no code implementations • ACL (WAT) 2021 • Sahinur Rahman Laskar, Abdullah Faiz Ur Rahman Khilji, Darsh Kaushik, Partha Pakray, Sivaji Bandyopadhyay
Neural machine translation attains a state-of-the-art approach in machine translation, but it requires adequate training data, which is a severe problem for low-resource language pairs translation.
no code implementations • WMT (EMNLP) 2020 • Sahinur Rahman Laskar, Abdullah Faiz Ur Rahman Khilji, Partha Pakray, Sivaji Bandyopadhyay
We have participated in WMT20 shared task of similar language translation on Hindi-Marathi pair.
no code implementations • WILDRE (LREC) 2022 • Vanlalmuansangi Khenglawt, Sahinur Rahman Laskar, Santanu Pal, Partha Pakray, Ajoy Kumar Khan
Multilingual country like India has an enormous linguistic diversity and has an increasing demand towards developing language resources such that it will outreach in various natural language processing applications like machine translation.
no code implementations • AACL (WAT) 2020 • Sahinur Rahman Laskar, Abdullah Faiz Ur Rahman Khilji, Partha Pakray, Sivaji Bandyopadhyay
Moreover, the utilization of monolingual data in the pre-training step can improve the performance of the system for low resource language translations.
no code implementations • WAT 2022 • Sahinur Rahman Laskar, Pankaj Dadure, Riyanka Manna, Partha Pakray, Sivaji Bandyopadhyay
Automatic translation of one natural language to another is a popular task of natural language processing.
no code implementations • WAT 2022 • Sahinur Rahman Laskar, Rahul Singh, Md Faizal Karim, Riyanka Manna, Partha Pakray, Sivaji Bandyopadhyay
Machine translation translates one natural language to another, a well-defined natural language processing task.
no code implementations • MTSummit 2021 • Sahinur Rahman Laskar, Abdullah Faiz Ur Rahman Khilji Darsh Kaushik, Partha Pakray, Sivaji Bandyopadhyay
In machine translation, corpus preparation is one of the crucial tasks, particularly for lowresource pairs.
no code implementations • WAT 2022 • Sahinur Rahman Laskar, Riyanka Manna, Partha Pakray, Sivaji Bandyopadhyay
In the domain of natural language processing, machine translation is a well-defined task where one natural language is automatically translated to another natural language.
no code implementations • loresmt (AACL) 2020 • Sahinur Rahman Laskar, Abdullah Faiz Ur Rahman Khilji, Partha Pakray, Sivaji Bandyopadhyay
The availability of a parallel corpus in low resource language pairs is one of the challenging tasks in MT.
no code implementations • loresmt (AACL) 2020 • Sahinur Rahman Laskar, Abdullah Faiz Ur Rahman Khilji, Partha Pakray, Sivaji Bandyopadhyay
The corpus preparation is one of the important challenging task for the domain of machine translation especially in low resource language scenarios.
no code implementations • WMT (EMNLP) 2021 • Sahinur Rahman Laskar, Bishwaraj Paul, Prottay Kumar Adhikary, Partha Pakray, Sivaji Bandyopadhyay
The neural machine translation approach has gained popularity in machine translation because of its context analysing ability and its handling of long-term dependency issues.
no code implementations • WS 2019 • Sahinur Rahman Laskar, Rohit Pratap Singh, Partha Pakray, B, Sivaji yopadhyay
With the widespread use of Machine Trans-lation (MT) techniques, attempt to minimizecommunication gap among people from di-verse linguistic backgrounds.
no code implementations • WS 2019 • Sahinur Rahman Laskar, Partha Pakray, B, Sivaji yopadhyay
Also, we have achieved BLEU score 53. 7 (Hindi to Nepali) and 49. 1 (Nepali to Hindi) in contrastive system type.