<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1425">
  <Title>Capturing the Interaction between Aggregation and Text Planning in Two Generation Systems</Title>
  <Section position="2" start_page="0" end_page="186" type="abstr">
    <SectionTitle>
Abstract
</SectionTitle>
    <Paragraph position="0"> In natural language generation, different generation tasks often interact with each other in a complex way. We think that how to resolve the complex interactions inside and between tasks is more important to the generation of a coherent text than how to model each individual factor. This paper focuses on the interaction between aggregation and text planning, and tries to explore what preferences exist among the features considered by the two tasks. The preferences are implemented in two generation systems, namely ILEX-TS and a text planner using a Genetic Algorithm. The evaluation emphasises the second implementation and shows that capturing these preferences properly can lead to coherent text.</Paragraph>
    <Paragraph position="1"> 1 Discourse coherence and aggregation hi NLG, theories based on domain-independent rhetorical relations, in particular, Rhetorical Structure Theory (Mann and Thompson, 1987), are often used in text planning, whose task is to select the relevant information to be expressed and organise it into a hierarchical structure which captures certain discourse preferences such as preferences for the use of rhetorical relations.</Paragraph>
    <Paragraph position="2"> In the theory of discourse structure developed by Grosz and Sidner (1986), each discourse segment exhibits two types of coherence: local coherence among utterances inside the segment, and global coherence between this segment and other discourse segments. Discourse segments are connected by either a dominaTzce relation or a satisfaction-precedence relation.</Paragraph>
    <Paragraph position="3"> There has been an effort to synthesise tile two accounts of discourse structure. X loser and Moore (1996) argue that the two theories have considerable common ground, which lies in the correspondence between the notion of dominance and nuclearity. It is possible to map between Grosz and Sidner's linguistic structure and RST text structure, and relation-based coherence and global coherence capture similar discourse properties.</Paragraph>
    <Paragraph position="4"> Oberlander et al. (1999) propose a distinction between two types of discourse coherence: proposition-based coherence, which exists between text spans connected by RST relations except for object-attribute elaboration, and entity-based coherence, which exists between spans of text in virtue of shared entities. entity-based coherence captures the coherence among adjacent propositions, which resembles local coherence in Grosz and Sidner's theory.</Paragraph>
    <Paragraph position="5"> To generate a coherent text, the text planning process must try to achieve both local (entitybased) and global (relation-based) coherence. Since the task of aggregation is to combine sinlple representations together to form a complex one, which in the mean time leads to a shorter text as a whole, aggregation could affect the ordering of text plans and the length of the whole text.. Therefore, it is closely related to tile task of maintaining both types of coherence. Here we treat embedding as a type of aggregation.</Paragraph>
    <Paragraph position="6"> There is no consensus as to where aggregation should happen or how it is related to other generation processes (Wilkinson, 1995; Reape and Mellish, 1999). In many NLG systems, aggregation is a post planning process whose preferences are only partially taken into account by the text planner.</Paragraph>
    <Section position="1" start_page="0" end_page="186" type="sub_section">
      <SectionTitle>
1.1 Aggregation and local coherence
</SectionTitle>
      <Paragraph position="0"> In a structured text plan produced by the text planner, local coherence is normally maintained through the ordering of the selected facts, where  certain types of center transition (e.g. center continuation) :are preferred :over:others (eig,. -; center shifting) (Centering Theory (Grosz et al., 1995)). Aggregation may affect text planning by taking away facts from a sequence featuring preferred center movements for embedding or subordination. As a result, the preferred center transitions in the original sequences could be cut off. For example, comparing the first two descriptions of.a necklace in Figure 1, 2 is less coherent than 1 because of the shifting from the description of the necklace to that of the designer, which is a side effect of embedding.</Paragraph>
      <Paragraph position="1"> Since the centers of sentences are normally NPs and embedding adds non-restrictive components into an NP, it could affect the way a Cb is realised (e.g. preventing it from being a pronoun). As pointed out in (Grosz et al., 1995), different realisations (e.g. pronoun vs. definite description) are not equivalent with respect to their effect on coherence. Therefore, embedding could influence local coherence by forcing a different realisation from that preferred by Centering Theory. There is an obvious need to balance the consideration for local coherence and stylistic preferences.</Paragraph>
    </Section>
    <Section position="2" start_page="186" end_page="186" type="sub_section">
      <SectionTitle>
1.2 Aggregation and global coherence
</SectionTitle>
      <Paragraph position="0"> Different types of aggregation need to be compatible among themselves, in particular, embedding and semantic parataxis and hypotaxis. Using the abstraction of RST, semantic parataxis concerns facts related by explicit multi-nuclear semantic relations (e.g. sequence and contrast) or by implicit connections like parallel common parts. If two facts have at least two identical parallel components, we say that a conjunct or disjunct relation exists between them, and these relations are multi-nuclear relations. Semantic hypotaxis concerns facts connected by nucleus-satellite relations (e.g. cause). Semantic parataxis and hypotaxis feature in relation-based coherence and they depend on the text planner to put the related facts next to each other in order to perform a combination.</Paragraph>
      <Paragraph position="1"> (Cheng, 1998) describes interactions that need to be taken into account in aggregation. Firstly, complex embedded components like non-restrictive clauses may interrupt tile semantic connection or syntactic similarity between a set of clauses. Secondly, the possibilities of other types of aggregation should be considered for both the main fact and the fact to be -embedded .during .:embedding .decision. maki ng...</Paragraph>
      <Paragraph position="2"> And thirdly, performing parataxis inside a hypotaxis could convey wrong information.</Paragraph>
      <Paragraph position="3"> We argue that the effect of aggregation is not limited to the particular NP or sentence where aggregation happens, but to the coherence of the text as a whole. The complex interactions demand the features of aggregation to be evaluated .together with other coherence~ features and aggregation to be planned as a part of text structuring. This requires better coordination between aggregation and other generation tasks as well as among different types of aggregation than is present in current NLG systems.</Paragraph>
      <Paragraph position="4"> In this paper, we describe how to capture the above interactions as preferences among related features, and the implementation of the preferences in two very different generation architectures to produce descriptions of museum objects on display.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>