Search Results for author: Kundan Krishna

Found 11 papers, 1 papers with code

Improving the Robustness of Summarization Models by Detecting and Removing Input Noise

no code implementations20 Dec 2022 Kundan Krishna, Yao Zhao, Jie Ren, Balaji Lakshminarayanan, Jiaming Luo, Mohammad Saleh, Peter J. Liu

We present a large empirical study quantifying the sometimes severe loss in performance (up to 12 ROUGE-1 points) from different types of input noise for a range of datasets and model sizes.

Abstractive Text Summarization

Out-of-Distribution Detection and Selective Generation for Conditional Language Models

no code implementations30 Sep 2022 Jie Ren, Jiaming Luo, Yao Zhao, Kundan Krishna, Mohammad Saleh, Balaji Lakshminarayanan, Peter J. Liu

Furthermore, the space of potential low-quality outputs is larger as arbitrary text can be generated and it is important to know when to trust the generated output.

Abstractive Text Summarization OOD Detection +1

Downstream Datasets Make Surprisingly Good Pretraining Corpora

no code implementations28 Sep 2022 Kundan Krishna, Saurabh Garg, Jeffrey P. Bigham, Zachary C. Lipton

For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e. g., BERT) using smaller downstream datasets.

Extracting Structured Data from Physician-Patient Conversations By Predicting Noteworthy Utterances

no code implementations14 Jul 2020 Kundan Krishna, Amy Pavel, Benjamin Schloss, Jeffrey P. Bigham, Zachary C. Lipton

In this exploratory study, we describe a new dataset consisting of conversation transcripts, post-visit summaries, corresponding supporting evidence (in the transcript), and structured labels.

Reinforced Rewards Framework for Text Style Transfer

no code implementations11 May 2020 Abhilasha Sancheti, Kundan Krishna, Balaji Vasan Srinivasan, Anandhavelu Natarajan

Style transfer deals with the algorithms to transfer the stylistic properties of a piece of text into that of another while ensuring that the core content is preserved.

Style Transfer Text Style Transfer

Improving generation quality of pointer networks via guided attention

no code implementations20 Jan 2019 Kushal Chawla, Kundan Krishna, Balaji Vasan Srinivasan

The first shortcoming is the extractive nature of the generated summaries, since the network eventually learns to copy from the input article most of the times, affecting the abstractive nature of the generated summaries.

Abstractive Text Summarization

Vocabulary Tailored Summary Generation

no code implementations COLING 2018 Kundan Krishna, Aniket Murhekar, Saumitra Sharma, Balaji Vasan Srinivasan

Neural sequence-to-sequence models have been successfully extended for summary generation. However, existing frameworks generate a single summary for a given input and do not tune the summaries towards any additional constraints/preferences.

Abstractive Text Summarization

Corpus-based Content Construction

no code implementations COLING 2018 Balaji Vasan Srinivasan, Pranav Maneriker, Kundan Krishna, Natwar Modani

Enterprise content writers are engaged in writing textual content for various purposes.

Generating Topic-Oriented Summaries Using Neural Attention

no code implementations NAACL 2018 Kundan Krishna, Balaji Vasan Srinivasan

Existing summarization algorithms generate a single summary and are not capable of generating multiple summaries tuned to the interests of the readers.

Abstractive Text Summarization

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