1 citations · 1 across the 6 of their papers we have counts for
7 papers
Making LoRA Identifiable: Orthogonal Alignment for Continual Learning
Pratik Rakesh Singh, Mohammadi Zaki, Akash Saha +2
There is growing interest in applying Parameter-Efficient Fine-Tuning (PEFT) to Continual Learning, as it enables faster training, mitigates catastrophic forgetting, and facilitate…
Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion
Uday Allu, Abhivanth Sivaprakash, Pratik Singh +1
Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document formats -- PDFs, Word documents, presentations, and scans -- whose c…
Graph-Based Phonetic Error Correction of Noisy ASR
Pratik Rakesh Singh, Mohammadi Zaki, Aneesh Mukkamala +1
Automatic speech recognition (ASR) systems, despite low overall word error rates, produce residual lexical errors that disproportionately affect semantically critical tokens such a…
Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages
Pratik Rakesh Singh, Kritarth Prasad, Mohammadi Zaki +1
Translating multi-word expressions (MWEs) and idioms requires a deep understanding of the cultural nuances of both the source and target languages. This challenge is further amplif…
In-Domain African Languages Translation Using LLMs and Multi-armed Bandits
Pratik Rakesh Singh, Kritarth Prasad, Mohammadi Zaki +1
Neural Machine Translation (NMT) systems face significant challenges when working with low-resource languages, particularly in domain adaptation tasks. These difficulties arise due…
Faster Machine Translation Ensembling with Reinforcement Learning and Competitive Correction
Kritarth Prasad, Mohammadi Zaki, Pratik Singh +1
Ensembling neural machine translation (NMT) models to produce higher-quality translations than the individual models has been extensively studied. Recent methods typically empl…
Enhancing Entertainment Translation for Indian Languages using Adaptive Context, Style and LLMs
Pratik Rakesh Singh, Mohammadi Zaki, Pankaj Wasnik
We address the challenging task of neural machine translation (NMT) in the entertainment domain, where the objective is to automatically translate a given dialogue from a source la…