<?xml version="1.0" standalone="yes"?>
<Paper uid="W90-0109">
  <Title>Abstract Linguistic Resources for Text Planning</Title>
  <Section position="4" start_page="63" end_page="64" type="metho">
    <SectionTitle>
3 The notation of the phrase structure in the diagram is the
</SectionTitle>
    <Paragraph position="0"> notation used in the linguistic component Mumble-86. While it is slightly unconventional in that it explicitly represents the path that wiU be followed in traversing the structure, it is in other respects fairly standard in its terminology. I use it here since it is the notation I work with and because it lends a concreteness and reality to the diagrams since this is the structure the linguistic component will actually build when generating this sentence.</Paragraph>
    <Paragraph position="1"> 4 The semantic relations shown here, &amp;quot;agent&amp;quot; and &amp;quot;patient&amp;quot;, are capturing internally consistent relations. They are not attempting to carry the kind of weight and meaning as, say, the terms in theta-theory.</Paragraph>
    <Paragraph position="3"/>
    <Section position="1" start_page="64" end_page="64" type="sub_section">
      <SectionTitle>
2.3 Developing a set of abstractions
</SectionTitle>
      <Paragraph position="0"> The development of the full vocabulary of particular abstract resources is an ongoing process. The motivation for determining the abstractions comes from analysis of the language and what is expressible. A great deal of work has already been done in linguistics that can contribute to defining the vocabulary of abstractions. In this section, I look at the work of four linguists in particular who have influenced my development of the current set of semantic categories: Jackendoff, Talmy, Pustejovsky, and Grimshaw. While their work is very different in character, all explore regularities in language using a more semantic than syntactic vocabulary.</Paragraph>
      <Paragraph position="1"> The notion of a semantic category used here was initially influenced by the work of Jackendoff (1983) who makes the following claim about the relationship between language structure and meaning: Each contentful major syntactic constituent of a sentence maps into a conceptual constituent in the meaning of the sentence. 5 Included in his vocabulary of conceptual categories are Thing, Path, Action, Event, and Place.</Paragraph>
      <Paragraph position="2"> Abstractions over concrete resources However, while Jackendoffs categories are useful in that they span the entire language (since they are projections from the syntactic categories), they are not discriminatory enough to capture the constraints necessary to ensure expressibility. For example, two of the semantic categories in the example above, NAMED-INDIVIDUAL and SAMPLE-OF-A-KIND, are subsumed by the same category in JackendoWs set, OBJECT.</Paragraph>
      <Paragraph position="3"> Similarly, his category EVENT has finer distinctions available in the actual resources: a finite verb (one which expresses tense) with its arguments expresses what I call an EVENT (Peter decided to go to the beach), whereas a nonfinite verb can express a generic ACTIVITY (to decide to go to the beach). Nominalizations make the event or activity into an OBJECT and different forms of nominalizations can pick out different aspects of the event, such as the PROCESS (Deciding to go to the beach took Peter all morning) or the RESULT (The decision to go to the beach caused controversy).</Paragraph>
      <Paragraph position="4"> Figure 2 shows a partial hierarchy of semantic categories that reflects these distinctions.</Paragraph>
      <Paragraph position="5">  In using these finer semantic categories in the planning vocabulary for generation, we are making a stronger claim than JackendoWs, namely that these categories define what combinations of surface resources are possible in the language. For example, an ACTIVITY cannot have a tense marker, since by definition it is not grounded in time. The categories also serve to constrain how constituents are composed.</Paragraph>
      <Paragraph position="6"> For example, if we choose the EVENT perspective (e.g.</Paragraph>
      <Paragraph position="7"> Michael decided to go to the beach), we can add an adjunct of type MANNER to it (Michael quickly decided to go to the beach) but we cannot add an adjunct of type PROPERTY (*Michael important(ly) decided to go to the beach) 6. However, if we choose an OBJECT perspective (Michael made a decision), the PROPERTY adjunct oan be added (Michael made an important decision ). Both perspectives are available, and the text planner's choice must be consistent with the kinds of adjunctions it intends to make.</Paragraph>
      <Paragraph position="8"> Research in lexical semantics has contributed a great deal to defining these finer grained semantic categories. Talmy's (1987) extensive cross language research resulted in a set of categories for the notions expressed grammatically in a language. Pustejovsky's (1989) Event Semantic Structure makes a three way distinction of event types (state, process, transition) which both captures the effects of nonlinear composition of resources and provides constraints on the composition of these types with other resources. Grirnshaw's analysis of nominals (1988) contributed to the definition of object types which convey particular perspectives on events, such as result and process.</Paragraph>
      <Paragraph position="9">  3. Using Abstract Resources for Text  In order to plan complex utterances and ensure they are expressible in language, i.e. can be successfully realized as grammatical utterances, the text planning process 6 Following the general convention in linguistics, we use a &amp;quot;*&amp;quot; to mark ungrammatical sentences, and a &amp;quot;?&amp;quot; to mark questionable ones.</Paragraph>
      <Paragraph position="11"> of semantic categories must know (1) what realizations are available to an element, that is, what resources are available for it, (2) the constraints on the composition of the resources, and  (3) what has been committed to so far in the utterance that may constrain the choice of resource. The first two  points are addressed by the the use of abstract linguistic resources discussed in the previous section. The third is addressed by the ongoing Text Structure representation of the utterance being planned, which is also in abstract linguistic terms. In this section, I describe the Text Structure and how it mediates and constrains the text planning process.</Paragraph>
    </Section>
    <Section position="2" start_page="64" end_page="64" type="sub_section">
      <SectionTitle>
3.1 Text Structure 7
</SectionTitle>
      <Paragraph position="0"> Text Structure is a tree in which each node represents a constituent in the utterance being planned. Figure 3 shows an example of the Text Structure representation for the utterance: &amp;quot;Karen likes watching movies on Sundays&amp;quot;.</Paragraph>
      <Paragraph position="1"> Text Structure represents the following information: Constituency: The nodes in the Text Structure tree reflect the constituency of the utterance. A constituent may range in size from a paragraph to a single word.</Paragraph>
      <Paragraph position="2"> Structural relations among constituents: Each node is marked with its structural relation to its parent (the top label) and to its children (the bottom label on nodes with children). Structural relations indicate where the tree can be expanded: composite nodes may be incrementally extended whereas a head/argument structure is built in a single action by the planner, reflecting the atomicity of predicate/argument structure.</Paragraph>
      <Paragraph position="3"> 7 Note that I will not attempt a formal definition. I agree with the text linguist Beaugrande that &amp;quot;Formalism should not be undertaken too early. Unwieldy constructs borrowed from mathematics and logic are out of place in domains where the basic concepts are still highly approximative. Such constructs give a false sense of security of having explained what has in fact only been rewritten in a formal language.&amp;quot; Beaugrande &amp; Dressier, 1981, p.14.</Paragraph>
      <Paragraph position="4">  Semantic category the constituent expresses: The labels in the center of the node (in bold) show the lexical head (when applicable, in italics) and the semantic category the constituent expresses.</Paragraph>
    </Section>
    <Section position="3" start_page="64" end_page="64" type="sub_section">
      <SectionTitle>
3.2 Using the Text Structure for Text
Planning
</SectionTitle>
      <Paragraph position="0"> The abstract linguistic terms of our planning vocabulary can provide constraints on the composition of the message to ensure that it will continue to be expressible as we add more information. For example, the semantic category of a constituent can constrain the kind of information that can be composed into that constituent.</Paragraph>
      <Paragraph position="1"> Consider the earlier example contrasting &amp;quot;decide&amp;quot; and &amp;quot;make a decision&amp;quot;, where in order to add an adjunct of type PROPERTY, the RESULT perspective of the EVENT must be explicit in the utterance, as shown in  In summary, the Text Structure can constrain the following types of decisions within the text planner: * where additional information may be added (e.g.</Paragraph>
      <Paragraph position="2"> structure can only he added at leaves and nodes of type COMPOSITE; furthermore, in an incremental pipeline architecture such as this, information can only be added ahead of the point of speech) * what functions and positions are available for the elements being added in (e.g. matrix or adjunc0 * what form the added element must be in (e.g. an object of type property can be added to a thing but not to an event)</Paragraph>
    </Section>
  </Section>
  <Section position="5" start_page="64" end_page="64" type="metho">
    <SectionTitle>
ADJUNCT
on ::temporal-relation
HEAD \
ARGUMENT I sunday ::sample-of-a-kind
</SectionTitle>
    <Paragraph position="0"> watching movies on Sundays&amp;quot; The Text Structure representation is used in the text planner of my SPOKESMAN generation system (Meteer 1989). It serves as an intermediate representation between a variety of application programs and the linguistic realization component Mumble-86 (McDonald 1984, Meteer, et.al 1987). Portions of the outputs for three of these applications are shown below. THE MAIN STREET SIMULATION PROGRAM (ABRE'rr, ET AL 1989) Karen 10:49 AM: Karen is at Internationalconglomerate, which is at 1375 Main Street. Her skills are managing and cooking. Karen likes watching movies. She watched &amp;quot;The Lady Vanishes&amp;quot; on Sunday.</Paragraph>
  </Section>
  <Section position="6" start_page="64" end_page="64" type="metho">
    <SectionTitle>
SEMI-AUTOMATED FORCES (SAF) PROJECT 8
</SectionTitle>
    <Paragraph position="0"> C/1 TB is to the east and its mission is to attack Objective GAMMA from ES646905 to ES758911 at 141423 Apr. All TB is to the south. B/1 TB and HHC/2 are to the east.</Paragraph>
  </Section>
  <Section position="7" start_page="64" end_page="64" type="metho">
    <SectionTitle>
AIRLAND BATrLE MANAGEMENT PROJECT 9
</SectionTitle>
    <Paragraph position="0"> Conduct covering force operations along avenues B and C to defeat the lead regiments of the first tactical echelon in the CFA in assigned sector.</Paragraph>
  </Section>
  <Section position="8" start_page="64" end_page="68" type="metho">
    <SectionTitle>
4. Contrasting Approaches
</SectionTitle>
    <Paragraph position="0"> The greatest difference between other approaches to NLG and ours is that they work directly in terms of concrete resources rather than introducing an abstract intermediate level as I have proposed here. Approaches fall into two classes: (1) those that use a two component architecture in which a text planner chooses and organizes the information to be expressed and passes it to a separate linguistic component that chooses the concrete resources to express the plan (e.g. McKeown 1985, Paris 1987, or Hovy 1988); and (2) those that use a single component which does the planning of the text directly in terms of the concrete resources (e.g. Nirenburg et al. 1989, Danlos 1987).</Paragraph>
    <Paragraph position="1"> The limitation of the two component architecture is that the text planner is not working in linguistic terms, and so it cannot be sure that the plan it builds is expressible, i.e. can have a successful realization. Most such systems avoid this problem by limiting the expressiveness of the system overall. The planner begins with a set of propositions, each verb-based and able to be realized independently as a simple sentence. It then organizes the propositions into a coherent discourse by combining them according to predefined &amp;quot;schemas&amp;quot; representing plausible discourse relationships.</Paragraph>
    <Paragraph position="2"> Subsequent choices of linguistic resources are all local to the propositions and not sensitive to the schemas or other context, except for the discourse-level connectives used in combining the propositions and occasionally a discourse history governing the use of pronouns.</Paragraph>
    <Paragraph position="3"> However, clauses in actual texts by people reflect a combination of multiple atomic units. Systems that ignore this and begin with units that are inevitably realized as kernel clauses under-utilize the expressive power of natural language, which can use complex noun phrases, nominalizations, adverbial phrases, and other adjuncts to pack information from multiple units into one clause.</Paragraph>
    <Paragraph position="4"> The second approach, using single component architecture, recognizes the limitation of separating text  planning from the choice of linguistic resources, and removes this division, letting the text planner manipulate concrete resources directly. However, this increase in complexity for the text planner has repercussions for the complexity of the architecture overall. For example, Nirenburg uses a blackboard architecture that must backtrack when the text planner has chosen incompatible concrete resources.</Paragraph>
  </Section>
class="xml-element"></Paper>