License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.TIME.2021.11
URN: urn:nbn:de:0030-drops-147876
URL: https://drops.dagstuhl.de/opus/volltexte/2021/14787/
Go to the corresponding LIPIcs Volume Portal


Apriceno, Gianluca ; Passerini, Andrea ; Serafini, Luciano

A Neuro-Symbolic Approach to Structured Event Recognition

pdf-format:
LIPIcs-TIME-2021-11.pdf (0.9 MB)


Abstract

Events are structured entities with multiple components: the event type, the participants with their roles, the outcome, the sub-events etc. A fully end-to-end approach for event recognition from raw data sequence, therefore, should also solve a number of simpler tasks like recognizing the objects involved in the events and their roles, the outcome of the events as well as the sub-events. Ontological knowledge about event structure, specified in logic languages, could be very useful to solve the aforementioned challenges. However, the majority of successful approaches in event recognition from raw data are based on purely neural approaches (mainly recurrent neural networks), with limited, if any, support for background knowledge. These approaches typically require large training sets with detailed annotations at the different levels in which recognition can be decomposed (e.g., video annotated with object bounding boxes, object roles, events and sub-events). In this paper, we propose a neuro-symbolic approach for structured event recognition from raw data that uses "shallow" annotation on the high-level events and exploits background knowledge to propagate this supervision to simpler tasks such as object classification. We develop a prototype of the approach and compare it with a purely neural solution based on recurrent neural networks, showing the higher capability of solving both the event recognition task and the simpler task of object classification, as well as the ability to generalize to events with unseen outcomes.

BibTeX - Entry

@InProceedings{apriceno_et_al:LIPIcs.TIME.2021.11,
  author =	{Apriceno, Gianluca and Passerini, Andrea and Serafini, Luciano},
  title =	{{A Neuro-Symbolic Approach to Structured Event Recognition}},
  booktitle =	{28th International Symposium on Temporal Representation and Reasoning (TIME 2021)},
  pages =	{11:1--11:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-206-8},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{206},
  editor =	{Combi, Carlo and Eder, Johann and Reynolds, Mark},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2021/14787},
  URN =		{urn:nbn:de:0030-drops-147876},
  doi =		{10.4230/LIPIcs.TIME.2021.11},
  annote =	{Keywords: Event recognition, learning and reasoning, neuro-symbolic integration}
}

Keywords: Event recognition, learning and reasoning, neuro-symbolic integration
Collection: 28th International Symposium on Temporal Representation and Reasoning (TIME 2021)
Issue Date: 2021
Date of publication: 16.09.2021


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI