no code implementations • ICON 2021 • Loitongbam Sanayai Meetei, Laishram Rahul, Alok Singh, Salam Michael Singh, Thoudam Doren Singh, Sivaji Bandyopadhyay
Based on this dataset, a benchmark evaluation is reported for the Manipuri-English Speech-to-Text translation using two approaches: 1) a pipeline model consisting of ASR (Automatic Speech Recognition) and Machine translation, and 2) an end-to-end Speech-to-Text translation.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • ICON 2021 • Salam Michael Singh, Loitongbam Sanayai Meetei, Alok Singh, Thoudam Doren Singh, Sivaji Bandyopadhyay
In recent times, machine translation models can learn to perform implicit bridging between language pairs never seen explicitly during training and showing that transfer learning helps for languages with constrained resources.
no code implementations • ICON 2021 • Alok Singh, Loitongbam Sanayai Meetei, Salam Michael Singh, Thoudam Doren Singh, Sivaji Bandyopadhyay
Describing a video is a challenging yet attractive task since it falls into the intersection of computer vision and natural language generation.
Ranked #1 on Video Captioning on Hindi MSR-VTT
no code implementations • WMT (EMNLP) 2020 • Salam Michael Singh, Thoudam Doren Singh, Sivaji Bandyopadhyay
We describe NITS-CNLP’s submission to WMT 2020 unsupervised machine translation shared task for German language (de) to Upper Sorbian (hsb) in a constrained setting i. e, using only the data provided by the organizers.
no code implementations • MMTLRL (RANLP) 2021 • Salam Michael Singh, Loitongbam Sanayai Meetei, Thoudam Doren Singh, Sivaji Bandyopadhyay
In this work, we utilise the multiple captions from the Multi-30K dataset to increase the lexical diversity aided with the cross-lingual transfer of information among the languages in a multilingual setup.
no code implementations • loresmt (AACL) 2020 • Salam Michael Singh, Thoudam Doren Singh
Availability of bitext dataset has been a key challenge in the conventional machine translation system which requires surplus amount of parallel data.
no code implementations • 29 Feb 2024 • Prottay Kumar Adhikary, Aseem Srivastava, Shivani Kumar, Salam Michael Singh, Puneet Manuja, Jini K Gopinath, Vijay Krishnan, Swati Kedia, Koushik Sinha Deb, Tanmoy Chakraborty
Further, expert evaluation reveals that Mistral supersedes both MentalLlama and MentalBART based on six parameters -- affective attitude, burden, ethicality, coherence, opportunity costs, and perceived effectiveness.