Alert button
Picture for Harshita Diddee

Harshita Diddee

Alert button

Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology

Add code
Bookmark button
Alert button
May 10, 2024
Rishav Hada, Safiya Husain, Varun Gumma, Harshita Diddee, Aditya Yadavalli, Agrima Seth, Nidhi Kulkarni, Ujwal Gadiraju, Aditya Vashistha, Vivek Seshadri, Kalika Bali

Viaarxiv icon

''Fifty Shades of Bias'': Normative Ratings of Gender Bias in GPT Generated English Text

Add code
Bookmark button
Alert button
Oct 26, 2023
Rishav Hada, Agrima Seth, Harshita Diddee, Kalika Bali

Viaarxiv icon

Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?

Add code
Bookmark button
Alert button
Sep 14, 2023
Rishav Hada, Varun Gumma, Adrian de Wynter, Harshita Diddee, Mohamed Ahmed, Monojit Choudhury, Kalika Bali, Sunayana Sitaram

Figure 1 for Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Figure 2 for Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Figure 3 for Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Figure 4 for Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Viaarxiv icon

MEGA: Multilingual Evaluation of Generative AI

Add code
Bookmark button
Alert button
Apr 03, 2023
Kabir Ahuja, Rishav Hada, Millicent Ochieng, Prachi Jain, Harshita Diddee, Samuel Maina, Tanuja Ganu, Sameer Segal, Maxamed Axmed, Kalika Bali, Sunayana Sitaram

Figure 1 for MEGA: Multilingual Evaluation of Generative AI
Figure 2 for MEGA: Multilingual Evaluation of Generative AI
Figure 3 for MEGA: Multilingual Evaluation of Generative AI
Figure 4 for MEGA: Multilingual Evaluation of Generative AI
Viaarxiv icon

Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi

Add code
Bookmark button
Alert button
Nov 29, 2022
Devansh Mehta, Harshita Diddee, Ananya Saxena, Anurag Shukla, Sebastin Santy, Ramaravind Kommiya Mothilal, Brij Mohan Lal Srivastava, Alok Sharma, Vishnu Prasad, Venkanna U, Kalika Bali

Figure 1 for Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi
Figure 2 for Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi
Figure 3 for Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi
Figure 4 for Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi
Viaarxiv icon

Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models

Add code
Bookmark button
Alert button
Nov 09, 2022
Harshita Diddee, Sandipan Dandapat, Monojit Choudhury, Tanuja Ganu, Kalika Bali

Figure 1 for Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models
Figure 2 for Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models
Figure 3 for Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models
Figure 4 for Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models
Viaarxiv icon

Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning

Add code
Bookmark button
Alert button
Jul 14, 2021
Rakshit Naidu, Harshita Diddee, Ajinkya Mulay, Aleti Vardhan, Krithika Ramesh, Ahmed Zamzam

Figure 1 for Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning
Figure 2 for Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning
Figure 3 for Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning
Figure 4 for Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning
Viaarxiv icon

Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages

Add code
Bookmark button
Alert button
Apr 29, 2021
Gowtham Ramesh, Sumanth Doddapaneni, Aravinth Bheemaraj, Mayank Jobanputra, Raghavan AK, Ajitesh Sharma, Sujit Sahoo, Harshita Diddee, Mahalakshmi J, Divyanshu Kakwani, Navneet Kumar, Aswin Pradeep, Kumar Deepak, Vivek Raghavan, Anoop Kunchukuttan, Pratyush Kumar, Mitesh Shantadevi Khapra

Figure 1 for Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
Figure 2 for Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
Figure 3 for Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
Figure 4 for Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
Viaarxiv icon