1 code implementation • EMNLP (sdp) 2020 • Rochana Chaturvedi, Saachi ., Jaspreet Singh Dhani, Anurag Joshi, Ankush Khanna, Neha Tomar, Swagata Duari, Alka Khurana, Vasudha Bhatnagar
We describe our approach for the 1st Computational Linguistics Lay Summary Shared Task CL-LaySumm20.
no code implementations • EMNLP (insights) 2020 • Alka Khurana, Vasudha Bhatnagar
Non-negative Matrix Factorization (NMF) has been used for text analytics with promising results.
no code implementations • 16 Mar 2024 • Sudipto Ghosh, Devanshu Verma, Balaji Ganesan, Purnima Bindal, Vikas Kumar, Vasudha Bhatnagar
Legal research is a crucial task in the practice of law.
no code implementations • 3 Mar 2024 • Kinshuk Vasisht, Balaji Ganesan, Vikas Kumar, Vasudha Bhatnagar
Knowledge infusion is a promising method for enhancing Large Language Models for domain-specific NLP tasks rather than pre-training models over large data from scratch.
no code implementations • 17 Dec 2023 • Vikas Kumar, Amisha Bharti, Devanshu Verma, Vasudha Bhatnagar
Generative language models, such as ChatGPT, have garnered attention for their ability to generate human-like writing in various fields, including academic research.
no code implementations • 16 Jun 2023 • Vasudha Bhatnagar, Alka Khurana, Vikas Kumar
In this paper, we present a proposal for an unsupervised algorithm, P-Summ, that generates an extractive summary of scientific scholarly text to meet the personal knowledge needs of the user.
no code implementations • 16 May 2022 • Vasudha Bhatnagar, Swagata Duari, S. K. Gupta
We use a publicly available dataset along with a curated set of contrasting examples to validate the proposed metrics by comparing them against select indices computed using existing cohesion analysis tools.
no code implementations • 22 Sep 2021 • Alka Khurana, Vasudha Bhatnagar
Ergo, informativeness is the prime attribute of document summary generated by an algorithm, and selecting sentences that capture the essence of a document is the primary goal of extractive document summarization.
1 code implementation • 10 Jul 2021 • Jaspreet Singh Dhani, Ruchika Bhatt, Balaji Ganesan, Parikshet Sirohi, Vasudha Bhatnagar
A legal knowledge graph constructed from court cases, judgments, laws and other legal documents can enable a number of applications like question answering, document similarity, and search.
1 code implementation • 26 Sep 2019 • Swagata Duari, Vasudha Bhatnagar
This shows that the proposed method is independent of the domain, collection, and language of the training corpora.
no code implementations • 1 May 2019 • Swagata Duari, Vasudha Bhatnagar
We further establish empirically that the proposed approach can be applied to any text irrespective of the training domain and corpus.
4 code implementations • 27 Nov 2018 • Swagata Duari, Vasudha Bhatnagar
Combination of the proposed graph construction and scoring methods leads to a novel, parameterless keyword extraction method (sCAKE) based on semantic connectivity of words in the document.
1 code implementation • 5 Aug 2010 • Richard Kessler, Bruce Bassett, Pavel Belov, Vasudha Bhatnagar, Heather Campbell, Alex Conley, Joshua A. Frieman, Alexandre Glazov, Santiago Gonzalez-Gaitan, Renee Hlozek, Saurabh Jha, Stephen Kuhlmann, Martin Kunz, Hubert Lampeitl, Ashish Mahabal, James Newling, Robert C. Nichol, David Parkinson, Ninan Sajeeth Philip, Dovi Poznanski, Joseph W. Richards, Steven A. Rodney, Masao Sako, Donald P. Schneider, Mathew Smith, Maximilian Stritzinger, Melvin Varughese
A spectroscopically confirmed subset was provided for training.
Cosmology and Nongalactic Astrophysics