Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Zero-Shot Learning: “The Seen, The Unseen and The Unknown”
Published:
In this blog, I try to encapsulate a fundamental idea of zero-shot learning using a simple analogy that was inspired by a couple of conversations with my co-workers. This is the blog link
Talking ML with Sahil Khose
Published:
ML can often come pre-packaged with a lot of intimidation for complete beginners. To break down what it is like to be passionate about this field, I was interviewed by thesilentgeeks. The talk was about my internship and student project experiences, the importance of research papers and to help break down the reader’s barrier of apprehension.
[Paper] Semi-Supervised Classification and Segmentation on High Resolution Aerial Images
Published:
In this story, Semi-Supervised Classification and Segmentation on High Resolution Aerial Images, by the authors: Sahil Khose, Abhiraj Tiwari and Ankita Ghosh, is presented. This is the blog link
Probability Paradoxes?
Published:
In this story, I try to explain the famous Monty Hall Problem and the Bertrand’s Box Problem This is the blog link
MANAS Taskphase: What did I learn?
Published:
In this story, I go through the things that I learnt in my taskphase of Project MANAS. This is a technical overview of the 5 month rigorous journey starting from sitting for the entrance interview to making it in the team. This is the blog link
MANAS Taskphase: Journey.
Published:
This is a personal overview of a 5 month rigorous journey starting from sitting for the entrance interview to making it in the Project MANAS team. This is the blog link
Machine Learning.
Published:
In this blog, I explain the basics of Machine Learning and the types of ML. Starting out with my own personal journey in ML and DL as a freshman in college, I wrote this blog in a hope to document my process. This is the blog link
publications
Occupational Gender Stereotypes in Indian Languages
Published in WiNLP, EMNLP, 2021
- Neeraja Kirtane and Tanvi Anand
Devised a metric to calculate bias in gendered languages like Hindi and Marathi. Used this metric on ULMFiT language model and quantified the bias present.
Download here
Transformer based ensemble for emotion detection
Published in WASSA, ACL, 2022
Aditya Kane, Shantanu Patankar, Neeraja Kirtane, Sahil Khose
Developed ensemble based solution consisting of multiple ELECTRA and BERT models. Proposed methods for synthetically generating datasets to mitigate class imbalance. Studied the behaviour of our models on various raw and synthetically generated datasets.
Download here
Mitigating gender stereotypes in Hindi and Marathi
Published in GeBNLP, NAACL, 2022
- Neeraja Kirtane and Tanvi Anand
Created a dataset of occupations and emotion in Hindi and Marathi. Proposed methods to quantify the bias in the word embeddings. Used existing methods to debias the embeddings.
Download here
ReGrAt: Regularization in graphs using attention mechanism to handle class imbalance
Published in GCLR workshop, AAAI, 2023
- Neeraja Kirtane, Jeshuren Chelladurai, Balaraman Ravindran, Ashish Tendulkar
Used attention mechanism to tackle imbalance. Used a custom loss function by adding a regularizer that handles imbalance. Got better results than already existing methods.
Download here
Hidden Voices: Reducing gender data gap, one Wikipedia article at a time
Published in Wiki Workshop, 2023
Neeraja Kirtane, Anuraag Shankar, Chelsi Jain, Ganesh Katrapati, Senthamizhan V, Raji Baskaran, Balaraman Ravindran
Wikipedia is the most widely available structured repository of information on the Internet. However, gender disparity has been observed in wiki articles, and it is a major issue. We aim to tackle this problem using Machine Learning methods to generate wiki-like biographies for notable women on Wikipedia. We present Hidden Voices, a project which will assist wiki editors and enthusiasts in writing more biographies about women, thereby increasing their representation on Wikipedia.
Download here
Efficient Gender Debiasing of Pre-trained Indic Language Models
Published in Deployable AI workshop, AAAI, 2023
Neeraja Kirtane, Aditya Kane, V Manushree
Quantified bias in Hindi Language model- Muril.Efficiently finetuned by unfreezing less than 1 percent of the parameters. Results showed that debiasing reduced the bias.
Download here
FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs
Published in Under Review, 2024
Neeraja Kirtane, Deema Alnuhait, Muhammad Khalifa, Hao Peng
Download here
LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language
Published in Under Review, 2025
Neeraja Kirtane*, Yubin Ge, Hao Peng, Dilek Hakkani-Tür
Download here