scispace - formally typeset
K

Kaustubh Dhole

Researcher at Tata Institute of Fundamental Research

Publications -  25
Citations -  704

Kaustubh Dhole is an academic researcher from Tata Institute of Fundamental Research. The author has contributed to research in topics: Computer science & Population. The author has an hindex of 7, co-authored 18 publications receiving 188 citations. Previous affiliations of Kaustubh Dhole include Birla Institute of Technology & Science, Pilani - Goa & Birla Institute of Technology and Science.

Papers
More filters
Journal Article

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava, +439 more
- 09 Jun 2022 - 
TL;DR: Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.
Journal ArticleDOI

Sequence-based prediction of protein–protein interaction sites with L1-logreg classifier

Kaustubh Dhole, +3 more
- 07 May 2014 - 
TL;DR: A novel method (LORIS: L1-regularized LOgistic Regression based protein-protein Interaction Sites predictor) is proposed, that identifies interaction residues, using sequence features and is implemented via the L 1-logreg classifier.
Posted Content

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics.

Sebastian Gehrmann, +55 more
- 02 Feb 2021 - 
TL;DR: GEM as discussed by the authors is a living benchmark for natural language generation (NLG), its Evaluation and Metrics, which provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested.
Posted ContentDOI

SPRINGS: Prediction of Protein- Protein Interaction Sites Using Artificial Neural Networks

Gurdeep Singh, +3 more
TL;DR: A novel method SPRINGS (Sequence-based predictor of Protein- protein Interacting Sites) for identification of interaction sites based on sequences is proposed, which uses protein evolutionary information, averaged cumulative hydropathy and predicted relative solvent accessibility from amino acid chains in artificial neural network architecture.
Proceedings ArticleDOI

Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation

Kaustubh Dhole, +1 more
TL;DR: This article proposed Syn-QG, a set of transparent syntactic rules leveraging universal dependencies, shallow semantic parsing, lexical resources and custom rules which transform declarative sentences into question-answer pairs.