Papers by Pawan Goyal

CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text (2023.findings-emnlp)

Challenge:	High lexical variation, ambiguous references, and long-range dependencies make entity resolution in literary texts particularly challenging.
Approach:	They present a large-scale dataset for end-to-end Entity Discovery and Linking (EDL) in Sanskrit.
Outcome:	The proposed dataset is aligned with an English knowledge base to support cross-lingual linking.

Copied to clipboard

Abhilash Nandy, Manav Kapadnis, Pawan Goyal, Niloy Ganguly

TransLIST: A Transformer-Based Linguistically Informed Sanskrit Tokenizer (2022.findings-emnlp)

Challenge:	Existing methods to solve procedural reasoning tasks are limited by the prior art.
Approach:	They propose a domain-specific, continual pre-training framework that learns from a large set of procedural recipes.
Outcome:	The proposed framework outperforms baselines on recipes (in-domain) but is able to generalize to open-domain procedural NLP tasks.

Copied to clipboard

Jivnesh Sandhan, Rathin Singha, Narein Rao, Suvendu Samanta, Laxmidhar Behera, Pawan Goyal

Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling (2024.naacl-long)

Challenge:	Existing approaches to SWS fail when encountering out-of-vocabulary tokens . lexicon driven approaches fail when dealing with out- of-vocal tokens, authors say .
Approach:	They propose a novel lexicon-driven shallow parser that takes into account sandhi phenomenon . they propose linguistically informed Sanskrit tokenizer module that encodes character input .
Outcome:	The proposed system outperforms the current state-of-the-art system by 7.2 points absolute gain on the benchmark datasets.

Copied to clipboard

Subhendu Khatuya, Rajdeep Mukherjee, Akash Ghosh, Manjunath Hegde, Koustuv Dasgupta, Niloy Ganguly, Saptarshi Ghosh, Pawan Goyal

Responsible & Trustworthy NLP

Challenge:	Existing methods to automatically annotate relevant numerals (GAAP metrics) occurring in financial documents are not cost-effective nor scalable.
Approach:	They propose a generative paradigm for annotating GAAP metrics with XBRL tags using metric metadata and a parameter efficient model using LoRA.
Outcome:	The proposed model outperforms baseline models on two financial numeric labeling datasets and outperformed several strong baseline models.

Poetry to Prose Conversion in Sanskrit as a Linearisation Task: A Case for Low-Resource Languages (P19-1)

Copied to clipboard

Amrith Krishna, Vishnu Sharma, Bishal Santra, Aishik Chakraborty, Pavankumar Satuluri, Pawan Goyal

Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs (2026.eacl-long)

Challenge:	Obtaining the proper word ordering, called as the prose ordering, from a verse is often considered a task which requires linguistic expertise.
Approach:	They propose a word ordering (linearisation) task that ignores the word arrangement at the verse side.
Outcome:	The proposed model outperforms current models in word ordering for the translation task in Sanskrit.

Copied to clipboard

Manoj Balaji Jagadeeshan, Samarth Bhatia, Pretam Ray, Harshul Raj Surana, Akhil Rajeev P, Priya Mishra, Annarao Kulkarni, Ganesh Ramakrishnan, Prathosh Ap, Pawan Goyal

SanskritShala: A Neural Sanskrit NLP Toolkit with Web-Based Interface for Pedagogical and Annotation Purposes (2023.acl-demo)

Challenge:	Large language models are capable of creative generation tasks but prominently for high-resource languages.
Approach:	They propose to use large language models for structured poetry generation in Sanskrit . their constrained decoding method achieves 99.86% syntactic accuracy .
Outcome:	The proposed model outperforms the existing model in generating metrically valid Sanskrit poetry.

Copied to clipboard

Jivnesh Sandhan, Anshul Agarwal, Laxmidhar Behera, Tushar Sandhan, Pawan Goyal

Financial Numeric Extreme Labelling: A dataset and benchmarking (2023.findings-acl)

Challenge:	SanskritShala is a neural-based Sanskrit NLP toolkit that is available as a web-based application .
Approach:	They propose a neural Sanskrit NLP toolkit that facilitates linguistic analyses for word segmentation, morphological tagging, dependency parsing, and compound type identification.
Outcome:	The proposed toolkit reports state-of-the-art performance on benchmark datasets . it is built with easy-to-use interactive data annotation features .

Copied to clipboard

Soumya Sharma, Subhendu Khatuya, Manjunath Hegde, Afreen Shaikh, Koustuv Dasgupta, Pawan Goyal, Niloy Ganguly

Can Network Embedding of Distributional Thesaurus Be Combined with Word Vectors for Better Representation? (N18-1)

Challenge:	In 2019, the SEC mandates that all public companies file periodic financial statements that should contain numerals annotated with a particular label.
Approach:	They propose to use a dataset to automate the assignment of a label to a particular numeral span in a sentence from an extremely large label set.
Outcome:	The proposed solution outperforms the previous approaches but is less frequent than the pipeline solution.

Copied to clipboard

Abhik Jana, Pawan Goyal

EduVidQA: Generating and Evaluating Long-form Answers to Student Questions based on Lecture Videos (2025.emnlp-main)

Challenge:	Distributed representations of words learned from text have proved to be successful in various natural language processing tasks.
Approach:	They propose to embed a distributional thesaurus network into dense word vectors and compare them to state-of-the-art word representations.
Outcome:	The proposed representations improve performance against state-of-the-art word representations even without handcrafted lexical resources.

Copied to clipboard

Sourjyadip Ray, Shubham Sharma, Somak Aditya, Pawan Goyal

Breaking Token Into Concepts: Exploring Extreme Compression in Token Representation Via Compositional Shared Semantics (2025.findings-emnlp)

Challenge:	This paper explores using Multimodal Large Language Models (MLLMs) to respond to student questions from online lectures . MLLM is a novel question answering task of real world significance .
Approach:	They propose to use Multimodal Large Language Models to automatically respond to student questions from online lectures by using a dataset of 5252 question-answer pairs from 296 computer science videos.
Outcome:	The proposed model can fine tune and fine tune questions from 296 computer science videos and show that students' preferences are important to the task.

Copied to clipboard

Kavin R V, Pawan Goyal

Using Sentence-level Classification Helps Entity Extraction from Material Science Literature (2022.lrec-1)

Challenge:	Standard language models employ unique, monolithic embeddings for each token, limiting their ability to capture multifaceted meanings.
Approach:	They propose a compositional structure that accumulates diverse semantic facets for tokens . they apply this representational scheme to standard transformer architectures and a biomedical domain benchmark .
Outcome:	The proposed representational scheme achieves extreme compression in embedding parameters while maintaining >95% task performance relative to the base model.

Copied to clipboard

Ankan Mullick, Shubhraneel Pal, Tapas Nayak, Seung-Cheol Lee, Satadeep Bhattacharjee, Pawan Goyal

Chat-Ghosting: Methods for Auto-Completion in Dialog Systems (2026.eacl-long)

Challenge:	Material Science research articles are a rich source of information about entities related to material science.
Approach:	They propose to use a sentence-level classifier to identify sentences containing at least one entity mention . they then apply the information extraction models only on the filtered sentences to extract various entities of interest.
Outcome:	The proposed model improves the F1 score by more than 4% . the proposed model removes redundant sentences from the articles that contain informative entities .

Copied to clipboard

Anubhab Mandal, Sandeep Mishra, Bishal Santra, Tushar Abhishek, Pawan Goyal, Manish Gupta

Dialogue Systems & Conversational Agents

Challenge:	Ghosting is a type-ahead completion task that predicts a user's intended input for inline query auto-completion (QAC).
Approach:	They propose to use ghosting to predict a user's intended input for inline query auto-completion by suggesting completions to incomplete queries.
Outcome:	The proposed method outperforms deep learning and deep learning methods with and without dialog context for ghosting.

Hierarchical Transformer for Task Oriented Dialog Systems (2021.naacl-main)

Copied to clipboard

Bishal Santra, Potnuru Anusha, Pawan Goyal

Natural Language Interfaces

Challenge:	Existing models for dialog generation are challenging to train using the standard Seq2Seq models.
Approach:	They propose a framework for Hierarchical Transformer Encoders that can be morphed into any hierarchical transformer by using specially designed attention masks and positional encodings.
Outcome:	The proposed framework can be morphed into any hierarchical encoder, including HRED and HIBERT like models, by using specially designed attention masks and positional encodings.

How Robust Are the QA Models for Hybrid Scientific Tabular Data? A Study Using Customized Dataset (2024.lrec-main)

Copied to clipboard

Akash Ghosh, Venkata Sahith Bathini, Niloy Ganguly, Pawan Goyal, Mayank Singh

Robustness in NLP

Challenge:	Existing tabular QA models are lacking in understanding their robustness on scientific information.
Approach:	They propose a dataset to assess the robustness of tabular QA models on scientific hybrid tabular data.
Outcome:	The proposed model performs well on scientific tables and text, while the best score is 0.462.

Network Features Based Co-hyponymy Detection (L18-1)

Copied to clipboard

Abhik Jana, Pawan Goyal

Challenge:	Existing methods to detect lexical relations have been used to identify them in both supervised and unsupervised ways.
Approach:	They propose to use distributional semantic models to detect co-hyponymy relation with high accuracy and various network measures to perform better or at par with the state-of-the-art models.
Outcome:	The proposed model performs better or at par with the state-of-the-art models.

IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning (2024.acl-long)

Copied to clipboard

Abhinav Joshi, Shounak Paul, Akshat Sharma, Pawan Goyal, Saptarshi Ghosh, Ashutosh Modi

Reasoning

Challenge:	Legal systems worldwide struggle with exponentially growing legal cases in various courts.
Approach:	They propose a benchmark for Indian legal text understanding and reasoning task that includes domain-specific tasks that address different aspects of the legal system.
Outcome:	The proposed benchmark for Indian legal text understanding and reasoning aims to address the gap between models and the ground truth.

A Framework to Generate High-Quality Datapoints for Multiple Novel Intent Detection (2022.findings-naacl)

Copied to clipboard

Ankan Mullick, Sukannya Purkayastha, Pawan Goyal, Niloy Ganguly

Sentiment Analysis

Challenge:	Existing approaches to detect novel intents have been tested in the last decade.
Approach:	They propose a framework to detect multiple novel intents with budgeted human annotation cost.
Outcome:	The proposed framework outperforms baseline methods in terms of accuracy and F1-score on a set of benchmark datasets.

IL-PCSR: Legal Corpus for Prior Case and Statute Retrieval (2025.emnlp-main)

Copied to clipboard

Shounak Paul, Dhananjay Ghumare, Pawan Goyal, Saptarshi Ghosh, Ashutosh Modi

Information Retrieval

Challenge:	Existing models for identifying/retrieving relevant statutes and prior cases/precedents are inherently related, e.g., similar cases tend to cite similar statutes due to similar factual situation.
Approach:	They propose a corpus that provides a common testbed for developing models that exploit the dependence between the two tasks.
Outcome:	The proposed corpus exploits the dependence between the two retrieval tasks and provides a baseline model for the two tasks.

Order-Based Pre-training Strategies for Procedural Text Understanding (2024.naacl-short)

Copied to clipboard

Abhilash Nandy, Yash Kulkarni, Pawan Goyal, Niloy Ganguly

ArgGen: Prompting Text Generation Models for Document-Level Event-Argument Aggregation (2022.findings-aacl)

Challenge:	Procedural text is difficult to understand due to the changing attributes of entities in the context.
Approach:	They propose sequence-based pre-training methods to enhance procedural understanding in natural language processing by using ordered instructions to guide individuals through a task.
Outcome:	The proposed methods improve on two datasets in the datasets NPN-Cooking and ProPara domains respectively.

Copied to clipboard

Debanjana Kar, Sudeshna Sarkar, Pawan Goyal

Representation Learning for Conversational Data using Discourse Mutual Information Maximization (2022.naacl-main)

Challenge:	Existing discourse-level information extraction tasks are extractive in nature, but extracting information from larger bodies of discourse-like documents requires more natural language understanding and reasoning capabilities.
Approach:	They propose a conditional text generation approach which generates consolidated event-arguments at a document-level with minimal loss of information.
Outcome:	The proposed approach generates document-level argument spans in a low-resource and zero-shot setting and can be leveraged in other related multilingual text generation tasks.

Copied to clipboard

Bishal Santra, Sumegh Roychowdhury, Aishik Mandal, Vasu Gurram, Atharva Naik, Manish Gupta, Pawan Goyal

Dialogue Systems & Conversational Agents

Challenge:	Existing language modeling pretraining objectives do not take structural information of conversational text into account.
Approach:	They propose a structure-aware Mutual Information based loss-function DMI for training dialog-representation models that captures the inherent uncertainty in response prediction.
Outcome:	The proposed model outperforms strong baseline models on nine diverse tasks.

Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification (2025.findings-acl)

Copied to clipboard

Subhendu Khatuya, Shashwat Naidu, Saptarshi Ghosh, Pawan Goyal, Niloy Ganguly

Information Retrieval

Challenge:	Existing approaches to multi-label text classification are limited by textual data.
Approach:	They propose a domain-agnostic generative model framework for multi-label text classification that generates predefined label descriptions and matches them to predefined labels.
Outcome:	The proposed model achieves 13.94% and 24.85% performance over all datasets.

Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation (2022.aacl-main)

Copied to clipboard

Abhay Shukla, Paheli Bhattacharya, Soham Poddar, Rajdeep Mukherjee, Kripabandhu Ghosh, Pawan Goyal, Saptarshi Ghosh

Summarization

Challenge:	Summarization of legal case judgement documents is a challenging problem in Legal NLP.
Approach:	They propose to use extractive and abstractive summarization methods to evaluate legal document summarizing systems.
Outcome:	The proposed methods have been evaluated on three legal summarization datasets.

CONTRASTE: Supervised Contrastive Pre-training With Aspect-based Prompts For Aspect Sentiment Triplet Extraction (2023.findings-emnlp)

Copied to clipboard

Rajdeep Mukherjee, Nithish Kannen, Saurabh Pandey, Pawan Goyal

Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit (2020.emnlp-main)

Challenge:	Existing studies on Aspect Sentiment Triplet Extraction focus on developing more efficient techniques for the task, but our proposed approach can improve the downstream performance of multiple ABSA tasks simultaneously.
Approach:	They propose a novel approach that uses contrastive learning to enhance the ASTE performance by masked sentiments.
Outcome:	The proposed approach improves the performance of multiple ABSA tasks simultaneously.

Copied to clipboard

Amrith Krishna, Ashim Gupta, Deepak Garasangi, Pavankumar Satuluri, Pawan Goyal

On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings (P19-1)

Challenge:	Morphologically rich languages benefit from joint processing of morphology and syntax, as compared to pipeline architectures.
Approach:	They propose a graph-based model for joint morphological parsing and dependency parser in Sanskrit using the Energy based model framework.
Outcome:	The proposed model outperforms standalone morphological parsers in morphology and syntax parsing, and in dependency parser.

Copied to clipboard

Abhik Jana, Dima Puzyrev, Alexander Panchenko, Pawan Goyal, Chris Biemann, Animesh Mukherjee

Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents (2025.emnlp-main)

Challenge:	idiomatic phrases have a non-compositional meaning, meanings of which can be derived from constituents and their grammatical relations.
Approach:	They propose to combine hierarchical and distributional information to blend hierarchic and distribution-based hierarchies to detect compositionality for noun phrases.
Outcome:	The proposed technique achieves significant improvements over state-of-the-art models based on distributional information and a weighted average of the distributional similarity and p-like function.

Copied to clipboard

Ankan Mullick, Sombit Bose, Rounak Saha, Ayan Kumar Bhowmick, Aditya Vempaty, Prasenjit Dey, Ravi Kokku, Pawan Goyal, Niloy Ganguly

Text Generation

Challenge:	Unlike highlights (fragmented key points) and traditional summaries, spotlights selectively emphasize intriguing content to foster deeper reader engagement with the source material.
Approach:	They propose a novel paradigm for information extraction that selectively emphasizes intriguing content to foster deeper reader engagement with the source material.
Outcome:	The proposed model improves readability and boosts engagement value of the original document.

Automatic Charge Identification from Facts: A Few Sentence-Level Charge Annotations is All You Need (2020.coling-main)

Copied to clipboard

Shounak Paul, Pawan Goyal, Saptarshi Ghosh

Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing (2023.eacl-main)

Challenge:	Existing work on charge-side representations but not much effort has been made in improving fact-side models.
Approach:	They propose to use sentence-level charge labels as an auxiliary task coupled with the main task of document-level charging identification in a multi-task learning framework to improve fact-side representations.
Outcome:	The proposed model outperforms a large number of baselines on a document-level charge identification task.

Copied to clipboard

Jivnesh Sandhan, Laxmidhar Behera, Pawan Goyal

Responsible & Trustworthy NLP

Challenge:	Several strategies have been proposed to enhance performance in low-resource scenarios.
Approach:	They propose to use 5 low-resource strategies for dependency parsing for multiple languages . they use ensembled approach on 7 UD low-rsource languages based on their results .
Outcome:	The proposed approach improves on a low-resource language Sanskrit.

Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights (2021.findings-acl)

Copied to clipboard

Devaraja Adiga, Rishabh Kumar, Amrith Krishna, Preethi Jyothi, Ganesh Ramakrishnan, Pawan Goyal

A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages (2021.eacl-srw)

Challenge:	In this paper, we propose the first large scale study of automatic speech recognition in Sanskrit . we focus on the impact of unit selection in San's ASR systems .
Approach:	They propose a large scale study of automatic speech recognition in Sanskrit . they propose syllable level unit selection that captures character sequences .
Outcome:	The proposed model captures character sequences from one vowel in the word to the next vowela.

Copied to clipboard

Jivnesh Sandhan, Amrith Krishna, Ashim Gupta, Laxmidhar Behera, Pawan Goyal

ILSIC: Corpora for Identifying Indian Legal Statutes from Queries by Laymen (2026.findings-eacl)

Challenge:	Neural dependency parsing has been a success for many domains and languages, but the bottleneck of massive labelled data limits its effectiveness for low resource languages.
Approach:	They propose to use morphological knowledge to improve dependency parsing for morphology rich languages in a low-resource setting to perform experiments.
Outcome:	The proposed method achieves an average gain of 2 points (UAS) and 3.6 points (LAS) on 10 MRLs in low-resource settings.

Copied to clipboard

Shounak Paul, Raghav Dogra, Pawan Goyal, Saptarshi Ghosh

Challenge:	Existing studies have focused on the use of court judgments as input for legal Statute Identification (LSI) however, there is little research to explore the differences between court and laypeople data for LSI.
Approach:	They create a corpus of laypeople queries covering 500+ statutes from Indian law . they use court case judgements to compare between the two datasets .
Outcome:	The proposed corpus of laypeople queries covers 500+ statutes from Indian law . the results show that models trained on court judgements are ineffective .

***YesBut***: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models (2024.emnlp-main)

Copied to clipboard

Abhilash Nandy, Yash Agarwal, Ashish Patwa, Millon Das, Aman Bansal, Ankit Raj, Pawan Goyal, Niloy Ganguly

WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pages (C18-1)

Challenge:	Existing Vision-Language models perform poorly on satirical image detecting tasks . satire and humor are powerful tools to highlight issues, provoke thought, and encourage critical perspective .
Approach:	They propose to use a dataset to evaluate satirical images and satire images to detect satiric images . they also propose to generate the reason behind the image being satiral by generating one half of the image to be satisfying .
Outcome:	The proposed dataset contains 2547 images, 1084 satirical and 1463 non-satirically, with different artistic styles.

Copied to clipboard

Abhik Jana, Pranjal Kanojiya, Pawan Goyal, Animesh Mukherjee

Text Classification

Challenge:	Existing methods to enhance Wikipedia's reference section are not effective.
Approach:	They propose a two-step approach that leverages the wikilinks present in a scientific Wikipedia target page and recommends highly relevant references to be included in that target page appropriately and automatically borrowed from the reference section of the wikipedia links.
Outcome:	The proposed approach achieves a notably good performance on two datasets from Computer Science and Physics.

Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit (D18-1)

Copied to clipboard

Amrith Krishna, Bishal Santra, Sasi Prasanth Bandaru, Gaurav Sahu, Vishnu Dutt Sharma, Pavankumar Satuluri, Pawan Goyal

Building a Word Segmenter for Sanskrit Overnight (L18-1)

Challenge:	a structured prediction framework is proposed to solve word segmentation and morphological tagging tasks in a free word order language.
Approach:	They propose a structured prediction framework that jointly solves word segmentation and morphological tagging tasks in Sanskrit.
Outcome:	The proposed model outperforms the state of the art with an F-Score of 96.92 (percentage improvement of 7.06%) while using less than one tenth of the task-specific training data.

Copied to clipboard

Vikas Reddy, Amrith Krishna, Vishnu Sharma, Prateek Gupta, Vineeth M R, Pawan Goyal

A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents (2024.findings-emnlp)

Challenge:	Sanskrit word segmentation is challenging due to the issue of Sandhi . digitisation efforts have made the manuscripts available in the public domain .
Approach:	They propose a deep sequence to sequence model that takes only the sandhied string as input and predicts the unsandhized string.
Outcome:	The proposed model improves on the current state of the art by 16.79% . the system can be trained "overnight" and be used for production .

Copied to clipboard

Ankan Mullick, Sombit Bose, Abhilash Nandy, Gajula Chaitanya, Pawan Goyal

Sentiment Analysis

Challenge:	Existing research focuses on simple queries with a single intent, lacking effective systems for handling complex queries with multiple intents.
Approach:	They propose a multi-label multi-class intent detection dataset curated from existing benchmarks and a pointer network-based architecture to extract intent spans and detect multiple intents with coarse and fine-grained labels in the form of sextuplets.
Outcome:	The proposed system outperforms baseline approaches in terms of accuracy and F1-score.

ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts (2022.emnlp-main)

Copied to clipboard

Rajdeep Mukherjee, Abhinav Bohra, Akash Banerjee, Soumya Sharma, Manjunath Hegde, Afreen Shaikh, Shivani Shrivastava, Koustuv Dasgupta, Niloy Ganguly, Saptarshi Ghosh, Pawan Goyal

Text Generation

Challenge:	ECTSum is a dataset for bullet-point summarization of earnings calls hosted by publicly traded companies.
Approach:	They propose a dataset with transcripts of earnings calls and bullet point summaries derived from Reuters articles.
Outcome:	The proposed dataset compares transcripts of earnings calls hosted by publicly traded companies with experts-written bullet point summaries derived from Reuters articles .

On The Persona-based Summarization of Domain-Specific Documents (2024.findings-acl)

Copied to clipboard

Ankan Mullick, Sombit Bose, Rounak Saha, Ayan Bhowmick, Pawan Goyal, Niloy Ganguly, Prasenjit Dey, Ravi Kokku

Summarization

Challenge:	In an ever-expanding world of domain-specific knowledge, summarization of information is a complex task . persona-based summarizing of domain specific information by humans is deemed not preferred .
Approach:	They propose a framework for efficient training of a small foundation LLM on a healthcare corpus.
Outcome:	The proposed framework fine-tunes a domain-specific small foundation LLM using a healthcare corpus and evaluates its quality using AI-based critiquing.

Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection (2025.emnlp-main)

Copied to clipboard

Ankan Mullick, Saransh Sharma, Abhik Jana, Pawan Goyal

Sentiment Analysis

Challenge:	a new study examines the effectiveness of large language models and non-LLMs in multimodal intent detection . large-scale multimodal data integrations include text, audio, and visual inputs .
Approach:	They propose a framework to debias multimodal intent detection datasets by using human evaluation.
Outcome:	The proposed framework debiases the datasets and shows that mistral-7B outperforms most competitive models by approximately 9% on MIntRec-1 and 4% on MIndRec2.0.

Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages? (2022.coling-1)

Copied to clipboard

Aniruddha Roy, Rupak Kumar Thakur, Isha Sharma, Ashim Gupta, Amrith Krishna, Sudeshna Sarkar, Pawan Goyal

Low-Resource NLP

Challenge:	Existing approaches to few-shot Question Generation (QG) are limited and require manual annotation.
Approach:	They propose to use multilingual BERT to perform few-shot question generation with cross-lingual transfer.
Outcome:	The proposed model improves in few-shot QG and human evaluation confirms it.

Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs (D19-1)

Copied to clipboard

Soumya Sharma, Bishal Santra, Abhik Jana, Santosh Tokala, Niloy Ganguly, Pawan Goyal

Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs (2026.eacl-industry)

Challenge:	Recent studies have shown that structured domain knowledge can be used for textual inference tasks in the medical domain.
Approach:	They propose to integrate structured domain knowledge into a knowledge graph for the Medical NLI task.
Outcome:	The proposed approach improves the baseline BioELMo architecture for the Medical NLI task.

Copied to clipboard

Sandeep Mishra, Devichand Budagam, Anubhab Mandal, Bishal Santra, Pawan Goyal, Manish Gupta

Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval (2025.emnlp-main)

Challenge:	a task that grounds predictions in multimodal context is essential for chatbots, chatbot systems and healthcare consultations.
Approach:	They propose a task that grounds predictions in multimodal context to better capture user intent.
Outcome:	The proposed task can be used to predict upcoming characters in live chats using partially typed text and visual cues.

Copied to clipboard

Subhendu Khatuya, Shashwat Naidu, Pawan Goyal, Niloy Ganguly

Low-Resource NLP

Challenge:	Numerical reasoning remains a challenging area for large language models (LLMs).
Approach:	They propose a two-step framework to enhance LLM's capabilities in financial numerical reasoning by using a generative retriever and context-aware program of thought prompting.
Outcome:	The proposed model surpasses previous benchmarks with execution accuracy improvements of 5.98% and 4.05%, respectively.

ERVQA: A Dataset to Benchmark the Readiness of Large Vision Language Models in Hospital Environments (2024.emnlp-main)

Copied to clipboard

Sourjyadip Ray, Kushal Gupta, Soumi Kundu, Dr Kasat, Somak Aditya, Pawan Goyal

Using Distributional Thesaurus Embedding for Co-hyponymy Detection (2020.lrec-1)

Challenge:	a global shortage of healthcare workers has demanded the development of smart healthcare assistants.
Approach:	They analyze the healthcare knowledge of existing Large Vision Language Models (LVLMs) using an annotated open-ended task.
Outcome:	The study analyzes the knowledge of large vision language models using open-ended questions . the results highlight the need for specialized, domain-specific solutions .

Copied to clipboard

Abhik Jana, Nikhil Reddy Varimalla, Pawan Goyal

Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework (2021.findings-emnlp)

Challenge:	Existing methods to detect lexical relations among distributionally similar words have been proposed to solve this problem.
Approach:	They propose to use distributional semantic models to detect co-hyponymy relations by embedding them into the distributional thesaurus.
Outcome:	The proposed model outperforms the state-of-the-art models for binary classification of co-hyponymy vs. hypernymy, as well as co-meronymy by huge margins.

Copied to clipboard

Abhilash Nandy, Soumya Sharma, Shubham Maddhashiya, Kapil Sachdeva, Pawan Goyal, NIloy Ganguly

Biomedical Relation Classification by single and multiple source domain adaptation (D19-62)

Challenge:	EMQAP is an automated question answering system for electronics devices . it uses a supervised multitask learning framework to identify the section in the E-manual where the answer can be found and the exact answer span within that section.
Approach:	They develop an algorithm to exploit data from E-manuals and pretrain RoBERTa on it.
Outcome:	The proposed algorithm improves ROUGE-L F1 scores over most competitive baseline.

Copied to clipboard

Sinchani Chakraborty, Sudeshna Sarkar, Pawan Goyal, Mahanandeeshwar Gattu

Intent Identification and Entity Extraction for Healthcare Queries in Indic Languages (2023.findings-eacl)

Challenge:	Existing supervised systems are highly data-driven and require a lot of effort to label data for a new domain.
Approach:	They propose to transfer knowledge from one or more related source domains to another domain to improve relation classification.
Outcome:	The proposed model outperforms neural-network based models on biomedical datasets and with contextualized embeddings on 3 biomedically-relevant datasets.

Copied to clipboard

Ankan Mullick, Ishani Mondal, Sourjyadip Ray, Raghav R, G Chaitanya, Pawan Goyal

CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages (2024.emnlp-main)

Challenge:	Currently, there is a lack of data and technology for resource-poor languages in developing countries like India.
Approach:	They propose to use two different datasets to analyze query intents and entities in healthcare.
Outcome:	The proposed model is useful to identify query intents and entities in real-world scenarios.

Copied to clipboard

Pretam Ray, Jivnesh Sandhan, Amrith Krishna, Pawan Goyal

Responsible & Trustworthy NLP

Challenge:	Neural dependency parsing has achieved remarkable performance for low resource morphologically rich languages.
Approach:	They propose a self-supervised learning method to make the model robust to word order variations.
Outcome:	The proposed model shows a substantial gain of 3.03/2.95 points in 7 relatively free word order languages when compared to the best performing baseline.

A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in Sanskrit (2022.coling-1)

Copied to clipboard

Jivnesh Sandhan, Ashish Gupta, Hrishikesh Terdalkar, Tushar Sandhan, Suvendu Samanta, Laxmidhar Behera, Pawan Goyal

PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction (2021.emnlp-main)

Challenge:	Previously, compounding is a problem of identifying semantic relations between components of a word.
Approach:	They propose a multi-task learning architecture which incorporates contextual information and enriches syntactic information using morphological tagging and dependency parsing as auxiliary tasks.
Outcome:	The proposed architecture shows 6.1 points accuracy and 7.7 points (F1-score) absolute gain in English and Marathi languages.

Copied to clipboard

Rajdeep Mukherjee, Tapas Nayak, Yash Butala, Sourangshu Bhattacharya, Pawan Goyal

SHR++: An Interface for Morpho-syntactic Annotation of Sanskrit Corpora (2020.lrec-1)

Challenge:	Existing methods for tagging opinion triplets fail to capture the strong interdependence between the three opinion factors, whereas grid tabbing fails to capture span-level semantics while predicting sentiment between an aspect-opinion pair.
Approach:	They propose a tagging-free approach to extracting opinion triplets using a pointer network decoding framework that captures the interdependence between the three elements of an opinion triple.
Outcome:	The proposed architecture captures the interdependence between the aspect and opinion triplets while predicting their connecting sentiment.

Copied to clipboard

Amrith Krishna, Shiv Vidhyut, Dilpreet Chawla, Sruti Sambhavi, Pawan Goyal