<?xml version="1.0" standalone="yes"?>
<Paper uid="W96-0404">
  <Title>Approximate Generation from Non-Hierarchical Representations</Title>
  <Section position="3" start_page="0" end_page="32" type="intro">
    <SectionTitle>
2 Generation from Non-
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="0" end_page="32" type="sub_section">
      <SectionTitle>
Hierarchical Representations
</SectionTitle>
      <Paragraph position="0"> The input for generation systems varies radically from system to system. Many generators expect their input to be cast in a tree-like notation which enables the actual systems to assume that nodes higher in the semantic structure are more prominent than lower nodes. The semantic representations used are variations of a predicate with its arguments. The predicate is realised as the main verb of the sentence and the  arguments are realised as complements of the main verb--thus the control information is to a large extent encoded in the tree-like semantic structure. Unfortunately, such dominance relationships between nodes in the semantics often stem from language considerations and are not always preserved across languages. Moreover, if the semantic input comes from other applications, it is hard for these applications to determine the most prominent concepts because linguistic knowledge is crucial for this task. The tree-like semantics assumption leads to simplifications which reduce the paraphrasing power of the generator (especially in the context of multilingual generation). 2 In contrast, the use of a non-hierarchical representation for the underlying semantics allows the input to contain as few language commitments as possible and makes it possible to address the generation strategy from an unbiased position. We have chosen a particular type of a non-hierarchical knowledge representation formalism, conceptual graphs \[24\], to represent the input to our generator. This has the added advantage that the representation has well defined deductive mechanisms. A graph is a set of concepts connected with relations. The types of the concepts and the relations form generalisation lattices which also help define a subsumption relation between graphs.</Paragraph>
      <Paragraph position="1"> Graphs can also be embedded within one another. The counterpart of the unification operation for conceptual graphs is maximal join (which is non-deterministic). Figure 1 shows a simple conceptual graph which does not have cycles. The arrows of the conceptual relations indicate the domain and range of the relation and do not impose a dominance relationship.</Paragraph>
      <Paragraph position="2">  The use of semantic networks in generation is not new \[21, 18\]. Two main approaches have been employed for generation from semantic networks: utterance path traversal and incremental 2The tree-like semantics imposes some restrictions which the language may not support.</Paragraph>
      <Paragraph position="3"> consumption. An utterance path is the sequence of nodes and arcs that are traversed in the process of mapping a graph to a sentence. Generation is performed by finding a cyclic path in the graph which visits each node at least once.</Paragraph>
      <Paragraph position="4"> If a node is visited more than once, grammar rules determine when and how much of its content will be uttered \[23\]. Under the second approach, that of incremental consumption, generation is done by gradually relating (consuming) pieces of the input semantics to linguistic structure \[3, 13\]. Such covering of the semantic structure avoids some of the limitations of the utterance path approach and is also the general mechanism we have adopted (we do not rely on the directionality of the conceptual relations per se--the primitive operation that we use when consuming pieces of the input semantics is maximal join which is akin to pattern matching).</Paragraph>
      <Paragraph position="5"> The borderline between the two paradigms is not clear-cut. Some researchers \[22\] are looking at finding an appropriate sequence of expansions of concepts and reductions of subparts of the semantic network until all concepts have realisations in the language. Others assume all concepts are expressible and try to substitute syntactic relations for conceptual relations \[2\].</Paragraph>
      <Paragraph position="6"> Other work addressing surface realisation from semantic networks includes: generation using Meaning-Text Theory \[6\], generation using the SNePS representation formalism \[19\], generation from conceptual dependency graphs \[26\]. Among those that have looked at generation with conceptual graphs are: generation using Lexical Conceptual Grammar \[15\], and generating from CGs using categorial grammar in the domain of technical documentation \[25\].</Paragraph>
      <Paragraph position="7"> This work improves on existing generation approaches in the following respects: (i) Unlike the majority of generators this one takes a non-hierarchical (logically well defined) semantic representation as its input. This allows us to look at a more general version of the realisation problem which in turn has direct ramifications for the increased paraphrasing power and usability of the generator; (ii) Following Nogier &amp; Zock \[14\], we take the view that lexical choice is essentially (pattern) matching, but unlike them we assume that the meaning representation may not be entirely consumed at the end of the generation process. Our generator uses a notion of approximate matching and can happen to con- null vey more (or less) information than is originally specified in its semantic input. We have a principled way to constrain this. We build the corresponding semantics of the generated sentence and aim for it to be as close as possible to the input semantics. (i) and (ii) thus allow for the input to come from a module that need not have linguistic knowledge. (iii) We show how the semantics is systematically related to syntactic structures in a declarative framework.</Paragraph>
      <Paragraph position="8"> Alternative processing strategies using the same knowledge sources can therefore be envisaged.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>