Choosing a Set of Coherence Relations for Text Generation: A Data-Driven Approach

Abstract. An active research programme in Natural Language Generation has grown up around the notion of `coherence relations'. Relations are being used in a variety of roles in generation systems, in planning the structure of messages and in guiding their linguistic realisation. However, a confusing diversity exists between systems with respect to the particular relations they use. This paper outlines a systematic methodology for justifying a set of relations, on the basis of the cue phrases that can be used to signal them explicitly in text. A large taxonomy of cue phrases has been gathered, from which a conception of relations as feature-based constructs is motivated. By considering small extracts from the taxonomy, individual features of relations can then be investigated in isolation. The paper concludes by noting some advantages of a feature-theoretic treatment of relations for NLG, as well as some problems with a reliance on cue phrases in a theory of text coherence.

• Type: Conference
• Year: 1993
• Where: EWNLG
• Authors: Alistair Knott, Robert Dale
• Keywords: Coherence Relations, Cue Phrases, EWNLG 1993, Natural Language Processing, Particular Relations