This paper introduces an approach to generate video clips starting from an annotated commentary. The novelty of the approach lies in the use of rhetorical structure of the accompanying audio commentary in planning the video. The basic notions of cinematography are briefly introduced together with the Rhetorical Relation Theory to model the structure of a discourse. Then, the architecture of a v...

The AlethGen tool has been used to build a system for automatically generating replies to complaints, for a European mail-order company. In the current version, letters are generated in French. AlethGen consists of several modules: the text deep structure planner (or conceptual planner), the text surface structure planner (or rhetorical planner), the computation of pronouns and quantifiers, and...

Previous work on discourse parsing has mostly relied on surface syntactic and lexical features; the use of semantics is limited to shallow semantics. The goal of this thesis is to exploit event semantics in order to build discourse parse trees (DPT) based on informational rhetorical relations. Our work employs an Inductive Logic Programming (ILP) based rhetorical relation classifier, a Neural N...

RASTA (Rhetorical Structure Theory Analyzer), a discourse analysis component within the Microsoft English Grammar, efficiently computes representations of the structure of written discourse using information available in syntactic and logical form analyses. RASTA heuristically scores the rhetorical relations that it hypothesizes, using those scores to guide it in producing more plausible discou...

Psych-verbs are a relatively well-studied phenomenon in theoretical linguistics (Belleti and Rizzi (1988), Grimshaw (1990), etc.), but one for which as yet no truly satisfactory analysis has been developed. This paper seeks to provide a new perspective on the semantics of psych-verbs by bringing ideas based on Asher and Pustejovsky (2000) into the discussion, namely, that the concept of rhetori...

In [1], we study how causal relations may be used to improve narrative generation from real-life temporal data. We describe a method for extracting potential causal relations from temporal data and for structuring a generated report. The method is applied to the generation of reports highlighting unusual combinations of events in the Activity of Daily Living (ADL) domain. Our experiment applies...

Studying dialogue relations as a complex structured output prediction problem, independently of the dialogue outcome, has been the focus of significant research efforts, such as discourse relations [9], rhetorical structure [8, 1] and dialogue act modeling [13]. While these works capture linguisticallymotivated fine-grained dialogue relations, they require considerable effort and linguistic kno...

This article describes the generation of aggregated and elliptic sentences, using Dependency Trees connected by rhetorical relations as input. The system we have developed can generate both hypotactic and paratactic constructions with appropriate cue words, and various forms of ellipsis such as Gapping and Conjunction Reduction. We contend that Dependency Trees connected by rhetorical relations...

We present the results of several machine learning tasks that exploit explicit spatial language to classify rhetorical relations and the spatial information of narrative events. Three corpora are annotated with figure and ground (granularity) relationships, mereotopologically classified verbs and prepositions, and frames of reference. For rhetorical relations, Naı̈ve Bayesian models achieve 84.9...