<?xml version="1.0" standalone="yes"?>
<Paper uid="N04-4037">
  <Title>A Lightweight Semantic Chunking Model Based On Tagging</Title>
  <Section position="2" start_page="0" end_page="9978025" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Semantic representation, and, obviously, its extraction from an input text, are very important for several natural language processing tasks; namely, information extraction, question answering, summarization, machine translation and dialog management. For example, in question answering systems, semantic representations can be used to understand the user's question, expand the query, find relevant documents and present a summary of multiple documents as the answer.</Paragraph>
    <Paragraph position="1"> Semantic representations are often defined as a collection of frames with a number of slots for each frame to represent the task structure and domain objects.</Paragraph>
    <Paragraph position="2"> This frame-based semantic representation has been successfully used in many limited-domain tasks. For This work is supported by the ARDA AQUAINT program via contract OCG4423B and by the NSF via grant ISS- null fully used in many limited-domain tasks. For example, in a spoken dialog system designed for travel planning one might have an Air frame with slots Origin, Destination, Depart_date, Airline etc. The drawback of this domain specific representation is the high cost to achieve adequate coverage in a new domain. A new set of frames and slots are needed when the task is extended or changed. Authoring the patterns that instantiate those frames is time consuming and expensive.</Paragraph>
    <Paragraph position="3"> Domain independent semantic representations can overcome the poor portability of domain specific representations. A natural candidate for this representation is the predicate-argument structure of a sentence that exists in most languages. In this structure, a word is specified as a predicate and a number of word groups are considered as arguments accompanying the predicate.</Paragraph>
    <Paragraph position="4"> Those arguments are assigned different semantic categories depending on the roles that they play with respect to the predicate. Researchers have used several different sets of argument labels. One possibility are the nonmnemonic labels used in the PropBank corpus (Kingsbury and Palmer, 2002): ARG0, ARG1, ..., ARGM-LOC, etc. An alternative set are thematic roles similar to those proposed in (Gildea and Jurafsky, 2002): AGENT, ACTOR, BENEFICIARY, CAUSE, etc.</Paragraph>
    <Paragraph position="5"> Shallow semantic parsing with the goal of creating a domain independent meaning representation based on predicate/argument structure was first explored in detail by (Gildea and Jurafsky, 2002). Since then several variants of the basic approach have been introduced using different features and different classifiers based on various machine-learning methods (Gildea and Palmer, 2002;.Gildea and Hockenmaier, 2003; Surdeanu et. al., 2003; Chen and Rambow, 2003; Fleischman and Hovy, 2003; Hacioglu and Ward, 2003; Thompson et. al., 2003 ; Pradhan et. al., 2003). Large semantically annotated databases, like FrameNet (Baker et.al, 1998) and Prop-Bank (Kingsbury and Palmer, 2002) have been used to train and test the classifiers. Most of these approaches can be divided into two broad classes: Constituent-by- null representation of a sentence is linearized into a sequence of its syntactic constituents (non-terminals). Then each constituent is classified into one of several arguments or semantic roles using a number of features derived from its respective context. In the W-by-W method (Hacioglu and Ward, 2003) the problem is formulated as a chunking task and the features are derived for each word (assuming part of speech tags and syntactic phrase chunks are available), and the word is classified into one of the semantic labels using an IOB2 representation. Among those methods, only the W-by-W method considered semantic classification with features created in a bot- null tom-up manner. The motivations for bottom-up analysis are * Full syntactic parsing is computationally expensive null * Taggers and chunkers are fast * Not all languages have full syntactic parsers * The annotation effort required for a full syntactic  parser is larger than that required for taggers and chunkers.</Paragraph>
    <Paragraph position="6"> In this paper, we propose a non-overlapping shallow tree structure, at lexical, syntactic and semantic levels to represent the language. The goal is to improve the portability of semantic processing to other applications, domains and languages. The new structure is complex enough to capture crucial (non-exclusive) semantic knowledge for intended applications and simple enough to allow flat, easier and fast annotation. The human effort required for flat labeling is significantly less than that required for creating tree bank style labels. We present a particular derivation of the structure yielding a lightweight machine learned semantic chunker.</Paragraph>
  </Section>
class="xml-element"></Paper>