Conference Paper

Information Extraction from Text Based on Semantic Inferentialism.

DOI: 10.1007/978-3-642-04957-6_29 Conference: Flexible Query Answering Systems, 8th International Conference, FQAS 2009, Roskilde, Denmark, October 26-28, 2009. Proceedings
Source: DBLP


One of the growing needs of information extraction (IE) from text is that the IE system must be able to perform enriched inferences
in order to discover and extract information. We argue that one reason for the current limitation of the approaches that use
semantics for that is that they are based on ontologies that express the characteristics of things represented by names, and
seek to draw inferences and to extract information based on such characteristics, disregarding the linguistic praxis (i.e.
the uses of the natural language). In this paper, we describe a generic architecture for IE systems based on Semantic Inferentialism.
We propose a model that seeks to express the inferential power of concepts and how these concepts, combined in sentence structures,
contribute to the inferential power of sentences. We demonstrate the validity of the approach and evaluate it by deploying
an application for extracting information about crime reported in on line newspapers.

5 Reads
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a semi-automated method for the acquisition of common-sense and inferentialist concepts in Portuguese. Its innovative feature is a module of reasoning over the pre-existing knowledge that aims to offer original content to the user, helping in the expression of semantic relationships and validation of new concepts. This reasoning process is based on heuristics and syntactic analysis of noun phrases. A qualitative evaluation with users who interacted with the system built on the proposed method showed that the interactions made in the process of knowledge acquisition are more productive since the user is reminded about semantic relations and common-sense knowledge about the new concepts.
    Journal of the Brazilian Computer Society 03/2012; 19(1). DOI:10.1007/s13173-012-0082-6
  • [Show abstract] [Hide abstract]
    ABSTRACT: This article describes an architecture for Information Extraction systems on the web, based on Natural Language Processing (NLP) and especially geared toward the exploration of information about crime. The main feature of the architecture is its NLP module, which is based on the Semantic Inferential Model. We demonstrate the feasibility of the architecture through the implementation thereof to provide input for a collaborative web-based system of registering crimes called WikiCrimes.
    IEEE International Conference on Intelligence and Security Informatics, ISI 2010, Vancouver, BC, Canada, May 23-26, 2010, Proceedings; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Often, the information necessary for a complete understanding of texts is implicit, which requires drawing inferences from the use of concepts in the linguistic praxis. We consider that the usual semantic reasoners of natural language systems face difficulties in capturing this knowledge, due mainly to the lack of linguistic-semantic resources that support reasoning of this nature. This paper presents a new linguistic resource that expresses semantic-inferentialist knowledge for the Portuguese language – InferenceNet.Br – containing a base of concepts and a base of sentence patterns. These bases provide content for a top layer of semantic reasoning in natural language systems, where semantic relations are considered according to their roles in inferences, as premises or conclusions. This linguistic resource was used in a system for extracting information about crime, and the results of this proof of concept are discussed.
    Computational Processing of the Portuguese Language, 9th International Conference, PROPOR 2010, Porto Alegre, RS, Brazil, April 27-30, 2010. Proceedings; 01/2010
Show more