This paper describes a new discourse module within our multilingual NLP system. Because of its unique data-driven architecture, the discourse module is language-independent. Moreover, the use of hierarchically organized multiple knowledge sources makes the module robust and trainable using discourse-tagged corpora. Separating discourse phenomena from knowledge sources makes the discourse module...

The overall sentiment of a text is critically affected by its discourse structure. By splitting a text into text spans with different discourse relations, we automatically train the weights of different relations in accordance with their importance, and then make use of discourse structure knowledge to improve sentiment classification. In this paper, we utilize explicit connectives to predict d...

This paper investigates the complexity of dependencies at the discourse level, in particular the dependencies between discourse connectives and their arguments. Our study is based on data from the Penn Discourse Treebank (PDTB) and is therefore an exploration into the ways treebanks can inform linguistic issues. We observe that, unlike in syntax, there is more uncertainty and flexibility with r...

Children can learn new words from non-instructive contexts (e.g., overheard speech). Recently, it has been proposed that one way that children do this is by using the surrounding discourse to constrain the interpretation of new words (Sullivan & Barner, 2015). However, little is known about what sort of discourse inferences children might compute when learning. In the present study, we adopt a ...

AIM The aim of the paper is (1) to offer an overview of different theoretical approaches to discourse analysis and (2) to review papers published in the Journal of Advanced Nursing from 1996-2004 in which discourse analysis is identified as a method of data analysis. BACKGROUND Discourse analysis offers rigorous approaches to analysing naturally occurring talk and texts. Forms of discourse an...

While it seems intuitively obvious tha t many discourse markers (DMs) are able to express discourse relat ions (DRs) which ex i s t independently, the specific contr ibut ion of DMs if any is not clear. In this paper , we investigate the s tatus of some consequence DMs in French. We observe tha t it is difficult to cons t ruc t a clear and simple definition based on DRs for these DMs. Next , we...

Discourse parsing is a challenging task in NLP and plays a crucial role in discourse analysis. To enable discourse analysis for Hindi, Hindi Discourse Relations Bank was created on a subset of Hindi TreeBank. The benefits of a discourse analyzer in automated discourse analysis, question summarization and question answering domains has motivated us to begin work on a discourse analyzer for Hindi...