<?xml version="1.0" standalone="yes"?>
<Paper uid="W93-0224">
  <Title>References HovY, E. H., LAVID, J. L., MATER, E., MtTrAL, V. O., AND PARTS, C. L. Employing Knowledge Resources in a New Text Planner Architecture. In Aspects of Automated Natttral Lzmguage Generation,</Title>
  <Section position="2" start_page="0" end_page="90" type="metho">
    <SectionTitle>
1 Need for communicative goals
</SectionTitle>
    <Paragraph position="0"> Typically, a speaker has some goal in mind when producing an utterance. Tiffs can be a very concrete goal such as &amp;quot;describe an object&amp;quot;, &amp;quot;motivate the user to perlt~rm an action&amp;quot;, or a much vaguer one, such as discussing an event or simply providing information about a subject. We believe that communicative goals should be represented explicitly in a generation system Ik~r several reasons: * To select the facts to be expressed, as typically, one does not utter everything one knows, and one's comnmnicative intentions influences strongly what is IO be said.</Paragraph>
    <Paragraph position="1"> * To determine the ordering of lacts to be expressed, in the event thai these facts have been determined ahead of time. Indeed, typically, several orderings will be possible, but only a subset of these will be appropriate Ik~r the speaker's intention(s).</Paragraph>
    <Paragraph position="2"> * To handle dialogue (feedback): it has already been shown that a record of the rhetorical relations holding in an utterance is not enough to be able to participate in a dialogue (specifically to recover from communication failures) \[6\]. This is because, as there is not always a one to one relationship between rhetorical relations and communicative goals, communicative goals cannot always be recovered Iiom a record of the rhetorical relationships and the communicative goal is necessary to handle fi~llow-up questions.</Paragraph>
    <Paragraph position="3"> * To take into account any non-textual phenomena: li.~r instance, there may be many ways to elaborate on a specific aspect in a presentation that includes both text and graphics: the specific manner of elaboration will depend upon the communicative goal to be achieved (e.g., providing inli:~rmation about the position of a knob in the control panel may result in a picture of the whole panel, while providing inlk~rmation in order to identity the knob may result in a descriptive phrase such as &amp;quot;the hexagonal knob&amp;quot;).</Paragraph>
    <Paragraph position="4"> We thus argue that communicative goals are important to represent in a generation system and are an essential part of discourse structure (which is not to say they are suMcient, however).</Paragraph>
    <Paragraph position="5"> Some researchers have argued that colnmunicative goals are not necessary l~lr coherent text generation, and have cited architectures such as schemas and systems based on &amp;quot;domain knowledge&amp;quot; to illustrate their point. In our view, this simply illustrates how one can compile out the intentional knowledge necessary  to achieve coherent discourse within a specific domain and context, not that intentions are not an essential part of the discourse structure. It is important to realize that, while Ibr some generation tasks, schemas that compile out intentional information are enough, systems based on such generation schemes are then unable to handle other discourse phenomena such as dialogue.</Paragraph>
    <Paragraph position="6"> Finally, some researchers have conflated the notion of communicative goals with that of rhetorical relations, arguing that it is sufficient to reason about rhetorical relations that hold between certain facts to construct a coherent text, and Ihrther arguing that the choice of a rhetorical relation indicates a specific communicative goal. We do not agree with these arguments, however, at least not with respect to the current theories of rhetorical relations. Indeed, in general, there is not a one-to-one mapping between intentions and rhetorical relations \[6\]. Consider lbr example the Ibllowing dialogue, taken from \[6\]: S: (1) Remove the cover. (2) You'll need the Phillips screwdriver. (3) It's in the top drawer of the toolbox. Do you have it'? H: No.</Paragraph>
    <Paragraph position="7"> Using an RST-type analysis \[4\], (3) is a CIRCUMSTANCE to (2). In terms of intentions, (2) is uttered in an attempt to make the hearer idenli\[y and find the screwdriver. Suppose the hearer is not able to find the screwdriver, because he or she cannot identit3, it. At this point, the speaker needs to recognize that the intention to make the hearer identiI3, the screwdriver has not been achieved. However, the speaker cannot recover this intention simply from knowing that there is a CIRCUMSTANCE relation between (2) and (3). CIRCUMSTANCE could have been used to achieve a variety of other intentions. Similarly, the communicative goal could have been achieved using other rhetorical relations such as, Ior example, ELABORATE-0BJECT-ATTRIBUTE. (For more details, see \[6\]).</Paragraph>
  </Section>
  <Section position="3" start_page="90" end_page="92" type="metho">
    <SectionTitle>
2 Rhetorical relations
</SectionTitle>
    <Paragraph position="0"> Doing text analysis, researchers have tbund that coherent texts tend to exlfibit patterns in their organization, with a limited set of relationships between their components. As a result, people have attempted to characterized these relationships in terms of &amp;quot;rhetorical relations&amp;quot; (or schemas of rlaetorical predicates).</Paragraph>
    <Paragraph position="1"> Typically, the relationships identified above arise because of various filctors, including: * There is a semantic relation that llolds between tile various semantic units (or sets of semantic units taken as a whole) - for example, given the Ihcts: &lt;John has a black car&gt; &lt;John's car is a Honda&gt;, since 'being a Honda' is an attribute of John's car, an item introduced in the first fact, we could say: &amp;quot;John has a black car. It is a Honda&amp;quot; and draw an &amp;quot;elaborate-object-attribute&amp;quot; between the two clauses. * Intentions also sometimes have a canonical clustering: tot example, the goal to provide evidence Ibr a claim often appears when a claim is given. In the resulting text, the relation &amp;quot;evidence&amp;quot; can be drawn between the two spans of text that result IYonl tile two intentional goals.</Paragraph>
    <Paragraph position="2"> * A recognized pattern of thematic progression is present in the text, giving rise to what has been called to a &amp;quot;textual relation&amp;quot; between units of text.</Paragraph>
    <Paragraph position="3"> Essentially, these standard patterns (or standard sets of constraints) have been given names (the names of the &amp;quot;rhetorical relations&amp;quot;, e.g., &amp;quot;elaboration&amp;quot;, &amp;quot;evidence&amp;quot;, or &amp;quot;additive&amp;quot;). These labels seem usetul to perform certain types of reasoning on a text, such as the choice of syntactic realization (including deciding where a sentence break should occur, or the choice of a cue phrase), e.g., \[6,10\], without reasoning explicitly about the actual constraints that hold, and which the speaker wanted to lfighlighl. (Note that this is not to say that there is a clear unambiguous mapping between tile rhetorical relation and the resulting syntactic realization).</Paragraph>
    <Paragraph position="4">  For example, if a system knows that a unit of lext U 1 is in PURPOSE relation to another unit U2, then the realization component can select an appropriate syntax It verbalize U 1 and U2 (e.g., &amp;quot;in order to...&amp;quot;), without re-reasoning about the constraints that hold between the inll~rmation presenled in U 1 and U2.</Paragraph>
    <Paragraph position="5"> Similarly, when several constraints hold and the speaker chooses to highlight one, tiffs can be indicated in the discourse structure by the appropriate preferred label, which then constrains the realization component to choose the appropriate syntactic structure allowing the hearer to recognize the prelerred interpretation.</Paragraph>
    <Paragraph position="6"> For example, consider the propositions &amp;quot;turn on the light&amp;quot; and &amp;quot;flip the switch&amp;quot; (taken lYom \[9\]). These propositions stand in several semantic relations with respect to each other: e.g., at least, CAUSE-EFFECT and PURPOSE. Given the speaker's intention to make the hearer know how to turn the light, depending, for example, on the focus the speaker wishes to have, several texts can be generated, each would highlight a different relation, and each would be analyzed with a ditl~rent RST-relation between the two clauses (e.g., &amp;quot;to turn on the light, flip the switch&amp;quot; or &amp;quot;flipping the switch will cause the light to be turned on&amp;quot;). If the discourse structure is annotated with the interpretation the speaker wishes to preI~r, the appropriate sentence can be generated.</Paragraph>
    <Paragraph position="7"> If, then, when generating text, one keeps track of these rhetorical relations to indicate the reasoning that has already taken place, the constraints that are already known to hold between various units, and which the speaker wishes to highlight, one avoids having to perl~rm that reasoning again, t~r example, to choose a cue phrase. While this might not be imporlant when the relation is a simple semantic one (e.g., &lt;x&gt; is the color of &lt;y&gt;) as tiffs check can be done easily, it is uselul (computationally speaking) when the reasoning that took place is complex (even on a semantic level, lot example, to ligure out that &lt;x&gt; is a cause of &lt;y&gt;, when no causal link exists in the knowledge base). It is also important when several relations exist, diflerent syntactic realization highlight different relations, and one was prelerred by the speaker. In this sense, current relations can be considered as 'macros' that represent a set of constraints that hold between various units (semantic units, textual units or intentions). As such, they might turn out to be an essential level of abstraction to represent as part of a discourse structure in a generation system to control realization. In general, however, there are serious problems with current theories of rhetorical relations such as RST.</Paragraph>
    <Paragraph position="8"> Several problems stand out: * It is not always clear what the label actually stands lbr and what exactly it is used tbr. The constraints they represent are not well defined, may even differ depending on tile surrounding context, and may encompass several different aspects of the discourse.</Paragraph>
    <Paragraph position="9"> * As already pointed out, these relations represent difl~rent types of constraints. This has also been discussed by other researchers \[ 1-3, 5-8\]. Conllating all these faclors by using one term &amp;quot;rhetorical relations&amp;quot; leads to contusion.</Paragraph>
    <Paragraph position="10"> * Few theories allow Ik~r several relations to hold at the same time. ~ Yet. semantic constraints, relations between communicative goals and textual relations usually co-occur \[2, 7\]. In fact, not only do they co-occur between two units of text, but they may also give rise to different non-isomorphic structures.</Paragraph>
    <Paragraph position="11"> However, all these relations (or constraints) contribute to generating an appropriate text and all should be represented and taken into account. Furthermore, several constraints of the same type might be present.</Paragraph>
    <Paragraph position="12"> * To do an analysis in terms of rhetorical relations such as RST, one is often implicitly also doing an intentional analysis. For example, consider the sentence:  Based purely on semantic ground, the sentences would be analyzed as having a condition between their two clauses. The other interpretation of MOTIVATION requires the analyzer to also do the intentional analysis. In truth, of course, both relations co-exist. (This is also discussed in \[7\].)</Paragraph>
  </Section>
class="xml-element"></Paper>