Vasudha Bhatnagar


2020

pdf
Divide and Conquer: From Complexity to Simplicity for Lay Summarization
Rochana Chaturvedi | Saachi . | Jaspreet Singh Dhani | Anurag Joshi | Ankush Khanna | Neha Tomar | Swagata Duari | Alka Khurana | Vasudha Bhatnagar
Proceedings of the First Workshop on Scholarly Document Processing

We describe our approach for the 1st Computational Linguistics Lay Summary Shared Task CL-LaySumm20. The task is to produce non-technical summaries of scholarly documents. The summary should be within easy grasp of a layman who may not be well versed with the domain of the research article. We propose a two step divide-and-conquer approach. First, we judiciously select segments of the documents that are not overly pedantic and are likely to be of interest to the laity, and over-extract sentences from each segment using an unsupervised network based method. Next, we perform abstractive summarization on these extractions and systematically merge the abstractions. We run ablation studies to establish that each step in our pipeline is critical for improvement in the quality of lay summary. Our approach leverages state-of-the-art pre-trained deep neural network based models as zero-shot learners to achieve high scores on the task.

pdf
NMF Ensembles? Not for Text Summarization!
Alka Khurana | Vasudha Bhatnagar
Proceedings of the First Workshop on Insights from Negative Results in NLP

Non-negative Matrix Factorization (NMF) has been used for text analytics with promising results. Instability of results arising due to stochastic variations during initialization makes a case for use of ensemble technology. However, our extensive empirical investigation indicates otherwise. In this paper, we establish that ensemble summary for single document using NMF is no better than the best base model summary.