84 citations · 109 across the 26 of their papers we have counts for
27 papers
Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations
Karthika Nhayakkat, Rajat Verma, Maharaj Brahma +4
Large Language Models (LLMs) demonstrate strong multilingual reasoning performance, yet their robustness to semantics-preserving structural variation remains underexplored, particu…
AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
Sravan Gorugantu, Mohd Nauman, Sravan Gvm +8
Current large language models excel at broad, general-purpose tasks, but consistently underperform when exposed to highly specialized domains that require deep cultural, linguistic…
DIWALI: Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context
Pramit Sahoo, Maharaj Brahma, Maunendra Sankar Desarkar
Large language models (LLMs) are widely used in various tasks and applications. However, despite their wide capabilities, they are shown to lack cultural alignment \citep{ryan-etal…
The Art of Breaking Words: Rethinking Multilingual Tokenizer Design
Aamod Thakur, Ajay Nagpal, Atharva Savarkar +7
While model architecture and training objectives are well-studied, tokenization, particularly in multilingual contexts, remains a relatively neglected aspect of Large Language Mode…
Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights
Maharaj Brahma, N J Karthika, Rajat Verma +4
Tokenization plays a pivotal role in NLP and is fundamental to training language models. However, existing tokenizers are often skewed towards high-resource languages, limiting the…
MorphTok: Morphologically Grounded Tokenization for Indian Languages
Maharaj Brahma, N J Karthika, Atul Singh +5
Tokenization is a crucial step in NLP, especially with the rise of large language models (LLMs), impacting downstream performance, computational cost, and efficiency. Existing LLMs…
BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation
Suvodip Dey, Maunendra Sankar Desarkar
The standard language modeling (LM) loss by itself has been shown to be inadequate for effective dialogue modeling. As a result, various training approaches, such as auxiliary loss…
NLIP_Lab-IITH Multilingual MT System for WAT24 MT Shared Task
Maharaj Brahma, Pramit Sahoo, Maunendra Sankar Desarkar
This paper describes NLIP Lab's multilingual machine translation system for the WAT24 shared task on multilingual Indic MT task for 22 scheduled languages belonging to 4 language f…
NLIP_Lab-IITH Low-Resource MT System for WMT24 Indic MT Shared Task
Pramit Sahoo, Maharaj Brahma, Maunendra Sankar Desarkar
In this paper, we describe our system for the WMT 24 shared task of Low-Resource Indic Language Translation. We consider eng {as, kha, lus, mni} as participating…
Transformer based Multitask Learning for Image Captioning and Object Detection
Debolena Basak, P. K. Srijith, Maunendra Sankar Desarkar
In several real-world scenarios like autonomous navigation and mobility, to obtain a better visual understanding of the surroundings, image captioning and object detection play a c…
Trie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes
Kaushal Kumar Maurya, Maunendra Sankar Desarkar, Manish Gupta +1
Query auto-completion (QAC) aims to suggest plausible completions for a given query prefix. Traditionally, QAC systems have leveraged tries curated from historical query logs to su…
CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages
Kaushal Kumar Maurya, Rahul Kejriwal, Maunendra Sankar Desarkar +1
We address the task of machine translation (MT) from extremely low-resource language (ELRL) to English by leveraging cross-lingual transfer from 'closely-related' high-resource lan…
ComplAI: Theory of A Unified Framework for Multi-factor Assessment of Black-Box Supervised Machine Learning Models
Arkadipta De, Satya Swaroop Gudipudi, Sourab Panchanan +1
The advances in Artificial Intelligence are creating new opportunities to improve lives of people around the world, from business to healthcare, from lifestyle to education. For ex…
On Text Style Transfer via Style Masked Language Models
Sharan Narasimhan, Pooja Shekar, Suvodip Dey +1
Text Style Transfer (TST) is performable through approaches such as latent space disentanglement, cycle-consistency losses, prototype editing etc. The prototype editing approach, w…
DialoGen: Generalized Long-Range Context Representation for Dialogue Systems
Suvodip Dey, Maunendra Sankar Desarkar, Asif Ekbal +1
Long-range context modeling is crucial to both dialogue understanding and generation. The most popular method for dialogue context representation is to concatenate the last- utt…
HyperHawkes: Hypernetwork based Neural Temporal Point Process
Manisha Dubey, P. K. Srijith, Maunendra Sankar Desarkar
Temporal point process serves as an essential tool for modeling time-to-event data in continuous time space. Despite having massive amounts of event sequence data from various doma…
Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances
Suvodip Dey, Ramamohan Kummara, Maunendra Sankar Desarkar
Dialogue State Tracking (DST) is primarily evaluated using Joint Goal Accuracy (JGA) defined as the fraction of turns where the ground-truth dialogue state exactly matches the pred…
Meta-X: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation
Kaushal Kumar Maurya, Maunendra Sankar Desarkar
Recently, the NLP community has witnessed a rapid advancement in multilingual and cross-lingual transfer research where the supervision is transferred from high-resource languages…
Graph Neural Network Enhanced Language Models for Efficient Multilingual Text Classification
Samujjwal Ghosh, Subhadeep Maji, Maunendra Sankar Desarkar
Online social media works as a source of various valuable and actionable information during disasters. These information might be available in multiple languages due to the nature…
Supervised Graph Contrastive Pretraining for Text Classification
Samujjwal Ghosh, Subhadeep Maji, Maunendra Sankar Desarkar
Contrastive pretraining techniques for text classification has been largely studied in an unsupervised setting. However, oftentimes labeled data from related tasks which share labe…
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation
Kaushal Kumar Maurya, Maunendra Sankar Desarkar, Yoshinobu Kano +1
Despite the recent advancement in NLP research, cross-lingual transfer for natural language generation is relatively understudied. In this work, we transfer supervision from high r…
Unsupervised Domain Adaptation with Global and Local Graph Neural Networks in Limited Labeled Data Scenario: Application to Disaster Management
Samujjwal Ghosh, Subhadeep Maji, Maunendra Sankar Desarkar
Identification and categorization of social media posts generated during disasters are crucial to reduce the sufferings of the affected people. However, lack of labeled data is a s…
Walk in Wild: An Ensemble Approach for Hostility Detection in Hindi Posts
Chander Shekhar, Bhavya Bagla, Kaushal Kumar Maurya +1
As the reach of the internet increases, pejorative terms started flooding over social media platforms. This leads to the necessity of identifying hostile content on social media pl…
Coarse and Fine-Grained Hostility Detection in Hindi Posts using Fine Tuned Multilingual Embeddings
Arkadipta De, Venkatesh E, Kaushal Kumar Maurya +1
Due to the wide adoption of social media platforms like Facebook, Twitter, etc., there is an emerging need of detecting online posts that can go against the community acceptance st…