<?xml version="1.0" standalone="yes"?>
<Paper uid="W96-0404">
  <Title>Approximate Generation from Non-Hierarchical Representations</Title>
  <Section position="10" start_page="38" end_page="38" type="concl">
    <SectionTitle>
9 Discussion
</SectionTitle>
    <Paragraph position="0"> During generation it is necessary to find appropriate mapping rules. However, at each stage a number of rules might be applicable. Due to possible interactions between some rules the generator may have to explore different choices before actually being able to produce a sentence.</Paragraph>
    <Paragraph position="1"> Thus, generation is in essence a search problem.</Paragraph>
    <Paragraph position="2"> In order to guide the search a number of heuristics can be used. In \[14\] the number of matching nodes has been used to rate different matches, which is similar to finding maximal reductions in \[6\]. Alternatively a notion of semantic distance \[5\] might be employed. In PROTECTOR we will use a much more sophisticated notion of what it is for a conceptual graph to match better the initial semantics than another graph. This captures the intuition that the generator should try to express as much as possible from the input while adding as little as possible extra material.</Paragraph>
    <Paragraph position="3"> We use instructions showing how the semantics of a mother syntactic node is computed because we want to be able to correctly update the semantics of nodes higher than the place where substitution or adjunction has taken placc i.e., we want to be able to propagate the substitution or adjunction semantics up the mixed structure whose backbone is the syntactic tree.</Paragraph>
    <Paragraph position="4"> We also use a notion of headed conceptual graphs, i.e., graphs that have a certain node chosen as the semantic head. The initial semantics need not be marked for its semantic head. This allows the generator to choose an appropriate (for the natural language) perspective. The notion of semantic head and their connectivity is a way to introduce a hierarchical view on the :emantic structure which is dependent on the language. When matching two conceptual graphs we require that their heads be the same. This reduces the search space and speeds up the generation process.</Paragraph>
    <Paragraph position="5"> Our generator is not coherent or complete (i.e., it can produce sentences with more general/specific semanticJ than the input semantics). We try to generate sentences whose semantics is as close as possible to the input in the sense that they introduce little extra material and leave uncovered a small part of the input semantics. We keep track of more structures as the generation proceeds and are in a position to make finer distinctions than was done in previous research. The generator never produces sentences with semantics which is more specific than the lower semantic bound which gives some degree of coherence. Our generation technique provides flexibility to address cases where the entire input cannot be expressed in a single sentence by first generating a &amp;quot;best match&amp;quot; sentence and allowing the remaining semantics to be generated in a follow-up sentence.</Paragraph>
    <Paragraph position="6"> Our approach can be seen as a generalisation of semantic head-driven generation \[20\]-we deal with a non-hierarchical input and non-concatenative grammars. The use of Lexicalised DTG means that the algorithm in effect looks first for a syntactic head. This aspect is similar to syntax-driven generation \[8\].</Paragraph>
    <Paragraph position="7"> The algorithm has to be checked against more linguistic data and we intend to do more work on additional control mechanisms and also using alternative generation strategies using knowledge sources free from control information. To this end we have explored aspects of a new semanticindexed chart generation which also allows us to rate intermediate results using syntactic as well as semantic preferences. Syntactic/stylistic preferences are helpful in cases where the semantics of two paraphrases are the same. One such instance of use of syntactic preferences is avoiding (giving lower rating to) heavy constituents in split verb particle constructions. Thus, the generator finds all possible solutions producing the &amp;quot;best&amp;quot; first.</Paragraph>
  </Section>
class="xml-element"></Paper>