Avatar

Rudra Murthy V

Browses memes and watches series to escape from reality

Biography

About Me?

Hmmm, I am an atom in the universe who is trying his best at adulting..?
I wanted to become an over-achiever but ended up becoming an overthinker 🤷

I am currently working as a Research Scientist at IBM Research, India. I pursued my PhD from Center For Indian Language Technology lab headed by Professor. Pushpak Bhattacharyya. My area of interest is using Deep Multilingual Learning to various Natural Language Processing(NLP) tasks.

You can get to know more about my hobbies here and here.

Research Summary

Pinky: Gee, Brain, What do you want to do today?
Brain: The same thing we do everyday, Pinky. Borrow features from high-resource language to improve NLP Task performance in low-resource languages

I am broadly interested in Natural Language Processing (NLP) for low-resource languages, specifically Indic languages. Recently, I have garnered interest in Multilingual Learning for NLP in Low-Resource Languages. Low-resource languages do not have sufficient data, tools, and other resources (leading to data sparsity) to successfully train existing machine learning models for any NLP task. My current focus is on borrowing features (implicitly statistics) from one or more related languages (multilingual learning).

Interests

  • Natural Language Processing
  • Multilingual Learning

Education

  • PhD, 2020

    Indian Institute Of Technology, Bombay

  • ME in Data Mining, 2013

    Indian Institute Of Science, Bengaluru

Experience

 
 
 
 
 

Staff Research Scientist

IBM IRL Bangalore India

Aug 2022 – Present Bangalore
Natural Language Processing
 
 
 
 
 

Visiting Faculty

Indian Institute of Information Technology Lucknow, India

Jan 2022 – Jun 2022 Lucknow
Natural Language Processing
 
 
 
 
 

Research Scientist

IBM IRL Bangalore India

Apr 2020 – Aug 2022 Bangalore
Natural Language Processing
 
 
 
 
 

Internship

Microsoft India (R&D) Pvt. Ltd.

Nov 2019 – Feb 2020 Hyderabad
Improve Indic Language to Indic Language Translation
 
 
 
 
 

Internship

IBM IRL Bangalore India

May 2016 – Jul 2016 Bangalore
Study the performance of deep learning models for language identification task

Recent Posts

New Year

New Year

Fear

Ideal Time to Reply

Projects

Chirp: Geo-Aware Chat app for Android with Automatic Translation Support

Assume that you have visited to some tourist place and you are hungry. Basically you want to find some good hotel to have lunch. You can use some existing apps but what if the checked-in hotel is no longer there? Or you want to find someone from your place? Location-aware chat i.e, chatting with someone in your proximity comes in handy for you. Chirp is a location-aware chat that allows you to chat with someone in your proximity.

Information Extraction on SMS related to LG products

Worked on Information Extraction on SMS related to LG products consultancy project for LGsoft Bangalore from June 2017 to December 2017.

Recent & Upcoming Talks

Information Retrieval

Towards understanding and mitigating the hallucinations in NLP and Speech

This tutorial covers the hallucination phenomenon observed in generative AI models like autoregressive models and sequence-to-sequence …

Indian Language Computing: SIKER 2023

This talk is aimed to discuss the challenges and the research opportunities in Indic Language Computing. The talk begins with an …

Unsupervised Machine Translation Tutorial at ICON 2020

The focus of this tutorial is to cover the breadth of the literature on recent advances in Unsupervised Machine Translation. The tutorial will help the audience in getting started with unsupervised machine translation. The tutorial will span over three sections. In the first section, we will cover the fundamental concepts like cross-lingual embeddings, denoising auto-encoders, language model pre-training, Back Translation (BT), etc which are key to the success of Unsupervised Machine Translation. In the second section, the tutorial will provide a brief summary of recent works on unsupervised machine translation. The tutorial will cover both Phrase-Based Statistical Machine Translation systems as well as Neural Machine Translation systems. In the last section, we will talk about the limitations of the existing approaches for Unsupervised machine translation approaches and provide general guidelines for successful training of these systems. We also discuss case-studies from Indian languages and provide results obtained with U-MT over Indian language pairs. Finally, we talk about possible research directions.

Contact