Semantic Novelty Detection in Natural Language Descriptions

Nianzu Ma, Alexander Politowicz, Sahisnu Mazumder, Jiahua Chen, Bing Liu, Eric Robertson, Scott Grigsby


Abstract
This paper proposes to study a fine-grained semantic novelty detection task, which can be illustrated with the following example. It is normal that a person walks a dog in the park, but if someone says “A man is walking a chicken in the park”, it is novel. Given a set of natural language descriptions of normal scenes, we want to identify descriptions of novel scenes. We are not aware of any existing work that solves the problem. Although existing novelty or anomaly detection algorithms are applicable, since they are usually topic-based, they perform poorly on our fine-grained semantic novelty detection task. This paper proposes an effective model (called GAT-MA) to solve the problem and also contributes a new dataset. Experimental evaluation shows that GAT-MA outperforms 11 baselines by large margins.
Anthology ID:
2021.emnlp-main.66
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
866–882
Language:
URL:
https://aclanthology.org/2021.emnlp-main.66
DOI:
10.18653/v1/2021.emnlp-main.66
Bibkey:
Cite (ACL):
Nianzu Ma, Alexander Politowicz, Sahisnu Mazumder, Jiahua Chen, Bing Liu, Eric Robertson, and Scott Grigsby. 2021. Semantic Novelty Detection in Natural Language Descriptions. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 866–882, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Semantic Novelty Detection in Natural Language Descriptions (Ma et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.66.pdf
Code
 nianzuma/semantic-novelty-detection-in-natural-language-descriptions
Data
COCOVisual Genome