Search Results for author: Anirudh Srinivasan

Found 10 papers, 2 papers with code

BERTologiCoMix: How does Code-Mixing interact with Multilingual BERT?

no code implementations EACL (AdaptNLP) 2021 Sebastin Santy, Anirudh Srinivasan, Monojit Choudhury

Models such as mBERT and XLMR have shown success in solving Code-Mixed NLP tasks even though they were not exposed to such text during pretraining.

CALCS 2021 Shared Task: Machine Translation for Code-Switched Data

no code implementations19 Feb 2022 Shuguang Chen, Gustavo Aguilar, Anirudh Srinivasan, Mona Diab, Thamar Solorio

For the unsupervised setting, we provide the following language pairs: English and Spanish-English (Eng-Spanglish), and English and Modern Standard Arabic-Egyptian Arabic (Eng-MSAEA) in both directions.

Language Identification Machine Translation +3

Predicting the Performance of Multilingual NLP Models

no code implementations17 Oct 2021 Anirudh Srinivasan, Sunayana Sitaram, Tanuja Ganu, Sandipan Dandapat, Kalika Bali, Monojit Choudhury

Recent advancements in NLP have given us models like mBERT and XLMR that can serve over 100 languages.

Multilingual NLP

GCM: A Toolkit for Generating Synthetic Code-mixed Text

1 code implementation EACL 2021 Mohd Sanad Zaki Rizvi, Anirudh Srinivasan, Tanuja Ganu, Monojit Choudhury, Sunayana Sitaram

Code-mixing is common in multilingual communities around the world, and processing it is challenging due to the lack of labeled and unlabeled data.

Code-mixed parse trees and how to find them

no code implementations LREC 2020 Anirudh Srinivasan, D, S apat, ipan, Monojit Choudhury

In this paper, we explore the methods of obtaining parse trees of code-mixed sentences and analyse the obtained trees.

Automated curriculum generation for Policy Gradients from Demonstrations

1 code implementation1 Dec 2019 Anirudh Srinivasan, Dzmitry Bahdanau, Maxime Chevalier-Boisvert, Yoshua Bengio

In this paper, we present a technique that improves the process of training an agent (using RL) for instruction following.

Cannot find the paper you are looking for? You can Submit a new open access paper.