In dialogue a set of actions are realized by linguistic means, and have consequences on the state of the interaction between two speakers. Analysing the interaction, the emphasis can be put on the effects on the mental states of the participants or on the social effects of dialogue acts (obligations, commitments) resulting from conventions. We try here to relate a formal semantics approach to d...

This paper investigates the usefulness of prosodic features in classifying rhetorical relations between utterances in meeting recordings. Five rhetorical relations of contrast, elaboration, summary, question and cause are explored. Three training methods supervised, unsupervised, and combined are compared, and classification is carried out using support vector machines. The results of this pilo...

Most storytelling model approaches consider stories formed by sequences of a particular type of event. These sequences are mostly constructed using the inherent temporal characteristic of each linked event and this limitation makes it difficult to adapt the models to other kinds of events. In order to develop a more generic model to create storytelling applications, we need to organize events u...

Storytelling models are usually constrained to the applications they are implemented in because of the particular characteristics of the data used to define story events and the way those events are linked. In order to develop a more generic model to create storytelling applications, we need to focus the solution not on the data itself, but on the manner this data, in the form of events, is org...

We propose a method for automatically identifying rhetorical relations. We use supervised machine learning but exploit cue phrases to automatically extract and label training data. Our models draw on a variety of linguistic cues to distinguish between the relations. We show that these feature-rich models outperform the previously suggested bigram models by more than 20%, at least for small trai...

To understand a discourse the reader needs to recover the relations between the discourse elements as intended by the writer Writers can and very often do help the reader along by providing explicit lexical signals of the intended discourse relations through the use of lexicalised discourse markers In this paper we present a novel approach for generating texts containing multiple embedded rheto...

To understand a discourse, the reader needs to recover the relations between the discourse elements as intended by the writer. Writers can, and very often do, help the reader along by providing explicit lexical signals of the intended discourse relations through the use of lexicalised discourse markers. In this paper we present a novel approach for generating texts containing multiple, embedded...

It is generMly agreed tha t coherent (lis('ourse consists of segments tha,t are related to one another. A number of researchers have a, rgm~d lbr the use of rhetorica,l[(~ri75] or coherence relations [I-Iol)79], and the rhetorical relations specified by R S'I? [MT87] have I)e(,~, used in s t ructur ing text [tlov88, MP90]. In this l)a.l)el" , we exa.mine rh(q.ori(:al relations in the cold.~,xt ...

Web searching is becoming more and more complex due to increased size of information on the web. Users have to face a lot of problems in specifying their needs in the form of query. Query Reformulation techniques are required in order to provide users with the results, according to their expectations. The existing reformulation techniques suffer from the problem of not providing users with expe...

'Relation based' approaches to discourse analysis and text generation suffer from a common problem: there is considerable disagreement between researchers over the set of relations which is proposed. Few researchers use identical sets of relations, and many use relations not found in any other sets. This proliferation of relations has been pointed out before (eg Hovy [1]), and several methods f...