mlsanityData to 7 Oct 2026

Semantic Novelty Detection and Characterization in Factual Text Involving Named Entities

arXiv 2210.17440 ↗First posted 31 Oct 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Much of the existing work on text novelty detection has been studied at the topic level, i.e., identifying whether the topic of a document or a sentence is novel or not. Little work has been done at the fine-grained semantic level (or contextual level). For example, given that we know Elon Musk is the CEO of a technology company, the sentence "Elon Musk acted in the sitcom The Big Bang Theory" is novel and surprising because normally a CEO would not be an actor. Existing topic-based novelty detection methods work poorly on this problem because they do not perform semantic reasoning involving relations between named entities in the text and their background knowledge. This paper proposes an effective model (called PAT-SND) to solve the problem, which can also characterize the novelty. An annotated dataset is also created. Evaluation shows that PAT-SND outperforms 10 baselines by large margins.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 111 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

39 of 111 references.

References · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  8. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  9. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  10. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  11. 2018A Simple Method for Commonsense Reasoningcited by 223
  12. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
27 more
  1. 2019Commonsense Knowledge Mining from Pretrained Modelscited by 189
  2. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  3. 2017DOC: Deep Open Classification of Text Documentscited by 109
  4. 2020Relational Graph Attention Network for Aspect-based Sentiment Analysiscited by 104
  5. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  6. 2019Enriching Pre-trained Language Model with Entity Information for Relation Classificationcited by 82
  7. 2019Attention Guided Graph Convolutional Networks for Relation Extractioncited by 82
  8. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  9. 2019Do Neural Language Representations Learn Physical Commonsense?cited by 62
  10. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  11. 2020SemEval-2020 Task 4: Commonsense Validation and Explanationcited by 42
  12. 2019Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detectioncited by 41
  13. 2018Open-world Learning and Application to Product Classificationcited by 39
  14. 2019Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networkscited by 39
  15. 2016Ordinal Common-sense Inferencecited by 35
  16. 2021One-Class Classification: A Surveycited by 35
  17. 2018One-Class Adversarial Nets for Fraud Detectioncited by 33
  18. 2017Verb Physics: Relative Physical Knowledge of Actions and Objectscited by 26
  19. 2018Modeling Semantic Plausibility by Injecting World Knowledgecited by 24
  20. 2016Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objectscited by 22
  21. 2018Unseen Class Discovery in Open-world Classificationcited by 20
  22. 2017Provable Self-Representation Based Outlier Detection in a Union of Subspacescited by 18
  23. 2019Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Textcited by 9
  24. 2020Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulationcited by 7
  25. 2017Distributional Modeling on a Diet: One-shot Word Learning from Text Onlycited by 5
  26. 2019Deep One-Class Classification Using Intra-Class Splittingcited by 4
  27. 2016Fun Facts: Automatic Trivia Fact Extraction from Wikipediacited by 3

Built on by

Not cited yet.