Laura Alonso Alemany

Integrating cohesion and coherence for automatic summarization

This paper presents the integration of cohesive properties of text with coherence relations, to obtain an adequate representation of text for automatic summarization. A summarizer based on Lexical Chains is enchanced with rhetorical and argumentative structure obtained via Discourse Markers.When evaluated with newspaper corpus, this integration yields only slight improvement in the resulting summaries and cannot beat a dummy baseline consisting of the first sentence in the document. Nevertheless, we argue that this approach relies on basic linguistic mechanisms and is therefore genre-independent.

Clustering adjectives for class acquisition

This paper presents an exploratory data analysis in lexical acquisition for adjective classes using clustering techniques. From a theoretical point of view, this approach provides large-scale empirical evidence for a sound classification. From a computational point of view, it helps develop a reliable automatic subclassification method.Results show that the features used in theoretical work can be successfully modelled in terms of shallow cues. The resulting clusters parallel to a large extent with proposals in the literature, which indicates that automatic acquisition of adjective classes for large-scale lexicons is possible.

A framework for feature-based description of low level discourse

We present the first stage of the discursive annotation of a corpus in Spanish. In contrast with previous annotation projects, we have applied a feature-based description of discourse relations, and we have focussed in the low level organization of discourse. This first annotation phase has served to settle the annotation framework and to provide empirical support to theoretical claims. Systematic guidelines have been established for the interpretation of relations between discourse units, by tests and interpretation procedures that characterize the presence of the features characterizing discourse relations.