no code implementations • MMTLRL (RANLP) 2021 • Baban Gain, Dibyanayan Bandyopadhyay, Asif Ekbal
In this paper, we evaluate the existing methods on Hindi and report our findings.
no code implementations • LREC 2022 • Dibyanayan Bandyopadhyay, Arkadipta De, Baban Gain, Tanik Saikh, Asif Ekbal
We perform experiments on English-Hindi language pairs in the cross-lingual setting to find out that our novel loss formulation could enhance the performance of the baseline model by up to 2%.
1 code implementation • AMTA 2022 • Baban Gain, Ramakrishna Appicharla, Asif Ekbal, Muthusamy Chelliah, Soumya Chennabasavraj, Nikesh Garera
Chatbots are used in various sectors such as banking, healthcare, e-commerce, etc, and are mainly available in English.
no code implementations • 13 Dec 2023 • Samrat Mukherjee, Dibyanayan Bandyopadhyay, Baban Gain, Asif Ekbal
Diabetic Retinopathy (DR) is a prevalent illness associated with Diabetes which, if left untreated, can result in irreversible blindness.
1 code implementation • 23 Oct 2023 • Baban Gain, Ramakrishna Appicharla, Soumya Chennabasavaraj, Nikesh Garera, Asif Ekbal, Muthusamy Chelliah
Translating questions using Neural Machine Translation (NMT) poses more challenges, especially in noisy environments, where the grammatical correctness of the questions is not monitored.
1 code implementation • 30 Aug 2023 • Baban Gain, Dibyanayan Bandyopadhyay, Samrat Mukherjee, Chandranath Adak, Asif Ekbal
Interestingly, the effect of visual context varies with source text noise: no visual context works best for non-noisy translations, cropped image features are optimal for low noise, and full image features work better in high-noise scenarios.
no code implementations • 11 Aug 2023 • Ramakrishna Appicharla, Baban Gain, Santanu Pal, Asif Ekbal
In this paper, we further explore this idea by evaluating with context-aware pronoun translation test set by training multi-encoder models trained on three different context settings viz, previous two sentences, random two sentences, and a mix of both as context.
no code implementations • ACL (WAT) 2021 • Baban Gain, Dibyanayan Bandyopadhyay, Asif Ekbal
Neural Machine Translation (NMT) is a predominant machine translation technology nowadays because of its end-to-end trainable flexibility.
no code implementations • 24 May 2021 • Baban Gain, Dibyanayan Bandyopadhyay, Arkadipta De, Tanik Saikh, Asif Ekbal
The outcomes of this track would be helpful for the automation of the working process of the Indian Judiciary System.
1 code implementation • 17 Apr 2021 • Baban Gain, Dibyanayan Bandyopadhyay, Tanik Saikh, Asif Ekbal
We make use of different Information Retrieval(IR) and deep learning based approaches to tackle these problems.
no code implementations • WS 2019 • Dibyanayan Bandyopadhyay, Baban Gain, Tanik Saikh, Asif Ekbal
We submitted five system results in each of the NLI and RQE tasks, and four system results for the QA task.