Previous experimental studies on concessive connectives have only looked at their local facilitating or predictive effect on discourse relation comprehension and have often viewed them as a class of discourse markers with similar effects. We look into the effect of two connectives, but and although, for inferring contrastive vs. concessive discourse relations to complement previous experimental...

A well modeled discourse is the fundamental work of building a dialogue system within a problem domain. The detail of the modeling process could be different from domain to domain. Many researchers have identified different dimensions to model the discourse structures in their own domains. Nevertheless, like most of the software engineering issues, even though the detail process could be domain...

The paper presents machine translation experiments from English to Czech with a large amount of manually annotated discourse connectives. The gold-standard discourse relation annotation leads to better translation performance in ranges of 4–60% for some ambiguous English connectives and helps to find correct syntactical constructs in Czech for less ambiguous connectives. Automatic scoring confi...

This paper looks at the role of situated discourse-as-practice in denaturalising and delegitimising capitalist/integrationist models of development espoused by many national and transnational groups. It focuses on intercultural discourse between the Makushi Amerindians of Guyana and professional development workers and draws on the descriptive methods of Systemic Functional Linguistics, Bernste...

We present an implemented system for processing definite descriptions. The system is based on the results of a corpus analysis previously reported, which showed how common discourse-new descriptions are in newspaper corpora, and identified several problems to be dealt with when developing computational methods for interpreting bridging descriptions. The annotated corpus produced in this earlier...

Introduction From controversial beginnings, the term Web 2.0 has become associated with a fairly well-defined set of popular Web-based platforms characterized by social interaction and user-generated content. Most of the content on such sites is human discourse, via text, audio, video, and/or static images. It is therefore, in principle, of theoretical and practical interest to scholars of comp...

We describe our efforts to apply the Penn Discourse Treebank guidelines on a Tamil corpus to create an annotated corpus of discourse relations in Tamil. After conducting a preliminary exploratory study on Tamil discourse connectives, we show our observations and results of a pilot experiment that we conducted by annotating a small portion of our corpus. Our ultimate goal is to develop a Tamil D...

There are two conceivable readings for (1). Either (a) it refers to the party or (b) Peter only disliked the food. Discourse grammars like Segmented Discourse Representation Theory (SDRT) offer an explanation for this phenomenon. SDRT an extension ofDRT (Kamp and Reyle, 1993) describes a complex propositional structure of Discourse Representation Structures (DRSs) connected via discourse relati...

Introduction The depiction of features in discourse production promotes accurate diagnosis and helps to establish the therapeutic intervention in cognitive impairment and dementia. We aimed to identify alterations in the macrolinguistic aspects of discourse using a new computational tool. Methods Sixty individuals, aged 60 years and older, were distributed in three different groups: mild Alzh...