Text processing requires inferences for establishing coherence between successive sentences. In neuropsychological studies and brain imaging studies, these coherence-building processes have been ascribed to the right hemisphere. On the other hand, there is evidence for prefrontal brain damage causing non-aphasic language disorders, in which text level processes are impaired. In this study, we u...

Not much is known about the linguistic resources other than discourse connectors for signalling coherence relations. We present here non discourse connector resources for marking coherence relations, namely “discourse verbs” and “discourse prepositions”. “Discourse verbs” are verbs such as precede or cause which take as arguments eventualities or facts. They enter into competition with discours...

We define a model of discourse coherence based on Barzilay and Lapata’s entity grids as a stylometric feature for authorship attribution. Unlike standard lexical and character-level features, it operates at a discourse (cross-sentence) level. We test it against and in combination with standard features on nineteen booklength texts by nine nineteenth-century authors. We find that coherence alone...

In this work we study the challenging task of automatically constructing essays for Chinese college entrance examination where the topic is specified in advance. We explore a sentence extraction framework based on diversified lexical chains to capture coherence and richness. Experimental analysis shows the effectiveness of our approach and reveals the importance of information richness in essay...

We propose and motivate a novel task: paragraph segmentation. We discuss and compare this task with text segmentation and discourse parsing. We present a system that performs the task with high accuracy. A variety of features is proposed and examined in detail. The best models turn out to include lexical, coherence, and structural features.

there are two components: (i) John could not go to the party and (ii) He was busy with his work. These components are connected to each other by a causal relation: John’s inability to go to the party is caused by the fact that he was doing his work. Coherence relations are often signalled by discourse markers (DMs). DMs are lexical expressions (such as although, because, since and thus) which b...

One of the major issues still open in ontology reuse is how to help users to find the appropriate ontologies and terms for a certain application or domain of interest. In order to complement current ontology similarity-based techniques, topic modeling has the potential of allowing comparisons among ontologies not only on the basis of their lexical content, but also considering their latent sema...