Approximate Generation from Non-Hierarchical Representations

This paper presents a technique for sentence generation. We argue that the input to generators should have a non-hierarchical nature. This allows us to investigate a more general version of the sentence generation problem where one is not pre-committed to a choice of the syntactically prominent elements in the initial semantics. We also consider that a generator can happen to convey more (or less) information than is originally specified in its semantic input. In order to constrain this approximate matching of the input we impose additional restrictions on the semantics of the generated sentence. Our technique provides flexibility to address cases where the entire input cannot be precisely expressed in a single sentence. Thus the generator does not rely on the strategic component having linguistic knowledge. We show clearly how the semantic structure is declaratively related to linguistically motivated syntactic representation. 1 I n t r o d u c t i o n Natural language generation is the process of realising communicative intentions as text (or speech). The generation task is standardly broken down into the following processes: content determination (what is the meaning to be conveyed), sentence planning 1 (chunking the meaning into sentence sized units, choosing words), surface realisation (determining the syntactic structure), morphology (inflection of words), synthesising speech or formatting the text output. In this paper we address aspects of sentence planning (how content words are chosen but not how the sem.untics is chunked in units realisable "Supported by Faculty of Science and Engineering Scholarship 343 EE06006 at the University of Edinburgh. 1Note that this does not involve planning mechanisms! as sentences) and surface realisation (how syntactic structures are computed). We thus discuss what in the literature is sometimes referred to as tactical generation, that is "how to say i t"--as opposed to strategic generation--"what to say". We look at ways of realising a nonhierarchical semantic representation as a sentence, and explore the interactions between syntax and semantics. Before giving a more detailed description of our proposals first we motivate the nonhierarchical nature of the input for sentence generators and review some approaches to generation from non-hierarchical representations-semantic networks (Section 2). We proceed with some background about the grammatical framework we will employ--D-Tree Grammars (Section 3) and after describing the knowledge sources available to the generator (Section 4) we present the generation algorithm (Section 5). This is followed by a step by step illustration of the generation of one sentence (Section 6). We then discuss further semantic aspects of the generation (Section 7) and the implementation (Section 8). We conclude with a discussion of some issues related to the proposed technique (Section 9). 2 G e n e r a t i o n f rom NonHie ra rch ica l R e p r e s e n t a t i o n s 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