Search Results for author: Aalok Sathe

Found 6 papers, 3 papers with code

SentSpace: Large-Scale Benchmarking and Evaluation of Text using Cognitively Motivated Lexical, Syntactic, and Semantic Features

no code implementations NAACL (ACL) 2022 Greta Tuckute, Aalok Sathe, Mingye Wang, Harley Yoder, Cory Shain, Evelina Fedorenko

The modular design of SentSpace allows researchersto easily integrate their own feature computation into the pipeline while benefiting from acommon framework for evaluation and visualization.

Natural Language Processing

Analyzing the Effects of Reasoning Types on Cross-Lingual Transfer Performance

1 code implementation EMNLP (MRL) 2021 Karthikeyan K, Aalok Sathe, Somak Aditya, Monojit Choudhury

Multilingual language models achieve impressive zero-shot accuracies in many languages in complex tasks such as Natural Language Inference (NLI).

Cross-Lingual Transfer Natural Language Inference

Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems

1 code implementation ACL (SIGMORPHON) 2021 Saujas Vaduguru, Aalok Sathe, Monojit Choudhury, Dipti Misra Sharma

Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples.

Program Synthesis

TaxiNLI: Taking a Ride up the NLU Hill

1 code implementation CONLL 2020 Pratik Joshi, Somak Aditya, Aalok Sathe, Monojit Choudhury

Pre-trained Transformer-based neural architectures have consistently achieved state-of-the-art performance in the Natural Language Inference (NLI) task.

Natural Language Inference

Automated Fact-Checking of Claims from Wikipedia

no code implementations LREC 2020 Aalok Sathe, Salar Ather, Tuan Manh Le, Nathan Perry, Joonsuk Park

However, such datasets suffer from limited applicability due to the synthetic nature of claims and/or evidence written by annotators that differ from real claims and evidence on the internet.

Fact Checking

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