<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3317">
  <Title>Using Dependency Parsing and Probabilistic Inference to Extract Relationships between Genes, Proteins and Malignancies Implicit Among Multiple Biomedical Research Abstracts</Title>
  <Section position="2" start_page="0" end_page="104" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Biomedical literature is growing at a breakneck pace, making the task of remaining current with all discoveries relevant to a given research area nearly impossible without the use of advanced NLP-based tools (Jensen et al, 2006). Two classes of tools that provide great value in this regard are those that help researchers find relevant documents and sentences in large bodies of biomedical texts (Muller, 2004; Schuler, 1996; Tanabe, 1999), and those that automatically extract knowledge from a set of documents (Smalheiser and Swanson, 1998; Rzhetsky et al, 2004). Our work falls into the latter category. We have created a prototype software system called BioLiterate, which applies dependency parsing and advanced probabilistic inference to the problem of combining semantic relationships extracted from biomedical texts, have tested this system via experimentation on research abstracts in the domain of the molecular genetics of oncology.</Paragraph>
    <Paragraph position="1"> In order to concentrate our efforts on the inference aspect of biomedical text mining, we have built our BioLiterate system on top of a number of general NLP and specialized bioNLP components created by others. For example, we have handled entity extraction -- perhaps the most mature existing bioNLP technology (Kim, 2004) -- via incorporating a combination of existing open-source tools. And we have handled syntax parsing via integrat- null ing a modified version of the link parser (Sleator and Temperley, 1992).</Paragraph>
    <Paragraph position="2"> The BioLiterate system is quite general in applicability, but in our work so far we have focused on the specific task of extracting relationships regarding interactions between genes, proteins and malignancies contained in, or implicit among multiple, biomedical research abstracts. This application is critical because the extraction of protein/gene/disease relationships from text is necessary for the discovery of metabolic pathways and non-trivial disease causal chains, among other applications (Nedellec, 2005; Davulcu, 2005, Ahmed, 2005).</Paragraph>
    <Paragraph position="3"> Systems extracting these sorts of relationships from text have been developed using a variety of technologies, including support vector machines (Donaldson et al, 2003), maximum entropy models and graph algorithms (McDonald, 2005), Markov models and first order logic (Riedel, 2005) and finite state automata (Hakenberg, 2005). However, these systems are limited in the relationships that they can extract. Most of them focus on relationships described in single sentences. The results we report here support the hypothesis that the methods embodied in BioLiterate, when developed beyond the prototype level and implemented in a scalable way, may be significantly more powerful, particularly in the extraction of relationships whose textual description exists in multiple sentences or multiple documents.</Paragraph>
    <Paragraph position="4"> Overall, the extraction of both entities and single-sentence-embodied inter-entity relationships has proved far more difficult in the biomedical domain than in other domains such as newspaper text (Nedellec, 2005; Jing et al, 2003; Pyysalo, 2004). One reason for this is the lack of resources, such as large tagged corpora, to allow statistical NLP systems to perform as well as in the news domain. Another is that biomedical text has many features that are quite uncommon or even non-existent in newspaper text (Pyysalo, 2004), such as numerical post-modifiers of nouns (Serine 38), non-capitalized entity names (...ftsY is solely expressed during...), hyphenated verbs (X cross-links Y), nominalizations, and uncommon usage of parentheses (sigma(H)-dependent expression of spo0A). While recognizing the critical importance of overcoming these issues more fully, we have not addressed them in any novel way in the context of our work on BioLiterate, but have rather chosen to focus attention on the other end of the pipeline: using inference to piece together relationships extracted from separate sentences, to construct new relationships implicit among multiple sentences or documents.</Paragraph>
    <Paragraph position="5"> The BioLiterate system incorporates three main components: an NLP system that outputs entities, dependencies and basic semantic relations; a probabilistic reasoning system (PLN = Probabilistic Logic Networks); and a collection of hand-built semantic mapping rules used to mediate between the two prior components.</Paragraph>
    <Paragraph position="6"> One of the hypotheses underlying our work is that the use of probabilistic inference in a bioNLP context may allow the capturing of relationships not covered by existing systems, particularly those that are implicit or spread among several abstracts.</Paragraph>
    <Paragraph position="7"> This application of BioLiterate is reminiscent of the Arrowsmith system (Smalheiser and Swanson, 1998), which is focused on creating novel biomedical discoveries via combining pieces of information from different research texts; however, Arrowsmith is oriented more toward guiding humans to make discoveries via well-directed literature search, rather than more fully automating the discovery process via unified NLP and inference.</Paragraph>
    <Paragraph position="8"> Our work with the BioLiterate prototype has tentatively validated this hypothesis via the production of interesting examples, e.g. of conceptually straightforward deductions combining premises contained in different research papers.</Paragraph>
    <Paragraph position="9">  Our future research will focus on providing more systematic statistical validation of this hypothesis.</Paragraph>
  </Section>
class="xml-element"></Paper>