{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T22:28:15Z","timestamp":1779920895091,"version":"3.53.1"},"reference-count":90,"publisher":"MIT Press","issue":"1","license":[{"start":{"date-parts":[[2021,12,22]],"date-time":"2021-12-22T00:00:00Z","timestamp":1640131200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>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 concern. 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.<\/jats:p>","DOI":"10.1162\/coli_a_00429","type":"journal-article","created":{"date-parts":[[2021,12,22]],"date-time":"2021-12-22T19:20:23Z","timestamp":1640200823000},"page":"77-117","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":20,"title":["Novelty Detection: A Perspective from Natural Language Processing"],"prefix":"10.1162","volume":"48","author":[{"given":"Tirthankar","family":"Ghosal","sequence":"first","affiliation":[{"name":"Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic. ghosal@ufal.mff.cuni.cz"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanik","family":"Saikh","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India. 1821cs08@iitp.ac.in"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tameesh","family":"Biswas","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India. biswas.cs16@iitp.ac.in"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asif","family":"Ekbal","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India. asif@iitp.ac.in"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pushpak","family":"Bhattacharyya","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Powai, India. pb@cse.iitb.ac.in"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2022,4,4]]},"reference":[{"key":"2022040614222031200_bib1","doi-asserted-by":"publisher","first-page":"137","DOI":"10.18653\/v1\/D19-5819","article-title":"ReQA: An evaluation for end-to-end answer retrieval models","volume-title":"Proceedings of the 2nd Workshop on Machine Reading for Question Answering, MRQA@EMNLP 2019","author":"Ahmad","year":"2019"},{"key":"2022040614222031200_bib2","first-page":"167","article-title":"Detections, bounds, and timelines: Umass and TDT-3","volume-title":"Proceedings of Topic Detection and Tracking Workshop","author":"Allan","year":"2000"},{"key":"2022040614222031200_bib3","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1145\/290941.290954","article-title":"On-line new event detection and tracking","volume-title":"Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Allan","year":"1998"},{"key":"2022040614222031200_bib4","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1145\/860435.860493","article-title":"Retrieval and novelty detection at the sentence level","volume-title":"SIGIR 2003: Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Allan","year":"2003"},{"key":"2022040614222031200_bib5","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1145\/860435.860493","article-title":"Retrieval and novelty detection at the sentence level","volume-title":"Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval","author":"Allan","year":"2003"},{"key":"2022040614222031200_bib6","doi-asserted-by":"publisher","first-page":"4684","DOI":"10.18653\/v1\/D19-1475","article-title":"MultiFC: A real-world multi-domain dataset for evidence-based fact checking of claims","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019","author":"Augenstein","year":"2019"},{"key":"2022040614222031200_bib7","doi-asserted-by":"crossref","DOI":"10.3115\/1608810.1608812","article-title":"Cross-document event coreference: Annotations, experiments, and observations","volume-title":"Coreference and Its Applications","author":"Bagga","year":"1999"},{"key":"2022040614222031200_bib8","first-page":"150","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings","author":"Bahdanau"},{"issue":"4","key":"2022040614222031200_bib9","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1162\/COLI_a_00153","article-title":"Plagiarism meets paraphrasing: Insights for the next generation in automatic plagiarism detection","volume":"39","author":"Barr\u00f3n-Cede\u00f1o","year":"2013","journal-title":"Computational Linguistics"},{"key":"2022040614222031200_bib10","first-page":"1","article-title":"The Seventh PASCAL Recognizing Textual Entailment Challenge","volume-title":"TAC 2011 Notebook Proceedings","author":"Bentivogli","year":"2011"},{"key":"2022040614222031200_bib11","first-page":"1","article-title":"The Sixth PASCAL Recognizing Textual Entailment Challenge","volume-title":"Proceedings of the Text Analysis Conference (TAC 2010)","author":"Bentivogli","year":"2010"},{"key":"2022040614222031200_bib12","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1145\/1099554.1099733","article-title":"Redundant documents and search effectiveness","volume-title":"Proceedings of the 14th ACM International Conference on Information and Knowledge Management","author":"Bernstein","year":"2005"},{"key":"2022040614222031200_bib13","first-page":"18","article-title":"Novelty as a measure of interestingness in knowledge discovery","volume":"9","author":"Bhatnagar","year":"2006","journal-title":"Constraints"},{"key":"2022040614222031200_bib14","doi-asserted-by":"publisher","first-page":"632","DOI":"10.18653\/v1\/D15-1075","article-title":"A large annotated corpus for learning natural language inference","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Bowman","year":"2015"},{"key":"2022040614222031200_bib15","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1145\/860435.860495","article-title":"A system for new event detection","volume-title":"Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval","author":"Brants","year":"2003"},{"key":"2022040614222031200_bib16","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","author":"Brown","year":"2020"},{"issue":"3","key":"2022040614222031200_bib17","first-page":"43","article-title":"Paraphrase acquisition via crowdsourcing and machine learning","volume":"4","author":"Burrows","year":"2013","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"2022040614222031200_bib18","first-page":"13","article-title":"Detecting novelty in the context of progressive summarization","volume-title":"Proceedings of the NAACL HLT 2010 Student Research Workshop","author":"Bysani","year":"2010"},{"key":"2022040614222031200_bib19","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1145\/290941.291025","article-title":"The use of MMR, diversity-based reranking for reordering documents and producing summaries","volume-title":"Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Carbonell","year":"1998"},{"key":"2022040614222031200_bib20","doi-asserted-by":"publisher","first-page":"169","DOI":"10.18653\/v1\/d18-2029","article-title":"Universal sentence encoder for English","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018: System Demonstrations","author":"Cer","year":"2018"},{"key":"2022040614222031200_bib21","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1145\/2484028.2484094","article-title":"Preference based evaluation measures for novelty and diversity","volume-title":"Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR \u201913","author":"Chandar","year":"2013"},{"key":"2022040614222031200_bib22","doi-asserted-by":"publisher","first-page":"1657","DOI":"10.18653\/v1\/P17-1152","article-title":"Enhanced LSTM for natural language inference","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Chen","year":"2017"},{"key":"2022040614222031200_bib23","doi-asserted-by":"publisher","first-page":"8772","DOI":"10.18653\/v1\/2020.acl-main.774","article-title":"Uncertain natural language inference","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020","author":"Chen","year":"2020"},{"key":"2022040614222031200_bib24","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1145\/1935826.1935847","article-title":"A comparative analysis of cascade measures for novelty and diversity","author":"Clarke","year":"2011"},{"key":"2022040614222031200_bib25","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1145\/1390334.1390446","article-title":"Novelty and diversity in information retrieval evaluation","volume-title":"Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR \u201908","author":"Clarke","year":"2008"},{"issue":"1","key":"2022040614222031200_bib26","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s10579-009-9112-1","article-title":"Developing a corpus of plagiarised short answers","volume":"45","author":"Clough","year":"2011","journal-title":"Language Resources and Evaluation"},{"key":"2022040614222031200_bib27","first-page":"1","article-title":"Information filtering, novelty detection, and named-page finding","volume-title":"TREC","author":"Collins-Thompson","year":"2002"},{"key":"2022040614222031200_bib28","first-page":"670","article-title":"Supervised learning of universal sentence representations from natural language inference data","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017","author":"Conneau","year":"2017"},{"key":"2022040614222031200_bib29","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/11736790_9","article-title":"The PASCAL recognising textual entailment challenge","volume-title":"Machine Learning Challenges, Evaluating Predictive Uncertainty, Visual Object Classification and Recognizing Textual Entailment, First PASCAL Machine Learning Challenges Workshop, MLCW 2005, Revised Selected Papers","author":"Dagan","year":"2005"},{"issue":"4","key":"2022040614222031200_bib30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2200\/S00509ED1V01Y201305HLT023","article-title":"Recognizing textual entailment: Models and applications","volume":"6","author":"Dagan","year":"2013","journal-title":"Synthesis Lectures on Human Language Technologies"},{"key":"2022040614222031200_bib31","first-page":"6","article-title":"Automatic scoring for innovativeness of textual ideas","volume-title":"Knowledge Extraction from Text, Papers from the 2016 AAAI Workshop","author":"Dasgupta","year":"2016"},{"key":"2022040614222031200_bib32","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/v1\/N19-1423","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"key":"2022040614222031200_bib33","doi-asserted-by":"publisher","first-page":"5408","DOI":"10.18653\/v1\/2021.naacl-main.426","article-title":"Self-training improves pre-training for natural language understanding","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Du","year":"2021"},{"issue":"5","key":"2022040614222031200_bib34","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1037\/h0031619","article-title":"Measuring nominal scale agreement among many raters","volume":"76","author":"Fleiss","year":"1971","journal-title":"Psychological Bulletin"},{"key":"2022040614222031200_bib35","first-page":"193","article-title":"First story detection: Combining similarity and novelty based approaches","volume-title":"Topic Detection and Tracking Workshop Report","author":"Franz","year":"2001"},{"key":"2022040614222031200_bib36","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1145\/988672.988738","article-title":"Newsjunkie: Providing personalized newsfeeds via analysis of information novelty","volume-title":"Proceedings of the 13th International Conference on World Wide Web","author":"Gabrilovich","year":"2004"},{"key":"2022040614222031200_bib37","first-page":"17","article-title":"Graph-based text representation for novelty detection","volume-title":"Proceedings of the First Workshop on Graph Based Methods for Natural Language Processing","author":"Gamon","year":"2006"},{"key":"2022040614222031200_bib38","first-page":"66","article-title":"Adapting by pruning: A case study on BERT","author":"Gao","year":"2021","journal-title":"CoRR"},{"key":"2022040614222031200_bib39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18653\/v1\/W18-2501","article-title":"AllenNLP: A deep semantic natural language processing platform","volume-title":"Proceedings of Workshop for NLP Open Source Software (NLP-OSS)","author":"Gardner","year":"2018"},{"issue":"4","key":"2022040614222031200_bib40","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1017\/S1351324920000194","article-title":"Is your document novel? Let attention guide you. An attention based model for document-level novelty detection","volume":"27","author":"Ghosal","year":"2021","journal-title":"Natural Language Engineering"},{"key":"2022040614222031200_bib41","first-page":"2802","article-title":"Novelty goes deep. A deep neural solution to document level novelty detection","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018","author":"Ghosal","year":"2018"},{"key":"2022040614222031200_bib42","first-page":"3541","article-title":"TAP-DLND 1.0 : A corpus for document level novelty detection","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018","author":"Ghosal","year":"2018"},{"key":"2022040614222031200_bib43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN.2019.8851857","article-title":"To comprehend the new: On measuring the freshness of a document","volume-title":"International Joint Conference on Neural Networks, IJCNN 2019","author":"Ghosal","year":"2019"},{"issue":"8","key":"2022040614222031200_bib44","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1002\/asi.23228","article-title":"Citation-based plagiarism detection: Practicability on a large-scale scientific corpus","volume":"65","author":"Gipp","year":"2014","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"2022040614222031200_bib45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.6028\/NIST.SP.500-251.novelty-overview","article-title":"Overview of the TREC 2002 novelty track","volume-title":"Proceedings of The Eleventh Text REtrieval Conference, TREC 2002","author":"Harman","year":"2002"},{"key":"2022040614222031200_bib46","first-page":"46","article-title":"Overview of the TREC 2002 novelty track","volume-title":"TREC","author":"Harman","year":"2002"},{"key":"2022040614222031200_bib47","first-page":"278","article-title":"Random decision forests","volume-title":"Proceedings of 3rd International Conference on Document Analysis and Recognition","author":"Ho","year":"1995"},{"key":"2022040614222031200_bib48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN.2019.8852327","article-title":"Multi-task sentence encoding model for semantic retrieval in question answering systems","volume-title":"International Joint Conference on Neural Networks, IJCNN 2019","author":"Huang","year":"2019"},{"key":"2022040614222031200_bib49","first-page":"547","article-title":"\u00c9tude comparative de la distribution florale dans une portion des alpes et des Jura","volume":"37","author":"Jaccard","year":"1901","journal-title":"Bulletin del la Soci\u00e9t\u00e9 Vaudoise des Sciences Naturelles"},{"key":"2022040614222031200_bib50","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/978-3-642-41230-1_5","article-title":"Efficient online novelty detection in news streams","volume-title":"Web Information Systems Engineering - WISE 2013 - 14th International Conference, Proceedings, Part I","author":"Karkali","year":"2013"},{"key":"2022040614222031200_bib51","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, A meeting of SIGDAT, a Special Interest Group of the ACL","author":"Kim","year":"2014"},{"key":"2022040614222031200_bib52","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1007\/978-3-642-01307-2_7","article-title":"Sentence-level novelty detection in English and Malay","volume-title":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","author":"Kwee","year":"2009"},{"key":"2022040614222031200_bib53","first-page":"100","article-title":"Natural language inference from multiple premises","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing, IJCNLP 2017, Volume 1: Long Papers","author":"Lai","year":"2017"},{"key":"2022040614222031200_bib54","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1145\/1099554.1099734","article-title":"Novelty detection based on sentence level patterns","volume-title":"Proceedings of the 14th ACM International Conference on Information and Knowledge Management","author":"Li","year":"2005"},{"key":"2022040614222031200_bib55","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"2022040614222031200_bib56","first-page":"404","article-title":"Textrank: Bringing order into text","volume-title":"Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, EMNLP 2004, A meeting of SIGDAT, a Special Interest Group of the ACL, held in conjunction with ACL 2004","author":"Mihalcea","year":"2004"},{"key":"2022040614222031200_bib57","doi-asserted-by":"publisher","first-page":"130","DOI":"10.18653\/v1\/P16-2022","article-title":"Natural language inference by tree-based convolution and heuristic matching","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Mou","year":"2016"},{"key":"2022040614222031200_bib58","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni","year":"2002"},{"key":"2022040614222031200_bib59","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.18653\/v1\/D16-1244","article-title":"A decomposable attention model for natural language inference","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Parikh","year":"2016"},{"key":"2022040614222031200_bib60","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1162\/tacl_a_00293","article-title":"Inherent disagreements in human textual inferences","volume":"7","author":"Pavlick","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2022040614222031200_bib61","first-page":"1","article-title":"Spotting rumors via novelty detection","author":"Qin","year":"2016","journal-title":"CoRR"},{"key":"2022040614222031200_bib62","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journals of Machine Learning Research"},{"key":"2022040614222031200_bib63","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.18653\/v1\/D16-1264","article-title":"SQuAD: 100,000+ Questions for machine comprehension of text","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Rajpurkar","year":"2016"},{"key":"2022040614222031200_bib64","first-page":"1","article-title":"Improved Feature Selection and Redundance Computing - THUIR at TREC 2004 Novelty Track","volume-title":"TREC","author":"Ru","year":"2004"},{"key":"2022040614222031200_bib65","first-page":"131","article-title":"Document level novelty detection: Textual entailment lends a helping hand","volume-title":"Proceedings of the 14th International Conference on Natural Language Processing (ICON-2017)","author":"Saikh","year":"2017"},{"key":"2022040614222031200_bib66","unstructured":"S\u00e1nchez-Vega, Jos\u00e9 Fernando . 2016. Identificaci\u00f3n de plagio parafraseado incorporando estructura, sentido y estilo de los textos. PhD thesis, Instituto Nacional de Astrof\u00edsica, Optica y Electr\u00f3nica."},{"key":"2022040614222031200_bib67","first-page":"716","article-title":"Context and learning in novelty detection","volume-title":"Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing","author":"Schiffman","year":"2005"},{"key":"2022040614222031200_bib68","doi-asserted-by":"crossref","DOI":"10.6028\/NIST.SP.500-261.novelty-overview","article-title":"Overview of the TREC 2004 novelty track","volume-title":"Proceedings of the Thirteenth Text REtrieval Conference, TREC 2004","author":"Soboroff","year":"2004"},{"key":"2022040614222031200_bib69","first-page":"38","article-title":"Overview of the TREC 2003 novelty track","volume-title":"TREC","author":"Soboroff","year":"2003"},{"key":"2022040614222031200_bib70","first-page":"105","article-title":"Novelty detection: The TREC experience","volume-title":"Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing","author":"Soboroff","year":"2005"},{"key":"2022040614222031200_bib71","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3115\/1072133.1072182","article-title":"First story detection using a composite document representation","volume-title":"Proceedings of the First International Conference on Human Language Technology Research","author":"Stokes","year":"2001"},{"issue":"4","key":"2022040614222031200_bib72","first-page":"15","article-title":"First direct evidence of two stages in free recall","author":"Tarnow","year":"2015","journal-title":"RUDN Journal of Psychology and Pedagogics"},{"key":"2022040614222031200_bib73","doi-asserted-by":"publisher","first-page":"2948","DOI":"10.18653\/v1\/n19-1302","article-title":"Repurposing entailment for multi-hop question answering tasks","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Volume 1 (Long and Short Papers)","author":"Trivedi","year":"2019"},{"issue":"6","key":"2022040614222031200_bib74","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1108\/09696471011082358","article-title":"Redundancy and novelty mining in the business blogosphere","volume":"17","author":"Tsai","year":"2010","journal-title":"The Learning Organization"},{"issue":"12","key":"2022040614222031200_bib75","doi-asserted-by":"crossref","first-page":"2359","DOI":"10.1016\/j.ins.2010.02.020","article-title":"Evaluation of novelty metrics for sentence-level novelty mining","volume":"180","author":"Tsai","year":"2010","journal-title":"Information Sciences"},{"issue":"2","key":"2022040614222031200_bib76","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1007\/s10115-010-0372-2","article-title":"D2s: Document-to-sentence framework for novelty detection","volume":"29","author":"Tsai","year":"2011","journal-title":"Knowledge and Information Systems"},{"issue":"3","key":"2022040614222031200_bib77","doi-asserted-by":"crossref","first-page":"387","DOI":"10.3758\/BF03210977","article-title":"Novelty assessment in the brain and long-term memory encoding","volume":"2","author":"Tulving","year":"1995","journal-title":"Psychonomic Bulletin & Review"},{"key":"2022040614222031200_bib78","first-page":"431","article-title":"A comparison study for novelty control mechanisms applied to Web news stories","volume-title":"Web Intelligence and Intelligent Agent Technology (WI-IAT), 2012 IEEE\/WIC\/ACM International Conferences","author":"Verheij","year":"2012"},{"key":"2022040614222031200_bib79","first-page":"1","article-title":"Evidence aggregation for answer re-ranking in open-domain question answering","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Conference Track Proceedings","author":"Wang","year":"2018"},{"key":"2022040614222031200_bib80","first-page":"28","article-title":"Topic Detection and Tracking (TDT)","volume-title":"Workshop held at the University of Maryland","author":"Wayne","year":"1997"},{"key":"2022040614222031200_bib81","first-page":"1112","article-title":"A broad-coverage challenge corpus for sentence understanding through inference","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Williams","year":"2018"},{"key":"2022040614222031200_bib82","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1145\/290941.290953","article-title":"A study of retrospective and on-line event detection","volume-title":"Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Yang","year":"1998"},{"key":"2022040614222031200_bib83","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1145\/775047.775150","article-title":"Topic-conditioned novelty detection","volume-title":"Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Yang","year":"2002"},{"key":"2022040614222031200_bib84","doi-asserted-by":"publisher","first-page":"87","DOI":"10.18653\/v1\/2020.acl-demos.12","article-title":"Multilingual universal sentence encoder for semantic retrieval","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, ACL 2020","author":"Yang","year":"2020"},{"key":"2022040614222031200_bib85","doi-asserted-by":"publisher","first-page":"2369","DOI":"10.18653\/v1\/d18-1259","article-title":"HotpotQA: A dataset for diverse, explainable multi-hop question answering","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Yang","year":"2018"},{"issue":"251","key":"2022040614222031200_bib86","first-page":"586","article-title":"Expansion-based technologies in finding relevant and new information: THU TREC 2002: Novelty Track Experiments","author":"Zhang","year":"2003","journal-title":"NIST Special Publication SP"},{"key":"2022040614222031200_bib87","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1145\/564376.564393","article-title":"Novelty and redundancy detection in adaptive filtering","volume-title":"Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Zhang","year":"2002"},{"key":"2022040614222031200_bib88","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1145\/564376.564393","article-title":"Novelty and redundancy detection in adaptive filtering","volume-title":"SIGIR 2002: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Zhang","year":"2002"},{"key":"2022040614222031200_bib89","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1145\/1506250.1506256","article-title":"Combining named entities and tags for novel sentence detection","volume-title":"Proceedings of the WSDM09 Workshop on Exploiting Semantic Annotations in Information Retrieval","author":"Zhang","year":"2009"},{"key":"2022040614222031200_bib90","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1145\/2911451.2911488","article-title":"How much novelty is relevant?: It depends on your curiosity","volume-title":"Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Zhao","year":"2016"}],"container-title":["Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/coli\/article-pdf\/48\/1\/77\/2006641\/coli_a_00429.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/coli\/article-pdf\/48\/1\/77\/2006641\/coli_a_00429.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T01:55:51Z","timestamp":1726365351000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/coli\/article\/48\/1\/77\/108847\/Novelty-Detection-A-Perspective-from-Natural"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":90,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,4,4]]},"published-print":{"date-parts":[[2022,4,4]]}},"URL":"https:\/\/doi.org\/10.1162\/coli_a_00429","relation":{},"ISSN":["0891-2017","1530-9312"],"issn-type":[{"value":"0891-2017","type":"print"},{"value":"1530-9312","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022]]},"published":{"date-parts":[[2022]]}}}