<?xml version="1.0" standalone="yes"?>
<Paper uid="P87-1028">
  <Title>Lexica\] Selection in the Process of Language Generation</Title>
  <Section position="3" start_page="201" end_page="202" type="metho">
    <SectionTitle>
2. Input to Generation
</SectionTitle>
    <Paragraph position="0"> As in McKeown (1985,1986) the input to the process of generation includes information about the discourse within which the proposition is to be generated. In our system the following static knowledge sources constitute the input to generation:  1. A representation of the meaning of the text to be generated, chunked into proposition-size modules, each of which carries its own set of contextual values; (cf. TRANSLA-TOR, Nirenburg et al., 1986, 1987); 2. the semantic knowledge base (concept lexicon) that  contains information about the types of concepts (objects (mental, physical and perceptuM) and processes (states and actions)) in the subject domain, represented with the help of the description module (DRL) of the TRANSLA-TOR knowledge representation language. The organizationa~ basis for the semantic knowledge base is an empirically derived set of inheritance networks (isa, m~ie-of, belongs-to, has-as-part, etc.).</Paragraph>
    <Paragraph position="1"> 3. The specific lexicon for generation, which takes the form of a set of discrimination nets, whose leaves are marked with lex/cal units or lexicM gaps and whose non-leaf nodes contain discrimination criteria that for open-class items are derived from selectional restrictions, in the sense of Katz and Fodor (1963) or Chomsk'y (1965), as modified by the ideas of preference semantics (Wilks, 1975, 1978). Note that most closed.class items have a special status in this generation lexicon: the discrimination nets for them axe indexed not by concepts in the concept lexicon, but rather by the types of values in certain (mostly, nonpropc~itional) slots in input frames;  4. The history of processing, structured Mong the lines of the episodic memory oWaa~zat~on suggested by Kolodner (1984) and including the feedback of the results of actual lexic~l choices during the generation of previous sentences in a text.</Paragraph>
  </Section>
  <Section position="4" start_page="202" end_page="204" type="metho">
    <SectionTitle>
3. Lexical Classes
</SectionTitle>
    <Paragraph position="0"> The distinction between the open- and closed-class lexical unite has proved an important one in psychology and psycholinguistics. The manner in which retrieval of elements from these two classes operates is taken as evidence for a particular mental lexicon structure. A recent proposal (Morrow, 1986) goes even further to explain some of our discourse processing capabilities in term~ of the properties of some closed-da~ lexicM items. It is interesting that for this end Morrow assumes, quite uncritically, the standard division between closed- and open-cla~ lexical categories: 'Open-class categories include content words, such as nouns, verbs and adjectives... Closed-class categories include function words, such as articles and prepositions...' (op. cir., p. 423). We do not elaborate on the definition of the open-class lexical items. We have, however, found it useful to actually define a particular subset of dosed-class items as being discourse-oriented, distinct from those closed-class items whose processing does not depend on discourse knowledge.</Paragraph>
    <Paragraph position="1"> A more complete list of closed-class lexical items will include the following:  We have concluded that the above is not a homogeneous list; its members can be characterized on the basis of what knowledge sources axe used to evaluate them in the generation process. We have established two such distinct knowledge sources: purely propositional information and contextual and discourse knowledge. Those closed-class items that are assigned a denotation only in the context of an utterance will be termed discourse-oriented closed class (DOCC) items; this includes determiners, pronouns, indexicals, and temporal prepositions. Those contributing to the propositional content of the utterance will be called proposition-oriented closed-class (POCC) items. These include modals, locative and function prepositions, and primary verbs.</Paragraph>
    <Paragraph position="2"> According to this classification, the ~definitenees effect&amp;quot; (that is, whether a definite or an intefinite noun phrase is selected for generation) is distinct from general quantification, which appears to be decided on the basis of propositional factors. Note that prepositions no longer form a natural class of simple closed-class items. For example, in (I) the preposition before unites two entities connected through a discourse marker. In (2) the choice of the preposition on is determined by information contained in the propositional content of the sentence.</Paragraph>
    <Paragraph position="3"> (I) John ate breakfast bet'ore leaving for work.</Paragraph>
    <Paragraph position="4"> (2) John sat on the bed.</Paragraph>
    <Paragraph position="5"> We will now suggest a set of processing heuristics for the lexical selection of a member from each lexical class.</Paragraph>
    <Paragraph position="6"> This classification entails that the lexicon for generation will contain only open-cla~ lexical items, because the rest of the lexical items do not have an independent epistemological status, outside the context of an utterance. The selection of closed-class items, therefore, comes as a result of the use of the various control heuristics that guide the process of generation. In other words, they axe incorporated in the procedural knowledge rather than the static knowledge.</Paragraph>
    <Section position="1" start_page="202" end_page="203" type="sub_section">
      <SectionTitle>
4.0 Lexical Selection
4.1 Selection of Open-Class Items
</SectionTitle>
      <Paragraph position="0"> A significant problem in lexical selection of open-class items is how well the concept to be generated matches the desired lexical output. In other words, the input to generate in English the concept 'son's wife's mother' will find no single lexical item covering the entire expression. In Russian, however, this meaning is covered by a single word 'swatja.' This illustrates the general problem of lexlcal gaps and bears on the question of how strongly the conceptual representation is influenced by the native tongue of the knowledge-engineer. The representation must be comprehensive yet flexible enough to accommodate this kind of problem. The processor, on the other hand, must be constructed so that it can accommodate lexical gaps by being able to build the most appropriate phrase to insert in the slot for which no single lexical unit can be selected (perhaps, along the lines of McDonald and Pustejovsky, 1985a).</Paragraph>
      <Paragraph position="1"> To illustrate the knowledge that bears upon the choice of an open-class lexicM item, let us trace the process of lexicai selection of one of the words from the list: desk, table, dining table, coffee table, utility table. Suppose, during a run of our generator we have already generated the following p~.-tial sentence: (3) John bought a ......</Paragraph>
      <Paragraph position="2"> and the pending input is as partially shown in Figures 1-3. Figure I contains the instance of a concept to be generated.</Paragraph>
      <Paragraph position="4"> In order to select the appropriate lexicalization the generator has to traverse the discrimination net, having first found the answers to tests on its nodes in the representation of the concept token (in Figure 1). In addition, the latter representation is compared with the representation of the concept type and if non-default values are found in some slots, then the result of the generation will be a noun phrase with the above noun as its he~l and a number of ~ljectival modifiers. Thus, in our example, the generator will produce 'bla~.k steel dining table'.</Paragraph>
    </Section>
    <Section position="2" start_page="203" end_page="203" type="sub_section">
      <SectionTitle>
4.2 Selection of POCC Items
</SectionTitle>
      <Paragraph position="0"> Now let us discuss the process of generating a proposition oriented lexical item. The example we will use here is that of the function preposition to. The observ'4tion here is that if to is a POCC item, the information required for generating it should be contained within the propositional content of the input representation; no contextual information should be necessary for the lexical decision.</Paragraph>
      <Paragraph position="1"> A~ume that we wish to generate sentence (1) where we axe focussing on the selection of to.</Paragraph>
      <Paragraph position="2"> (1) John walked to the store.</Paragraph>
      <Paragraph position="3"> If the input to the gener~tor is  then the only information necessary to generate the preposition is the case role for the goal, 8tore. Notice that a change in the lexicalization of this attribute would only arise with a different input to the generator. Thus, if the goal were unspecified, we might generate (2) instead of (1); but here the propositional content is different.</Paragraph>
      <Paragraph position="4"> (2) John walked towards the store.</Paragraph>
      <Paragraph position="5"> In the complete paper we will discuss the generation of two other DOCC items; namely, quantifiers and primary verbs, such as do and have.</Paragraph>
    </Section>
    <Section position="3" start_page="203" end_page="204" type="sub_section">
      <SectionTitle>
4.2 Selection of DOCC Items:
</SectionTitle>
      <Paragraph position="0"> * Generating a discourse anaphor Suppose we wish to generate an anaphoric pronoun for an NP in a discourse where its antecedent was mentioned in a previous sentence. We illustrate this in Figure 2. Unlike open-cl~s items, pronominals axe not going to be directly a~ociated with concepts in the semantic knwoledge b~se. Rather, they are generated as a result of decisions involving contextual knowledge, the beliefs of the speaker and hearer, and previous utterances. Suppose, we have alre~ly generated (4) and the next sentence to be generated a.l~o refers to the same individual and informs us that John was at his father's for two days.</Paragraph>
      <Paragraph position="1">  (1) John, visited his father.</Paragraph>
      <Paragraph position="2"> (2) He~ stayed for two days.</Paragraph>
      <Paragraph position="3">  Immediate/ocuz information, in the sense of Grosz (1979) interacts with a history of the previous sentence structures to determine a strategy for selecting the appropriate anaphor. Thus, selecting the appropriate pronoun is an attached procedure. The heuristic for discourse-directed pronomin~ization is as follows:  IF: (I) the input for the generation of a sentence includes an instance of an object present in a recent input; and (2) the the previous instance of this object (the potential antecedent} is in the topic position; and (3) there are few intervening potential antecedents; and (4} there is no focus shift in the space between the occurrence of the antecedent and the current object instance THEN: realize the current instance of that object as a pronoun; consult the grammatical knowledge source for the proper gender, number and case form of the pronoun. null In McDonald and Pustejovsky (1985b) a heursitic was given for deciding when to generate a full NP and when a pronoun. This decision was fully integrated into the grammatical decisions made by MUMBLE in terms of realization-classes, and was no different from the decision to make a sentence active or passive. Here, we are separat. ing discourse information from linguistic knowledge. Our system is closer to McKeown's (1985, 1986) TEXT system, where discourse information acts to constrain the control regimen for Linguistic generation. We extend McKeown's idea, however, in that we view the process of lexical selection as a constraining factor i~ geruera/. In the complete paper, we illustrate how this works with other discourse oriented dosed-class items.</Paragraph>
    </Section>
  </Section>
  <Section position="5" start_page="204" end_page="204" type="metho">
    <SectionTitle>
5. The Role of Focus in Lexical Selection
</SectionTitle>
    <Paragraph position="0"> As witnessed in the previous section, focus is an important factor in the generation of discourse anaphors. In this section we demonstrate that focus plays an important role in selecting non-discourse items as well. Suppose your generator has to describe a financial transaction as a result of which (I) Bill is the owner of a car that previously belonged to John, and (2) John is richer by $2,000.</Paragraph>
    <Paragraph position="1"> Assuming your generator is capable of representing the ~atical structure of the resulting-English sentence, it still faces an important decision of how to express lexically the actual transaction relation. Its choice is to either use buy or 8ell as the main predicate, leading to either (I) or (2), or to use a non-perspective phrasing where neither verb is used.</Paragraph>
    <Paragraph position="2"> (1) Bill bought a car from John for $2,000.</Paragraph>
    <Paragraph position="3"> (2) John sold a car to Bill for $2,000.</Paragraph>
    <Paragraph position="4"> We distinguish the following major contributing factors for selecting one verb over the other;, (I) the intended perspective of the situation, (2) the emphasis of one activity rather than another, (3) the focus being on a particular individual, and (4) previous lexicalizations of the concept. These observations are captured by allowing/ocu8 to operate over several expression including event-types such as tra~/sr. Thus, the variables at pIw for focus indude: null  That is, lexical/zation depends on which expressions are in focus. For example, if John is the immediate focus (as in McKeown (1985)) and beginning-of-transfer is the currentfocus, the generator will lexicalize from the perspective of the sell/ng, namely (2). Given a different focus configuration in the input to the generator, the selection would be different and another verb would be generated.</Paragraph>
  </Section>
class="xml-element"></Paper>