Some languages do not have enough labeled data to obtain good discourse parsing, specially in the relation identification step, and the additional use of unlabeled data is a plausible solution. A workflow is presented that uses a semi-supervised learning approach. Instead of only a predefined additional set of unlabeled data, texts obtained from the web are continuously added. This obtains near...

A study of a small corpus of pharmaceutical leaflets supports the hypothesis that a subset of Mann and Thompson’s Rhetorical Relations may hold within as well as between clauses, with one or more propositional arguments nominalised. This paper summarises the main results of this study and outlines a formal account of the phenomenon within a framework of discourse generation, whereby nominalisat...

We present our recent work on query-focused summarization, focusing on our efforts in building and applying models of rhetorical-semantic relations (RSRs) such as contrast and causality. We overview ongoing work in extracting and evaluating RSR models. We describe our system for query-focused summarization, focusing on an enhanced, feature-based framework. We present results of experiments to m...

We present the results of several machine learning tasks designed to predict rhetorical relations that hold between clauses in discourse. We demonstrate that organizing rhetorical relations into different granularity categories (based on relative degree of detail) increases average prediction accuracy from 58% to 70%. Accuracy further increases to 80% with the inclusion of clause types. These r...

This paper describes how discursive knowledge, given by the discursive theories RST (Rhetorical Structure Theory) and CST (Crossdocument Structure Theory), may improve the automatic evaluation of local coherence in multi-document summaries. Two of the main coherence models from literature were incremented with discursive information and obtained 91.3% of accuracy, with a gain of 53% in relation...

We propose designing a discourse parser specifically for the evaluative text genre. We aim to see whether focusing on a certain genre and relations specific to that genre offers performance gain beyond more generic discourse parsers. In this extended abstract we describe the approach we intend to take, and how this differs from what has been done previously. The problem of discourse parsing It ...

Annotating biomedical text with discourse-level information is a well-studied topic. Several research efforts have annotated textual zones (e.g., sentences or clauses) with information about rhetorical status, whilst other efforts have linked and classified sets of text spans according to the type of discourse relation holding between them. A relatively new approach has involved annotating meta...

Given the prevalence of the use of rhetorical relations in the generation of text (Itovy, 1989; Moore and Paris, 1988; Scott and Souza, 1990), it is surprising how little work has actually been done on the grammatical realization of these relations. Most systems, based on Mann and Thompson's formulation of Rhetorical Structure Theory (Mann and Thompson, 1988), have adopted simplified solutions ...

The paper deals with the cohesion part of a model of global discourse interpretation, usually known as Veins Theory (VT). By taking from the Rhetorical Structure Theory the notions of nuclearity and relations, but ignoring the relations’ names, VT computes from rhetorical structures strings of discourse units, called veins, from which domains of accessibility can be determined for each discours...