no code implementations • 10 Dec 2023 • Yash Kumar Atri, Vikram Goyal, Tanmoy Chakraborty
We employ clustering techniques to learn the diversity of a model's sample space and how data points are mapped from the embedding space to the encoder space and vice versa.
no code implementations • 24 Jun 2023 • Yash Kumar Atri, Vikram Goyal, Tanmoy Chakraborty
In this paper, we deal with a novel task of extreme abstractive text summarization (aka TL;DR generation) by leveraging multiple input modalities.
no code implementations • 1 Mar 2023 • Priyanshi Gupta, Yash Kumar Atri, Apurva Nagvenkar, Sourish Dasgupta, Tanmoy Chakraborty
Current datasets and methods used for inline citation classification only use citation-marked sentences constraining the model to turn a blind eye to domain knowledge and neighboring contextual sentences.
1 code implementation • 10 Sep 2021 • Vaibhav Pulastya, Gaurav Nuti, Yash Kumar Atri, Tanmoy Chakraborty
Therefore, by identifying the outliers in the latent space, we can find the mislabeled samples.
no code implementations • 20 May 2021 • Yash Kumar Atri, Shraman Pramanick, Vikram Goyal, Tanmoy Chakraborty
However, existing methods use short videos as the visual modality and short summary as the ground-truth, therefore, perform poorly on lengthy videos and long ground-truth summary.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Alvin Dey, Tanya Chowdhury, Yash Kumar Atri, Tanmoy Chakraborty
Owing to no standard definition of the task, we encounter a plethora of datasets with varying levels of overlap and conflict between participating documents.