<?xml version="1.0" standalone="yes"?>
<Paper uid="C02-1156">
  <Title>Putting Frames in Perspective</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> FrameNet (Fillmore et al., 2001) is an online lexical resource1 designed according to the principles of frame semantics (Fillmore, 1985; Petruck, 1996).</Paragraph>
    <Paragraph position="1"> It thus takes as foundational the assumptions that (1) lexical items draw on rich conceptual structures, or frames, for their meaning and function; and (2) conceptually related lexical items may foreground different aspects of the same background frame.</Paragraph>
    <Paragraph position="2"> Verbs involved with commercial events serve as  canonical examples: (1) a. Chuck bought a car from Jerry for $1000.</Paragraph>
    <Paragraph position="3"> b. Jerry sold a car to Chuck for $1000.</Paragraph>
    <Paragraph position="4"> c. Chuck paid Jerry $1000 for a car.</Paragraph>
    <Paragraph position="5"> d. Jerry charged Chuck $1000 for a car.</Paragraph>
    <Paragraph position="6"> e. Chuck spent $1000 on a car.</Paragraph>
    <Paragraph position="7">  The sentences in (1) might describe the same interaction - in which one individual (Chuck) transfers money ($1000) to another (Jerry) in exchange for some goods (a car) - but differ in the perspective they impose on the scene.</Paragraph>
    <Paragraph position="8"> The shared inferential structure of verbs like buy and sell is captured in FrameNet by the COMMERCE frame, which is associated with a set of situational  roles, or frame elements (FEs), corresponding to event participants and props. These FEs are used to annotate sentences like those in (1), yielding: (2) a. [Chuck]Buyer bought [a car]Goods [from Jerry]Seller [for $1000]Payment.</Paragraph>
    <Paragraph position="9"> b. [Jerry]Seller sold [a car]Goods [to Chuck]Buyer [for $1000]Payment.</Paragraph>
    <Paragraph position="10"> FE tags act as a shorthand that allows diverse verbs to tap into a common subset of encyclopedic knowledge. Moreover, regularities in the set of FEs realized with specific lexical items can be taken as correlated with their favored perspective.</Paragraph>
    <Paragraph position="11"> A significant gap remains, however, between the unstructured and intuitively chosen tag sets used in FrameNet and a formal characterization of the inter-related actions and relations holding among them. An explicit representation of such frame-semantic information is needed to fully realize FrameNet's potential use in text understanding and inference (Fillmore and Baker, 2001). In this paper we attempt to bridge the gap by defining a formalism that unpacks the shorthand of frames into structured event representations. These dynamic representations allow annotated FrameNet data to parameterize event simulations (Narayanan, 1999b) that produce fine-grained, context-sensitive inferences. We illustrate our formalism for the COMMERCE frame and show how it can account for some of the wide-ranging consequences of perspective-taking.</Paragraph>
  </Section>
class="xml-element"></Paper>