Papers by Amrith Krishna

18 papers
ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification (2025.findings-naacl)

Copied to clipboard

Challenge: Existing frameworks for large language models (LLMs) generate high-quality synthetic data that can be used to supplement training data or surpass crowd-sourced annotations.
Approach: They propose a framework that iteratively induces rules and generates synthetic data for text classification.
Outcome: The proposed framework outperforms existing models on in-context learning and fine-tuning settings by using augmented data.
ProoFVer: Natural Logic Theorem Proving for Fact Verification (2022.tacl-1)

Copied to clipboard

Challenge: Recent fact verification systems rely on neural network classifiers for veracity prediction, which lack explainability.
Approach: They propose a model that generates natural logic-based inferences as proofs using lexical mutations between spans in the claim and the evidence retrieved.
Outcome: The proposed model has highest label accuracy and second best score in the FEVER leaderboard.
Scaling Neural ITN for Numbers and Temporal Expressions in Tamil: Findings for an Agglutinative Low-resource Language (2023.emnlp-industry)

Copied to clipboard

Challenge: Inverse Text Normalisation (ITN) is a textrewriting task that converts verbalized text to written form.
Approach: They propose to use a seq2seq model, a non-autoregressive text editor and a sequence tagger + rules combination to fine-tune three pre-trained neural models.
Outcome: The proposed model improves with bootstrapping and data augmentation, and bootstrap alone shows a percentage improvement of 14.12 %.
Mahānāma: A Unique Testbed for Literary Entity Discovery and Linking (2025.emnlp-main)

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

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 .
IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery (2023.findings-emnlp)

Copied to clipboard

Challenge: Intent-related tasks are typically modeled as separate tasks, but a unified approach is proposed . INTENDD uses an entirely unsupervised contrastive learning strategy for representation learning .
Approach: They propose a unified approach to identifying intents from dialogue utterances . they propose an unsupervised contrastive learning strategy for representation learning .
Outcome: The proposed approach outperforms baselines on three intent-related tasks on multiple datasets.
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

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

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

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

Copied to clipboard

Challenge: SHR++ is designed to generate annotations for word segmentation, morphological parsing and dependency analysis tasks in Sanskrit.
Approach: They propose a web-based annotation framework, SHR++, for morpho-syntactic annotation of corpora in Sanskrit.
Outcome: The proposed framework reduces the time spent on the annotation tasks by 20.15 %.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations