<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0508">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A hybrid approach for extracting semantic relations from texts</Title>
  <Section position="3" start_page="0" end_page="57" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Semantic relations extracted from texts are useful for several applications, including question answering, information retrieval, semantic web annotation, and construction and extension of lexical resources and ontologies. In this paper we present an approach for relation extraction developed to semantically annotate relational knowledge coming from raw text, within a framework aiming to automatically acquire high quality semantic metadata for the Semantic Web.</Paragraph>
    <Paragraph position="1"> In that framework, applications such as semantic web portals (Lei et al., 2006) analyze data from texts, databases, domain ontologies, and knowledge bases in order to extract the semantic knowledge in an integrated way. Known entities occurring in the text, i.e., entities that are included in the knowledge base, are semantically annotated with their properties, also provided by the knowledge base and by databases. New entities, as given by a named entity recognition system according to the possible types of entities in the ontology, are annotated without any additional information. In this context, the goal of the relation extraction approach presented here is to extract relational knowledge about entities, i.e., to identify the semantic relations between pairs of entities in the input texts. Entities can be both known and new, since named entity recognition is also carried out. Relations include those already existent in the knowledge base, new relations predicted as possible by the domain ontology, or completely new (unpredicted) relations.</Paragraph>
    <Paragraph position="2"> The approach makes use of a domain ontology, a knowledge base, and lexical databases, along with knowledge-based and empirical resources and strategies for linguistic processing.</Paragraph>
    <Paragraph position="3"> These include a lemmatizer, syntactic parser, part-of-speech tagger, named entity recognition system, and pattern matching and word sense disambiguation models. The input data used in the experiments with our approach consists of English texts from the Knowledge Media Institute (KMi)1 newsletters. We believe that by integrating corpus and knowledge-based techniques and using rich linguistic processing strategies in a completely automated fashion, the approach can achieve effective results, in terms of both accuracy and coverage.</Paragraph>
    <Paragraph position="4"> With relational knowledge, a richer representation of the input data can be produced. Moreover, by identifying new entities, the relation extraction approach can also be applied to ontology population. Finally, since it extracts new relations, it can also be used as a first step for ontology learning.</Paragraph>
    <Paragraph position="5"> In the remaining of this paper we first describe some cognate work on relation extraction, particularly those exploring empirical methods, for various applications (Section 2). We then present  our approach, showing its architecture and describing each of its main components (Section 3).</Paragraph>
    <Paragraph position="6"> Finally, we present the next steps (Section 4).</Paragraph>
  </Section>
class="xml-element"></Paper>