In this paper we report on several issues arising out of a first attempt to annotate task-oriented spoken dialog for rhetorical structure using Rhetorical Structure Theory. We discuss an annotation scheme we are developing to resolve the difficulties we have encountered.

We derive the rhetorical structures of texts by means of two new, surface-form-based algorithms: one that identifies discourse usages of cue phrases and breaks sentences into clauses, and one that produces valid rhetorical structure trees for unrestricted natural language texts. The algorithms use information that was derived from a corpus analysis of cue phrases.

Rhetorical moves are a useful framework for analyzing the hidden rhetorical organization in research papers, in teaching academic writing. We propose a ∗ 國立清華大學資工系 NTHU NLPLAB Email: {cheng, hsiang, joe}@nlplab.cc; [email protected]; [email protected]

Negative Polarity Items (NPIs) are known to be licensed in wh-questions. But not all wh-questions behave alike with respect to NPI licensing. As pointed out in Han and Siegel (1996), while all argument wh-questions with NPIs can have a RHETORICAL QUESTION reading, only a subset of them can have a true wh-question reading. In this paper, we point out that adjunct wh-questions with NPIs cannot ha...

Attentional State Theory and Rhetorical Structure Theory are two predominant theories of discourse parsing. Combining these two approaches, in this paper, we describe a novel approach for discourse parsing. The resulting discourse tree structure retains following properties: structure of purpose from Attentional State Theory and relations between sentences from Rhetorical Structure Theory. We d...

The study of argumentation has undergone periods of decadence alternate with periods of renaissance. Currently, we are witnessing one of the latter, as proved by research flowering in many issues and aspects, both in Philosophy and in Artificial Intelligence. The work presented in this thesis is concerned in particular with “rhetorical argumentation”, which on the other hand has enjoyed conside...

Then he went about his regular, non-Twitter affairs. The next afternoon, fresh from a nap, he checked his account, stared at the outcome, and tweeted to @upulieto, an associate, “I just woke up. What a mess” [49]. His tweet had spiraled virally: tens of thousands of likes, retweets, endless streams of commentary. Why? Well, lots of factors, of course. There is rarely a single factor to which on...

In many applications in computational linguistics, such as machine translation, we want to understand why a writer has used language in a particular way, what specific effects she intended to convey, and which linguistic choices were made to achieve those goals. This idea, that a writer has specific communicative goals or intentions in mind when she composes text, goes back to the study of clas...