Papers by V.S.D.S.Mahesh Akavarapu
Cognate Transformer for Automated Phonological Reconstruction and Cognate Reflex Prediction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Phonological reconstruction is one of the central problems in historical linguistics where a proto-word of an ancestral language is determined from the observed cognate words of daughter languages. |
| Approach: | They propose to use a protein language model to train on multiple sequence alignments to train a model on phonological reconstruction. |
| Outcome: | The proposed model outperforms existing models on cognate reflex prediction task. |
A Likelihood Ratio Test of Genetic Relationship among Languages (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing tests of significance for bilateral comparisons are infeasible by design or yield false positives when applied to groups of languages or language families. |
| Approach: | They propose a likelihood ratio test to determine if given languages are related based on the proportion of invariant character sites in aligned wordlists. |
| Outcome: | The proposed test solves the problem of false positives on some language families. |
Hard to Be Heard: Phoneme-Level ASR Analysis of Phonologically Complex, Low-Resource Endangered Languages (2026.findings-acl)
Copied to clipboard
| Challenge: | a phoneme-level analysis of automatic speech recognition (ASR) is performed on two low-resource, typologically complex East Caucasian languages. |
| Approach: | They propose a phoneme-level analysis of automatic speech recognition for two East Caucasian languages, Archi and Rutul. |
| Outcome: | The proposed model improves on existing models and improves in low-resource settings. |
A Case Study of Cross-Lingual Zero-Shot Generalization for Classical Languages in LLMs (2025.findings-acl)
Copied to clipboard
V.S.D.S.Mahesh Akavarapu, Hrishikesh Terdalkar, Pramit Bhattacharyya, Shubhangi Agarwal, Dr. Vishakha Deulgaonkar, Chaitali Dangarikar, Pralay Manna, Arnab Bhattacharya
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable generalization capabilities across diverse tasks and languages. |
| Approach: | They focus on named entity recognition and machine translation into English to examine factors affecting cross-lingual zero-shot generalization. |
| Outcome: | The proposed models perform better than fine-tuned baselines on out-of-domain data, but smaller models struggle with niche or abstract entity types. |
Automated Cognate Detection as a Supervised Link Prediction Task with Cognate Transformer (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing methods for cognate identification are based on distributions of phonemes and make little use of cognacy labels. |
| Approach: | They propose a transformer-based architecture inspired by computational biology for automated cognate detection. |
| Outcome: | The proposed architecture performs better than existing methods with increased supervision. |