activity
20202022
most citedA New Dataset for Natural Language Inference from Code-mixed Conversations

22 citations · 26 across the 5 of their papers we have counts for

collaborators

7 papers

cs.CL20222 cited

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

Harshita Diddee, Sandipan Dandapat, Monojit Choudhury +2

Leveraging shared learning through Massively Multilingual Models, state-of-the-art machine translation models are often able to adapt to the paucity of data for low-resource langua…

cs.CL20222 cited

On the Calibration of Massively Multilingual Language Models

Kabir Ahuja, Sunayana Sitaram, Sandipan Dandapat +1

Massively Multilingual Language Models (MMLMs) have recently gained popularity due to their surprising effectiveness in cross-lingual transfer. While there has been much work in ev…

cs.CL2022

Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models

Kabir Ahuja, Shanu Kumar, Sandipan Dandapat +1

Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from…

cs.CL2021

Predicting the Performance of Multilingual NLP Models

Anirudh Srinivasan, Sunayana Sitaram, Tanuja Ganu +3

Recent advancements in NLP have given us models like mBERT and XLMR that can serve over 100 languages. The languages that these models are evaluated on, however, are very few in nu…

cs.CL2020

GLUECoS : An Evaluation Benchmark for Code-Switched NLP

Simran Khanuja, Sandipan Dandapat, Anirudh Srinivasan +2

Code-switching is the use of more than one language in the same conversation or utterance. Recently, multilingual contextual embedding models, trained on multiple monolingual corpo…

cs.CL202022 cited

A New Dataset for Natural Language Inference from Code-mixed Conversations

Simran Khanuja, Sandipan Dandapat, Sunayana Sitaram +1

Natural Language Inference (NLI) is the task of inferring the logical relationship, typically entailment or contradiction, between a premise and hypothesis. Code-mixing is the use…