque, Asif Ekbal, Pushpak Bhattacharyya, Andy Way

In this study, we model source-language syntactic constituency parse and target-language syntactic descriptions in the form of supertags as conditional context for interactive prediction in neural MT (NMT).

Machine Translation NMT +1

IITP-MT at WAT2018: Transformer-based Multilingual Indic-English Neural Machine Translation System

no code implementations • PACLIC 2018 • Sukanta Sen, Kamal Kumar Gupta, Asif Ekbal, Pushpak Bhattacharyya

Machine Translation Translation

Pre-training Synthetic Cross-lingual Decoder for Multilingual Samples Adaptation in E-Commerce Neural Machine Translation

no code implementations • EAMT 2022 • Kamal Kumar Gupta, Soumya Chennabasavraj, Nikesh Garera, Asif Ekbal

We perform the experiments over eight low-resource and three high resource language pairs from the generic domain, and two language pairs from the product review domains.

Incremental Learning Machine Translation +2

IITP-MT System for Gujarati-English News Translation Task at WMT 2019

no code implementations • WS 2019 • Sukanta Sen, Kamal Kumar Gupta, Asif Ekbal, Pushpak Bhattacharyya

We describe our submission to WMT 2019 News translation shared task for Gujarati-English language pair.

Machine Translation NMT +1

Multilingual Unsupervised NMT using Shared Encoder and Language-Specific Decoders

no code implementations • ACL 2019 • Sukanta Sen, Kamal Kumar Gupta, Asif Ekbal, Pushpak Bhattacharyya

In this paper, we propose a multilingual unsupervised NMT scheme which jointly trains multiple languages with a shared encoder and multiple decoders.

Denoising NMT +1