no code implementations • loresmt (AACL) 2020 • Akshai Ramesh, Venkatesh Balavadhani parthasa, Rejwanul Haque, Andy Way
Statistical machine translation (SMT) which was the dominant paradigm in machine translation (MT) research for nearly three decades has recently been superseded by the end-to-end deep learning approaches to MT.
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).
no code implementations • AACL (WAT) 2020 • Prashanth Nayak, Rejwanul Haque, Andy Way
This paper describes the ADAPT Centre sub-missions to WAT 2020 for the English-to-Odia translation task.
no code implementations • AACL (WAT) 2020 • Wandri Jooste, Rejwanul Haque, Andy Way
In this paper we describe the ADAPT Centre’s submissions to the WAT 2020 document-level Business Scene Dialogue (BSD) Translation task.
no code implementations • AACL (WAT) 2020 • Akshai Ramesh, Venkatesh Balavadhani parthasa, Rejwanul Haque, Andy Way
Statistical machine translation (SMT) was the state-of-the-art in machine translation (MT) research for more than two decades, but has since been superseded by neural MT (NMT).
no code implementations • WMT (EMNLP) 2020 • Venkatesh Parthasarathy, Akshai Ramesh, Rejwanul Haque, Andy Way
This paper describes the ADAPT Centre’s submissions to the WMT20 News translation shared task for English-to-Tamil and Tamil-to-English.
no code implementations • WMT (EMNLP) 2020 • Prashant Nayak, Rejwanul Haque, Andy Way
This paper describes the ADAPT Centre’s submissions to the WMT20 Biomedical Translation Shared Task for English-to-Basque.
no code implementations • CSRNLP (LREC) 2022 • Yash Pilankar, Rejwanul Haque, Mohammed Hasanuzzaman, Paul Stynes, Pramod Pathak
Social media is not just meant for entertainment, it provides platforms for sharing information, news, facts and events.
no code implementations • MTSummit 2021 • Kamal Gupta, Dhanvanth Boppana, Rejwanul Haque, Asif Ekbal, Pushpak Bhattacharyya
It also improves the present state-of-the-art by 0. 35 and 0. 12 BLEU points for German-English and Spanish-English and respectively.
no code implementations • AMTA 2022 • Wandri Jooste, Andy Way, Rejwanul Haque, Riccardo Superbo
Knowledge distillation (KD) can be used to reduce model size and training time, without significant loss in performance.
1 code implementation • ICON 2020 • Raghvendra Pratap Singh, Rejwanul Haque, Mohammed Hasanuzzaman, Andy Way
Automatic recognition of customer complaints on products or services that they purchase can be crucial for the organisations, multinationals and online retailers since they can exploit this information to fulfil their customers’ expectations including managing and resolving the complaints.
no code implementations • WILDRE (LREC) 2022 • Sanket Sonu, Rejwanul Haque, Mohammed Hasanuzzaman, Paul Stynes, Pramod Pathak
Code-mixing (CM) is a process of mixing linguistic units such as words of two different languages.
no code implementations • ICON 2020 • Rejwanul Haque, Yasmin Moslem, Andy Way
This paper describes the ADAPT Centre’s submission to the Adap-MT 2020 AI Translation Shared Task for English-to-Hindi.
2 code implementations • 20 Dec 2023 • Yasmin Moslem, Rejwanul Haque, Andy Way
These findings emphasise the significance of fine-tuning efficient LLMs like Mistral 7B to yield high-quality zero-shot translations comparable to task-oriented models like NLLB 3. 3B.
1 code implementation • 30 Jan 2023 • Yasmin Moslem, Rejwanul Haque, John D. Kelleher, Andy Way
By feeding an LLM at inference time with a prompt that consists of a list of translation pairs, it can then simulate the domain and style characteristics.
1 code implementation • 23 Oct 2022 • Yasmin Moslem, Rejwanul Haque, Andy Way
Research on Machine Translation (MT) has achieved important breakthroughs in several areas.
2 code implementations • AMTA 2022 • Yasmin Moslem, Rejwanul Haque, John D. Kelleher, Andy Way
Preservation of domain knowledge from the source to target is crucial in any translation workflow.
1 code implementation • 1 Dec 2020 • Yasmin Moslem, Rejwanul Haque, Andy Way
Accordingly, we made use of a bidirectional LSTM language model (LM) for our context-sensitive spelling detection and correction model which is shown to have much control over the correction process.
no code implementations • WS 2020 • Rejwanul Haque, Yasmin Moslem, Andy Way
This paper describes the ADAPT Centre{'}s submission to STAPLE (Simultaneous Translation and Paraphrase for Language Education) 2020, a shared task of the 4th Workshop on Neural Generation and Translation (WNGT), for the English-to-Portuguese translation task.
no code implementations • 1 May 2020 • Andy Way, Rejwanul Haque, Guodong Xie, Federico Gaspari, Maja Popovic, Alberto Poncelas
Every day, more people are becoming infected and dying from exposure to COVID-19.
no code implementations • RANLP 2019 • Rejwanul Haque, Md Hasanuzzaman, Andy Way
Terminology translation plays a critical role in domain-specific machine translation (MT).