Search Results for author: Thoudam Doren Singh

Found 20 papers, 2 papers with code

The NITS-CNLP System for the Unsupervised MT Task at WMT 2020

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.

Translation Unsupervised Machine Translation

An Experiment on Speech-to-Text Translation Systems for Manipuri to English on Low Resource Setting

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

On the Transferability of Massively Multilingual Pretrained Models in the Pretext of the Indo-Aryan and Tibeto-Burman Languages

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.

Machine Translation Transfer Learning +1

Image Caption Generation Framework for Assamese News using Attention Mechanism

no code implementations ICON 2021 Ringki Das, Thoudam Doren Singh

Automatic caption generation is an artificial intelligence problem that falls at the intersection of computer vision and natural language processing.

Image Captioning

Unsupervised Neural Machine Translation for English and Manipuri

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.

Denoising Machine Translation +1

Low Resource Multimodal Neural Machine Translation of English-Hindi in News Domain

no code implementations MMTLRL (RANLP) 2021 Loitongbam Sanayai Meetei, Thoudam Doren Singh, Sivaji Bandyopadhyay

The parallel corpus is used to train the English-Hindi Neural Machine Translation (NMT) and an English-Hindi MMT system by incorporating the image feature paired with the corresponding parallel corpus.

Multimodal Machine Translation NMT +1

Multiple Captions Embellished Multilingual Multi-Modal Neural Machine Translation

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.

Cross-Lingual Transfer Machine Translation +2

An encoder-decoder based framework for hindi image caption generation

no code implementations Multimedia Tools and Applications 2021 Alok Singh, Thoudam Doren Singh, Sivaji Bandyopadhyay

The model is tested over Hindi visual genome dataset to validate the proposed approach’s performance and cross-verification is carried out for English captions with Flickr dataset.

Hindi Image Captioning

A Comprehensive Review on Recent Methods and Challenges of Video Description

no code implementations30 Nov 2020 Alok Singh, Thoudam Doren Singh, Sivaji Bandyopadhyay

In this work, we report a comprehensive survey on the phases of video description approaches, the dataset for video description, evaluation metrics, open competitions for motivating the research on the video description, open challenges in this field, and future research directions.

Machine Translation Video Description +1

Towards the Study of Morphological Processing of the Tangkhul Language

no code implementations29 Jun 2020 Mirinso Shadang, Navanath Saharia, Thoudam Doren Singh

There is no or little work on natural language processing of Tangkhul language.

Seq2Seq and Joint Learning Based Unix Command Line Prediction System

2 code implementations20 Jun 2020 Thoudam Doren Singh, Abdullah Faiz Ur Rahman Khilji, Divyansha, Apoorva Vikram Singh, Surmila Thokchom, Sivaji Bandyopadhyay

Experimental methods state that our model has achieved accuracy surpassing mixture of other techniques and adaptive command line interface mechanism as acclaimed in the past.

Recommendation Systems

NITS-VC System for VATEX Video Captioning Challenge 2020

no code implementations7 Jun 2020 Alok Singh, Thoudam Doren Singh, Sivaji Bandyopadhyay

Video captioning is process of summarising the content, event and action of the video into a short textual form which can be helpful in many research areas such as video guided machine translation, video sentiment analysis and providing aid to needy individual.

Machine Translation Sentiment Analysis +3

WAT2019: English-Hindi Translation on Hindi Visual Genome Dataset

no code implementations WS 2019 Loitongbam Sanayai Meetei, Thoudam Doren Singh, B, Sivaji yopadhyay

In this paper, we carried out an extensive comparison to evaluate the benefits of using a multimodal approach on translating text in English to a low resource language, Hindi as a part of WAT2019 shared task.

Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.