Towards a discourse coherent structure

Date
2010
Authors
Nand, P
Yeap, WK
Supervisor
Item type
Conference Contribution
Degree name
Journal Title
Journal ISSN
Volume Title
Publisher
INSTICC publications
Abstract

In this paper we argue that coherence relations between discourse units are ultimately based on mentioned discourse entities embedded in the units participating in the relation. Coherence relations as discussed in most literature ((Mann and Thompson, 1988), (Hobbs, 1985), (Grosz and Sidner, 1986) inter alia) are defined between text segments, where a text segment could range from a single utterance to the whole discourse. We show that these coherence relations are formed either directly or indirectly between embedded discourse entities. Other semantic entities might be derived via inference/s based on the mentioned entities and the complexity of these inferences determines some of the types of relations defined in literature. Hence, the coherence relations as defined by (Mann and Thompson, 1988), (Hobbs, 1985) inter alia, existing between text units is essentially an abstraction of these fundamental relations formed between embedded entities. We argue that any representation of discourse coherence structure should entail representation of information down to the resolution level of these embedded entities in order for such structures to be useful for automated language processing tasks. We also show that the commonly accepted tree structure ((Hobbs, 1985),(Marcu, 1996) inter alia) is not sufficient to represent discourse relations to such a resolution level, and propose a semiconstrained directed graph as the alternative.

Description
Keywords
Discourse processing NLP Coherence Discourse Relations Discourse structure
Source
2nd International Conference on Agents and Artificial Intelligence, Valencia, Spain, 2010-01-22 - 2010-01-24, pages 11 - 19
DOI
Rights statement
The Author retains the rights to publish the contribution in his/her own website or in his/her employer’s website, as long as it is clearly stated in which publication or event it was originally published in and a link to the original publication or event is made.