<?xml version="1.0" standalone="yes"?>
<Paper uid="H05-1092">
  <Title>Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), pages 732-739, Vancouver, October 2005. c(c)2005 Association for Computational Linguistics Multi-way Relation Classification: Application to Protein-Protein Interactions</Title>
  <Section position="3" start_page="0" end_page="732" type="intro">
    <SectionTitle>
2 Related work
</SectionTitle>
    <Paragraph position="0"> There has been little work in general NLP on trying to identify different relations between entities. Many papers that claim to be doing relationship recognition in actuality address the task of role extraction: (usually two) entities are identified and the relationship is implied by the co-occurrence of these entities or by some linguistic expression (Agichtein and Gravano, 2000; Zelenko et al., 2002).</Paragraph>
    <Paragraph position="1"> The ACE competition2 has a relation recognition subtask, but assumes a particular type of relation holds between particular entity types (e.g., if the two entities in question are an EMP and an ORG, then an employment relation holds between them; which type of employment relation depends on the type of entity, e.g., staff person vs partner).</Paragraph>
    <Paragraph position="2">  In the BioNLP literature there have recently been a number of attempts to automatically extract protein-protein interactions from PubMed abstracts.</Paragraph>
    <Paragraph position="3"> Some approaches simply report that a relation exists between two proteins but do not determine which relation holds (Bunescu et al., 2005; Marcotte et al., 2001; Ramani et al., 2005), while most others start with a list of interaction verbs and label only those sentences that contain these trigger words (Blaschke and Valencia, 2002; Blaschke et al., 1999; Rindflesch et al., 1999; Thomas et al., 2000; Sekimizu et al., 1998; Ahmed et al., 2005; Phuong et al., 2003; Pustejovsky et al., 2002). However, as Marcotte et al. (2001) note, &amp;quot;... searches for abstracts containing relevant keywords, such as interact*, poorly discriminate true hits from abstracts using the words in alternate senses and miss abstracts using different language to describe the interactions.&amp;quot; Most of the existing methods also suffer from low recall because they use hand-built specialized templates or patterns (Ono et al., 2001; Corney et al., 2004). Some systems use link grammars in conjunction with trigger verbs instead of templates (Ahmed et al., 2005; Phuong et al., 2003). Every paper evaluates on a different test set, and so it is quite difficult to compare systems.</Paragraph>
    <Paragraph position="4"> In this paper, we use state-of-the-art machine learning methods to determine the interaction types and to extract the proteins involved. We do not use trigger words, templates, or dictionaries.</Paragraph>
  </Section>
class="xml-element"></Paper>