Papers by Ganesh Ramakrishnan

Cross-Lingual Training for Automatic Question Generation (P19-1)

Challenge:	Existing approaches to domain-specific neural machine translation (NMT) are lexically constrained and draw from domain- specific dictionaries.
Approach:	They propose a lexically constrained neural machine translation system that disambiguates between multiple dictionary candidates.
Outcome:	The proposed system disambiguates between multiple candidate translations derived from dictionaries on English-Hindi, English-German, and English-French datasets.

Copied to clipboard

Vishwajeet Kumar, Nitish Joshi, Arijit Mukherjee, Ganesh Ramakrishnan, Preethi Jyothi

Cross-Lingual Transfer

Challenge:	Automatic question generation is a challenging problem in natural language understanding . manual curating a dataset of comparable size for a new language is tedious and expensive.
Approach:	They propose to reuse available large QG dataset in a secondary language to learn a QG model for a primary language.
Outcome:	The proposed model outperforms baseline models in Hindi and Chinese.

WARM: A Weakly (+Semi) Supervised Math Word Problem Solver (2022.coling-1)

Copied to clipboard

Oishik Chatterjee, Isha Pandey, Aashish Waikar, Vishwajeet Kumar, Ganesh Ramakrishnan

Low-Resource NLP

Challenge:	Existing approaches to solving math word problems require full supervision in the form of intermediate equations.
Approach:	They propose a weakly supervised model that requires only the final answer as supervision to solve math word problems.
Outcome:	The proposed model achieves accuracy gains of 4.5% and 32% over current weakly-supervised methods on standard Math23K and AllArith datasets.

Rolling Out Data Quality Overnight, without losing the plot: A Multi-Agent System for Speech Data Quality Management (2026.findings-acl)

Copied to clipboard

Rishabh Kumar, Abhinav Painuli, Chriss Philip Saji, Devesh Soni, Amrith Krishna, Ganesh Ramakrishnan

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

Challenge:	Using automation to improve quality management is expensive and resource-intensive for speech datasets.
Approach:	They propose a natural language-driven agentic framework that compiles user requirements into dependency-aware DAG workflows over modular tools for audio, transcript, and metadata verification.
Outcome:	The proposed framework achieves 80-90% agreement with expert verification while requiring less than 20% of the cost and time of manual QC.

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

Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming (2022.findings-acl)

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

Ayush Maheshwari, Krishnateja Killamsetty, Ganesh Ramakrishnan, Rishabh Iyer, Marina Danilevsky, Lucian Popa

Semi-Supervised Data Programming with Subset Selection (2021.findings-acl)

Challenge:	supervised machine learning requires large amounts of labeled data to train models.
Approach:	They propose a framework to generate human-interpretable labeling functions . they propose to learn a model on the same labeled dataset and unlabeled data .
Outcome:	The proposed framework outperforms prior approaches on several text classification datasets.

Copied to clipboard

Ayush Maheshwari, Oishik Chatterjee, Krishnateja Killamsetty, Ganesh Ramakrishnan, Rishabh Iyer

Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification (2021.eacl-main)

Challenge:	Several approaches to improve annotation cost have been proposed to use large amounts of labelled training data.
Approach:	They propose a semi-supervised data programming paradigm that uses weak supervision and semi-supervised loss functions to augment small amounts of labelled data with a large unlabelled dataset.
Outcome:	The proposed framework outperforms the current state-of-the-art on seven publicly available datasets.

Copied to clipboard

Soumya Chatterjee, Ayush Maheshwari, Ganesh Ramakrishnan, Saketha Nath Jagarlapudi

Information Retrieval

Challenge:	Existing methods for hierarchical multi-label classification do not assume label hierarchy exists.
Approach:	They propose to jointly learn the classifier parameters as well as the label embeddings . they propose to use hyperbolic embeddables to gain better generalisation over the labels .
Outcome:	The proposed method achieves state-of-the-art generalization on benchmarks and is more accurate than existing methods.

GuideQ: Framework for Guided Questioning for progressive informational collection and classification (2025.findings-naacl)

Copied to clipboard

Priya Mishra, Suraj Racha, Kaustubh Ponkshe, Adit Akarsh, Ganesh Ramakrishnan

Information Retrieval

Challenge:	Using a new multilingual dataset, we examine how LLMs can be used to represent factual knowledge across languages.
Approach:	They propose a methodology to measure the extent of representation sharing across languages by repurposing knowledge editing methods.
Outcome:	The proposed model can answer a question consistently across languages and can store the answers in a shared representation for several languages.

Few shot chain-of-thought driven reasoning to prompt LLMs for open-ended medical question answering (2024.findings-emnlp)

Copied to clipboard

Saeel Nachane, Ojas Gramopadhye, Prateek Chanda, Ganesh Ramakrishnan, Kshitij Jadhav, Yatin Nandwani, Dinesh Raghu, Sachindra Joshi

Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights (2026.findings-acl)

Challenge:	Large Language models (LLMs) are increasingly utilized in the healthcare sector for query-related tasks.
Approach:	They propose a modified version of the MedQA-USMLE dataset, named MEDQA-OPEN, which contains open-ended medical questions without options to mimic clinical scenarios.
Outcome:	The proposed approach outperforms the state-of-the-art 5-shot CoT-based prompt by exploring multiple differential diagnoses and narrowing down to a final diagnosis using MCQ-ELIMINATIVE.

Copied to clipboard

Maharaj Brahma, N J Karthika, Rajat Verma, Nagasai Saketh Naidu, Rohit Saluja, Maunendra Sankar Desarkar, Ganesh Ramakrishnan

Syntactic Text Processing

Challenge:	Existing tokenizers are often skewed towards high-resource languages limiting their effectiveness for linguistically diverse and morphologically rich languages.
Approach:	They evaluate multilingual tokenization across 17 Indic languages spanning 11 scripts and two language families.
Outcome:	The proposed method improves tokenization quality and vocabulary size in 17 languages . poor tokenization can lead to increase in sequence lengths, fragment meaningful units, weaken model's ability to capture linguistic structure and semantics.

Entity Resolution and Location Disambiguation in the Ancient Hindu Temples Domain using Web Data (N18-5)

Copied to clipboard

Ayush Maheshwari, Vishwajeet Kumar, Ganesh Ramakrishnan, J. Saketha Nath

Visual Data in NLP

Challenge:	Existing systems for resolving entities and disambiguating locations based on publicly available web data are challenging because of the limited information available on the Web.
Approach:	They propose a system for resolving entities and disambiguating locations based on publicly available web data in the domain of ancient Hindu Temples.
Outcome:	The proposed system resolves entities and disambiguates locations with high confidence using grammar rules and clustering algorithms.

Meta-Learning for Effective Multi-task and Multilingual Modelling (2021.eacl-main)

Copied to clipboard

Ishan Tarunesh, Sushil Khyalia, Vishwajeet Kumar, Ganesh Ramakrishnan, Preethi Jyothi

DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation (2023.acl-long)

Challenge:	Existing studies on multitask and multilingual learning have shown that learning cross-lingual embeddings can benefit multiple tasks and languages.
Approach:	They propose a meta-learning approach to learn interactions between tasks and languages . they also investigate the role of different sampling strategies used during meta-learned model .
Outcome:	The proposed model improves on five different tasks and six different languages from the XTREME multilingual benchmark dataset.

Copied to clipboard

Suraj Kothawade, Anmol Mekala, D.Chandra Sekhara Hetha Havya, Mayank Kothyari, Rishabh Iyer, Ganesh Ramakrishnan, Preethi Jyothi

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

Challenge:	State-of-the-art automatic speech recognition systems exhibit disparate performance on varying speech accents.
Approach:	They propose to use submodular mutual information to find the most informative set of utterances matching a target accent within a fixed budget.
Outcome:	The proposed model is 3-5 times more label-efficient on the Indic-TTS and L2 datasets than other methods.

Copied to clipboard

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

INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models (2023.findings-emnlp)

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

H S V N S Kowndinya Renduchintala, Krishnateja Killamsetty, Sumit Bhatia, Milan Aggarwal, Ganesh Ramakrishnan, Rishabh Iyer, Balaji Krishnamurthy

Vocabulary Matters: A Simple yet Effective Approach to Paragraph-level Question Generation (2020.aacl-main)

Challenge:	Pre-trained language models have a remarkable improvement in generalization capability . however, this leads to prohibitively long training times and a detrimental environmental impact .
Approach:	They propose to use submodular optimization to select highly informative subsets of training data to train multiple PTLMs using only fractions of data.
Outcome:	The proposed framework achieves 99% of the performance of fully-trained models using only fraction of training data.

Copied to clipboard

Vishwajeet Kumar, Manish Joshi, Ganesh Ramakrishnan, Yuan-Fang Li

Text Generation

Challenge:	Current neural network-based questions generation techniques take only one or two sentences as input.
Approach:	They propose a simple yet effective technique for question generation from paragraphs . they augment a sequence-to-sequence QG model with dynamic, paragraph-specific dictionary .
Outcome:	The proposed model outperforms state-of-the-art systems in question generation from paragraphs in automatic and human evaluation.

ParaQG: A System for Generating Questions and Answers from Paragraphs (D19-3)

Copied to clipboard

Vishwajeet Kumar, Sivaanandh Muneeswaran, Ganesh Ramakrishnan, Yuan-Fang Li

Text Generation

Challenge:	Automated question generation systems generate questions from sentences and paragraphs . manual generation of questions is labour-intensive as it requires reading, parsing and understanding of long passages of text.
Approach:	They propose a web-based system for generating questions from sentences and paragraphs . paraQG provides an interactive interface for a user to select answers with visual insights .
Outcome:	The proposed system generates questions from sentences and paragraphs on a web-based platform.

A Benchmark and Dataset for Post-OCR text correction in Sanskrit (2022.findings-emnlp)

Copied to clipboard

Ayush Maheshwari, Nikhil Singh, Amrith Krishna, Ganesh Ramakrishnan

Syntactic Text Processing

Challenge:	Sanskrit is a classical language with 30 million manuscripts available for digitisation . however, it is considered to be low-resource when it comes to available digital resources.
Approach:	They propose to use a post-OCR text correction dataset to correct errors from OCR predictions from 30 different books in the Indian subcontinent.
Outcome:	The proposed model outperforms OCR models on graphemic and lexical levels and shows that it is more accurate than previous models.

SMART: Submodular Data Mixture Strategy for Instruction Tuning (2024.findings-acl)

Copied to clipboard

H S V N S Kowndinya Renduchintala, Sumit Bhatia, Ganesh Ramakrishnan

Post-ASR Correction in Hindi: Comparing Language Models and Large Language Models in Low-Resource Scenarios (2026.eacl-short)

Challenge:	Existing methods for fine tuning language models are manual or rely on intuition.
Approach:	They propose a method which uses a submodular function to assign importance scores to tasks and then use them to determine mixture weights.
Outcome:	The proposed method outperforms traditional methods such as examples proportional mixing and equal mixing.

Copied to clipboard

Rishabh Kumar, Amrith Krishna, Ganesh Ramakrishnan, Preethi Jyothi

Samayik: A Benchmark and Dataset for English-Sanskrit Translation (2024.lrec-main)

Challenge:	Automatic Speech Recognition (ASR) systems for low-resource languages produce erroneous transcripts due to limited annotated data and linguistic complexity.
Approach:	They compare language models and large language models for post-ASR correction in Hindi . they observe a scaling trend under zero-shot ICL where mid-sized LLMs degrade performance before marginal recovery at extreme scales.
Outcome:	The proposed model outperforms larger models in both fine-tuning and in-context learning settings.

Copied to clipboard

Ayush Maheshwari, Ashim Gupta, Amrith Krishna, Atul Kumar Singh, Ganesh Ramakrishnan, Anil Kumar Gourishetty, Jitin Singla

Beyond Common Words: Enhancing ASR Cross-Lingual Proper Noun Recognition Using Large Language Models (2024.findings-emnlp)

Challenge:	Existing Sanskrit corpora focus on poetry and offer limited coverage of contemporary written materials.
Approach:	They release a dataset of 53,000 parallel English-Sanskrit sentences . they use spoken content that covers contemporary world affairs and interpretations .
Outcome:	a new dataset of 53,000 parallel English-Sanskrit sentences is released . the dataset outperforms existing models trained on older classical-era poetry datasets .

Copied to clipboard

Rishabh Kumar, Sabyasachi Ghosh, Ganesh Ramakrishnan

Speech & Audio in NLP

Challenge:	In this work, we address the challenge of cross-lingual proper noun recognition in automatic speech recognition systems where proper nodes in an utterance may originate from a language different from the language in which the ASR system is trained.
Approach:	They propose a dictionary-based method to correct ASR predictions in a large language model .
Outcome:	The proposed method significantly reduces word error rates across cross-lingual proper noun recognition tasks involving three secondary languages.

Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training (2022.findings-emnlp)

Copied to clipboard

Ashish Mittal, Durga Sivasubramanian, Rishabh Iyer, Preethi Jyothi, Ganesh Ramakrishnan

Rule Augmented Unsupervised Constituency Parsing (2021.findings-acl)

Challenge:	Existing DSS algorithms for RNN-T have a high cost and performance degradation.
Approach:	They propose a distributable DSS algorithm for RNN-T that can be used to train a subset of training data.
Outcome:	The proposed algorithm achieves between 3x to 6x speedup with only a small accuracy degradation even in settings where the training data is corrupted with noise.

Copied to clipboard

Atul Sahay, Anshul Nasery, Ayush Maheshwari, Ganesh Ramakrishnan, Rishabh Iyer

LexGen: Domain-aware Multilingual Lexicon Generation (2025.acl-long)

Challenge:	Recent studies have shown that unsupervised parsing methods do not learn meaningful semantics (not even simple grammar)
Approach:	They propose an approach that utilizes very generic linguistic knowledge of the language present in the form of syntactic grammar rules and is independent of the base system.
Outcome:	The proposed model is independent of the base system and takes advantage of syntactic grammar rules.

Copied to clipboard

Ayush Maheshwari, Atul Kumar Singh, N J Karthika, Krishnakant Bhatt, Preethi Jyothi, Ganesh Ramakrishnan

INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages (2025.findings-naacl)

Challenge:	Lexicon generation is a key task in specialized domains due to infrequent usage of terms . a new model is proposed to generate dictionary words for 6 Indian languages .
Approach:	They propose a model to generate dictionary words for 6 Indian languages in the multi-domain setting.
Outcome:	The proposed model generalizes to unseen domains and unsealed languages.

Copied to clipboard

Abhishek Kumar Singh, Vishwajeet Kumar, Rudra Murthy, Jaydeep Sen, Ashish Mittal, Ganesh Ramakrishnan

SPEAR : Semi-supervised Data Programming in Python (2022.emnlp-demos)

Challenge:	Large Language Models perform well on unseen tasks in English, but their abilities in non-English languages are less explored due to limited benchmarks and training data.
Approach:	They propose to release a large dataset for context-grounded question answering in 11 major Indian languages.
Outcome:	The Indic-QA Benchmark compared large datasets of large LLMs on extractive and abstractive tasks in 11 major Indian languages.

Copied to clipboard

Guttu Abhishek, Harshad Ingole, Parth Laturia, Vineeth Dorna, Ayush Maheshwari, Ganesh Ramakrishnan, Rishabh Iyer