<?xml version="1.0" standalone="yes"?>
<Paper uid="P93-1044">
  <Title>Guiding an HPSG Parser using Semantic and Pragmatic Expectations</Title>
  <Section position="4" start_page="0" end_page="295" type="metho">
    <SectionTitle>
FEATURE MAPPING
</SectionTitle>
    <Paragraph position="0"> Planning &amp; generation of coherent &amp;quot;speech&amp;quot; in a conversation requires some understanding of the &amp;quot;hearer's&amp;quot; perspective. Thus the speaker naturally has some (limited) knowledge about possible responses from the hearer. This knowledge can be given to the same planner used for generation, producing a partial set of pragmatic features or expectations. These pragmatic expectations can then be mapped into the systemic grammar, producing a set of semantic and syntactic expectations about what other participants in the conversation will say.</Paragraph>
    <Paragraph position="1"> The technique explored here is to bring such expectations to bear during the parse process, guiding the parser to the most likely solution in a best-first manner. It is thus necessary that the generated expectations be mapped into a form which can be directly compared with constituents proposed within the HPSG parse.</Paragraph>
    <Paragraph position="2"> Consider the sentence &amp;quot;Robin promised to come at noon&amp;quot;, with the following context: Sandy: &amp;quot;I guess we should get started, what time did they say they would be here?&amp;quot; Kim: &amp;quot;Robin promised to come at noon&amp;quot; A set of plausible partial expectations generated by the pragmatic and systemic components in anticipation of Kim's response might be:  In these expectations the first list of each pair (e.g. (S BETA)) represents a functional role within the expected sentence. The  second list in each pair are sets (in this case singleton) of expected features for the associated functional roles. These expected features assert expectations which are both semantic (e.g. PROMISED) and syntactic (e.g. ((S BETA TEMPORAL) (PP)) asserts both the existance and location of a temporal adjunct PP).</Paragraph>
    <Paragraph position="3"> Note that in these expectations the temporal adjunct &amp;quot;at noon&amp;quot; should modify the embedded clause &amp;quot;to come&amp;quot;, as would be expected in the specified context.</Paragraph>
    <Paragraph position="4"> Next consider the possible HPSG parses of the example sentence. Figures 1 and 2 below illustrate two semantically distinct parses generated by our HPSG parser.</Paragraph>
    <Paragraph position="5">  Mapping expected features into HPSG constraints: Features generated from pragmatic expectations can be mapped into constraints on HPSG structures, stated in terms of feature descriptions. Below are the HPSG feature descriptions corresponding to the pragmatically generated features PP and UNMARKED-DECLARATIVE.</Paragraph>
    <Paragraph position="7"> Mapping expected functional roles into HPSG constituent structure: Pragmatic expectations are expected within certain functional roles, such a SUBJECT, PREDICATOR, BETA (the embedded clause) etc. This structural information must be used to assert the constraints into the relevant HPSG substructures. This mapping is not as straightforward as the feature mapping technique, as the structure induced by the systemic grammar is &amp;quot;flatter&amp;quot; than the structure produced by HPSG.</Paragraph>
    <Paragraph position="8"> Consider the following pragmatically generated expectation: ((S TEMPORAL) (PP)) Such an expectation may be realized by great variety of HPSG structural realizations, e.g.:  1. Kim ran at noon 2. Kim could run home at noon 3. K.im could have been running home at noon 4. Kim ran east at noon.</Paragraph>
    <Paragraph position="9">  In these examples modal verb operators (1-3) and multiple adjuncts (4) vary the actual structural depth of the temporal PP within the HPSG model. Thus a given systemic role path may have numerous HI~G constituent path realizations. One possible mapping technique is to generate constraints expressing all possible HPSG structural variants. This, however would lead in many cases to a combinatorial explosion of constraints. The technique employed by this study was to add a new clause attribute to verbal HPSG signs, and use this attribute to embed within the signs a &amp;quot;clausally flattened&amp;quot; structures. Each HPSG verbal sign in the same clause structure shares the same clausal value. The clause value is a structure with labels for each systemic role, where each label points to the constituent which fills that role in the given verbal clause. A clausal boundry is said to exist between distinct clausal domains. A clausal structure is illustrated in figure 5:</Paragraph>
    <Paragraph position="11"> The current mapping only considers the mapping of roles within verbal signs. Similar role structures may exist for other constituent types, such as for noun phrase. Thus far the verbal clause boundary definition has been adequate for other phrasal structures.</Paragraph>
  </Section>
  <Section position="5" start_page="295" end_page="296" type="metho">
    <SectionTitle>
GUIDING THE HPSG PARSE
</SectionTitle>
    <Paragraph position="0"> The guidance strategy employed is to evaluate all proposed edges (i.e. complete and partially complete constituents) against the expectations, ranking each based on the relative similarity with the expectations. These edges are  then placed in an agenda (a list of priority queues) and removed from the agenda and included in the partial parse in a best first order.</Paragraph>
    <Paragraph position="1"> Critical to the success of a best-first algorithm is the heuristic evaluation function used to order the proposed constituents.</Paragraph>
    <Paragraph position="2"> The heuristic evaluation function: The heuristic evaluation function is based on three specific types of tests: I. Role match - does a constituent match a role's set of expected features? II. Role path match - is a constituent role path compatible with the roles of its children? III. Clausal completeness - are all clausal roles expected for this constituent present? Tests II and III above require that constituents under consideration have roles already assigned to them. For example, in the case of II, the test requires roles for both the new constituent and the proposed daughters of the constituent. But since the parse strategy employeed is bottom-up, role paths cannot be anchored to a root, and thus fully known, until parse completion. The solution to this dilemma is to hypothesise a constituent's role using a process similar to abduction. Two types of knowledge are exploited in this process. First, roles with features which subsume or are consistant with a proposed constituent are considered good candidate roles. Also, roles may also be inferred by projecting up from the roles already hypothesized for the children. By intersecting these two sources of role evidence, the list of hypothesized roles can be refined (by ruling out roles without both types of evidence). In this manner the hypothesized roles of later constituents can be refined from descendant constituents. In the case of roles projected from daughters, clausal boundary knowledge must be applied to correctly infer the parent role.</Paragraph>
  </Section>
class="xml-element"></Paper>