<?xml version="1.0" standalone="yes"?>
<Paper uid="P96-1004">
  <Title>Morphological Cues for Lexical Semantics</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Some natural language processing (NLP) tasks can be performed with only coarse-grained semantic information about individual words. For example, a system could utilize word frequency and a word cooccurrence matrix in order to perform information retrieval. However, many NLP tasks require at least a partial understanding of every sentence or utterance in the input and thus have a much greater need for lexical semantics. Natural language generation, providing a natural language front end to a database, information extraction, machine translation, and task-oriented dialogue understanding all require lexical semantics. The lexical semantic information commonly utilized includes verbal argument structure and selectional restrictions, corresponding nominal semantic class, verbal aspectual class, synonym and antonym relationships between words, and various verbal semantic features such as causation and manner.</Paragraph>
    <Paragraph position="1"> Machine readable dictionaries do not include much of this information and it is difficult and time consuming to encode it by hand. As a consequence, current NLP systems have only small lexicons and thus can only operate in restricted domains. Automated methods for acquiring lexical semantics could increase both the robustness and the portability of such systems. In addition, such methods might provide inSight into human language acquisition.</Paragraph>
    <Paragraph position="2"> After considering different possible approaches to acquiring lexicM semantic information, this paper concludes that a &amp;quot;surface cueing&amp;quot; approach is currently the most promising. It then introduces morphological cueing, a type of surface cueing, and discusses an implementation. It concludes by evaluating morphological cues with respect to a list of desiderata for good surface cues.</Paragraph>
  </Section>
class="xml-element"></Paper>