Novelty Detection: A Perspective from Natural Language Processing

Novelty Detection: A Perspective from Natural Language Processing Tirthankar Ghosal∗† Institute of Formal and Applied Linguistics Faculty of Mathematics and Physics Charles University Prague, Czech Republic ghosal@ufal.mff.cuni.cz Tanik Saikh Department of Computer Science and Engineering Indian Institute of Technology Patna Patna, India 1821cs08@iitp.ac.in Tameesh Biswas Department of Computer Science and Engineering Indian Institute of Technology Patna Patna, India biswas.cs16@iitp.ac.in Asif Ekbal† Department of Computer Science and Engineering Indian Institute of Technology Patna Patna, India asif@iitp.ac.in Pushpak Bhattacharyya Department of Computer Science and Engineering Indian Institute of Technology Bombay Powai, India pb@cse.iitb.ac.in ∗ The author carried out this work during his doctoral studies at the Indian Institute of Technology Patna, India. † Corresponding Authors. Submission received: 28 October 2020; revised version received: 17 October 2021; accepted fo publication: 5 December 2021. https://doi.org/10.1162/COLI a 00429 © 2022 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Computational Linguistics Volume 48, Number 1 The quest for new information is an inborn human trait and has always been quintessential for human survival and progress. Novelty drives curiosity, which in turn drives innovation. In Natural Language Processing (NLP), Novelty Detection refers to finding text that has some new information to offer with respect to whatever is earlier seen or known. With the exponential growth of information all across the Web, there is an accompanying menace of redundancy. A considerable portion of the Web contents are duplicates, and we need efficient mechanisms to retain new information and filter out redundant information. However, detecting redundancy at the semantic level and identifying novel text is not straightforward because the text may have less lexical overlap yet convey the same information. On top of that, non-novel/redundant information in a document may have assimilated from multiple source documents, not just one. The problem surmounts when the subject of the discourse is documents, and numerous prior documents need to be processed to ascertain the novelty/non-novelty of the current one in con- cern. In this work, we build upon our earlier investigations for document-level novelty detection and present a comprehensive account of our efforts toward the problem. We explore the role of pre-trained Textual Entailment (TE) models to deal with multiple source contexts and present the outcome of our current investigations. We argue that a multipremise entailment task is one close approximation toward identifying semantic-level non-novelty. Our recent approach either performs comparably or achieves significant improvement over the latest reported results on several datasets and across several related tasks (paraphrasing, plagiarism, rewrite). We critically analyze our performance with respect to the existing state of the art and show the superiority and promise of our approach for future investigations. We also present our enhanced dataset TAP-DLND 2.0 and several baselines to the community for further research on document-level novelty detection. 1. Introduction Of all the passions of mankind, the love of novelty most rules the mind. –Shelby Foote This quote by Shelby Foote1 sums up the importance of novelty in our existence. Most of the breakthrough …

Content truncated to 500 words