Skip to main content

Learning to Extract Action Descriptions from Narrative Text

Ludwig, Oswaldo, Do, Quynh, Smith, Cameron, Cavazza, Marc, Moens, Marie-Francine (2017) Learning to Extract Action Descriptions from Narrative Text. IEEE Transactions on Computational Intelligence and AI in Games, . pp. 1-14. ISSN 1943-068X. E-ISSN 1943-0698. (doi:10.1109/TCIAIG.2017.2657690)

PDF - Author's Accepted Manuscript
Download (379kB) Preview
[img]
Preview
PDF - Pre-print
Restricted to Repository staff only
Contact us about this Publication Download (1MB)
[img]
Official URL
http://doi.org/10.1109/TCIAIG.2017.2657690

Abstract

This paper focuses on the mapping of natural language sentences in written stories to a structured knowledge representation. This process yields an exponential explosion of instance combinations since each sentence may contain a set of ambiguous terms, each one giving place to a set of instance candidates. The selection of the best combination of instances is a structured classification problem that yields a highdemanding combinatorial optimization problem which, in this paper, is approached by a novel and efficient formulation of a genetic algorithm, which is able to exploit the conditional independence among variables, while improving the parallel scalability. The automatic rating of the resulting set of instance combinations, i.e. possible text interpretations, demands an exhaustive exploitation of the state-of-the-art resources in natural language processing to feed the system with pieces of evidence to be fused by the proposed framework. In this sense, a mapping framework able to reason with uncertainty, to integrate supervision, and evidence from external sources, was adopted. To improve the generalization capacity while learning from a limited amount of annotated data, a new constrained learning algorithm for Bayesian networks is introduced. This algorithm bounds the search space through a set of constraints which encode information on mutually exclusive values. The mapping of natural language utterances to a structured knowledge representation is important in the context of game construction, e.g. in an RPG setting, as it alleviates the manual knowledge acquisition bottleneck. The effectiveness of the proposed algorithm is evaluated on a set of three stories, yielding nine experiments. Our mapping framework yields performance gains in predicting the most likely structured representations of sentences when compared with a baseline algorithm.

Item Type: Article
DOI/Identification number: 10.1109/TCIAIG.2017.2657690
Uncontrolled keywords: Semantics, Knowledge representation, Context, Games, Bayes methods, Cognition, Data models
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.76.E95 Expert Systems (Intelligent Knowledge Based Systems)
Divisions: Faculties > Sciences > School of Engineering and Digital Arts
Depositing User: Marc Cavazza
Date Deposited: 31 Jan 2017 16:58 UTC
Last Modified: 01 Aug 2019 10:41 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/60145 (The current URI for this page, for reference purposes)
Cavazza, Marc: https://orcid.org/0000-0001-6113-9696
  • Depositors only (login required):

Downloads

Downloads per month over past year