<?xml version="1.0" standalone="yes"?>
<Paper uid="I05-6002">
  <Title>Obtaining Japanese Lexical Units for Semantic Frames from Berkeley FrameNet Using a Bilingual Corpus</Title>
  <Section position="2" start_page="0" end_page="11" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Making use of deep semantics in information processing is one of the major problems confronting today's NLP community. More and more NLP researchers are realizing that they need semantic/lexical resources that go beyond such ones as WordNet (Fellbaum, 1998) that only specify hierarchical semantic relationships. One of the crucial reasons for this is that raw linguistic data embodies semantic associations that are difficult to capture in terms of such hierarchical relationships, one of which is the so-called &amp;quot;semantic field&amp;quot; effect, a class of associative relationships among words (or concepts). To deal with these issues, deeper semantics are needed with descriptions that incorporate ontological inferences. Let us assume that X attacked Y is to be interpreted.1 This is a complex situation. In interpreting The man attacked a bank, it may be necessary to specify (by inference) that the subject used a weapon (e.g., a gun) and his purpose was to obtain money (illegally), whereas in interpreting The wolf attacked a flock of sheep, it may be necessary to specify that the subject never used a weapon and its purpose was to eat one or two individual sheep (rather than the entire flock) after killing them.</Paragraph>
    <Paragraph position="1"> Relevant inferences are clearly situation-based, or &amp;quot;case-based&amp;quot; in the sense of Case-based Reasoning (Kolodner, 1993), and difficult to specify in terms of the lexical semantic descriptions available in resources such as WordNet (Fellbaum, 1998) which don't specify associative relationships among concepts, including the relationships between ROBBER (e.g., a man) and WAREHOUSE OF VALUABLES (e.g., a bank, museum, jewelry shop), and the one between a PREDATOR (e.g., a wolf) and its PREY (e.g., sheep, rabbit). Thus, the NLP community has a critical need for resources that encode this kind of information.</Paragraph>
    <Paragraph position="2"> Along with PropBank (Kingsbury and Palmer, 2002; Ellsworth et al., 2004), Berkeley FrameNet 1One of the anonymous reviewers told us that it was unclear how ontological inferences of this sort are related to BFN's frame definitions. The question boils down to the question of definition, i.e., what kind of information we need to define semantic frames to encode, and as we will see later, this is exactly the question addressed by FOCAL claiming that BFN frames are too coarse-grained to be used as an effective knowledge-base for ontological inferences.</Paragraph>
    <Paragraph position="3">  (BFN) (Baker et al., 1998) is an ongoing research project that is attempting to meet the demand for resources that encode deeper lexical semantics by providing a semantic frame lexicon (sometimes called the &amp;quot;FrameNet&amp;quot;) and a corpus annotated for semantic information encoded in terms of semantic frames.</Paragraph>
    <Paragraph position="4"> Thus far, BFN has produced &amp;quot;a lexical database that currently contains more than 8,900 lexical units, more than 6,100 of which are fully annotated, in more than 625 semantic frames, exemplified in more than 135,000 annotated sentences&amp;quot; (cited from the FrameNet web page). Other ongoing projects, i.e., the German FrameNet or &amp;quot;SALSA&amp;quot; (Erk et al., 2003), the Spanish FrameNet (Subirats and Petruck, 2003), and the Japanese FrameNet (Ohara et al., 2003), are trying to build lexical resources that are compatible with the BFN, but for Japanese at least, no data has been released in a usable form, except for a few annotation examples for verbs of motion.</Paragraph>
    <Paragraph position="5"> In sum, no useful resource exists for frame-based description/analysis of Japanese. This is one of the reasons that we attempted the task in this paper, along with our efforts to assess the usefulness of the database provided by BFN.</Paragraph>
    <Paragraph position="6"> The anonymous reviewers of our paper pointed out that there have been some similar projects and other methodologies that have tried to translate BFN into other languages automatically, such as BiFrameNet (Chen and Fung, 2004) and Romance FrameNet2, and that it would have been better to include the comparison against them.</Paragraph>
    <Paragraph position="7"> BiFrameNet presented an automatic approach to constructing a bilingual semantic network using the Chinese HowNet, which is a Chinese ontology. While it is an interesting approach, we have not compared their results with ours, mainly because they seem to have used different resources and had somewhat different goals, along with the space consideration.</Paragraph>
    <Paragraph position="8"> No papers are released, let alone being available to us, related to the Romance FrameNet project for the time being. We couldn't help putting a comparison with it on hold.3  to mention Romance FrameNet project in our paper; it is just unreasonable. The project was announced on June 1 on the</Paragraph>
  </Section>
class="xml-element"></Paper>