Data Set Used
In this paper, we propose a generalization of Centering Theory (CT) (Grosz, Joshi, Weinstein (1995)) called Veins Theory (VT), which extends the applicability of centering rules from local to global discourse. A key facet of the theory involves the identification of <<veins>> over discourse structure trees such as those defined in RST, which delimit domains… (More)
This paper investigates the problem of automatically annotating resources with NP coreference information using a parallel corpus, English-Romanian, in order to transfer, through word alignment, coreference chains from the English part to the Romanian part of the corpus. The results show that we can detect Romanian referential expressions and coreference… (More)
Evaluation campaigns have become an established way to evaluate automatic systems which tackle the same task. This paper presents the first edition of the Anaphora Resolution Exercise (ARE) and the lessons learnt from it. This first edition focused only on English pronominal anaphora and NP coreference, and was organised as an exploratory exercise where… (More)
We compare the potential of two classes el' linear and hierarchical models of discourse to determine co-reference links and resolve anaphors. The comparison uses a col pus of thirty texts, which were manually annotated for co-reference and discourse structure.
BalkaNet is an EC funded project (IST-2000-29388) that started in September 2001 and will end in August 2004. It aims at developing  aligned wordnets for the following Balkan languages: Bulgarian, Greek, Roma-nian, Serbian, Turkish and to extend the Czech wordnet previously developed in the EuroWordNet project. BalkaNet project has insofar delivered… (More)
In this paper, we outline a theory of referential accessibility called Veins Theory (VT). We show how VT addresses the problem of "left satellites", currently a problem for stack-based models, and show that VT can be used to significantly reduce the search space for antecedents. We also show that VT provides a better model for determining domains of… (More)
The paper proposes a model for dynamical building of architectures intended to process natural language. The representation that stays at the base of the model is a hierarchy of XML annotation schemas in which the parent-child links are defined by subsumption relations. We show how the hierarchy may be augmented with processing power by marking the edges… (More)
In this paper we present a possibility for integrating Anaphora Resolution (AR) in a system to automatically evaluate students' free-text answers. An initial discussion introduces some of the several methods that can be tried out. The implementation makes use of the AR-Engine RARE (Cristea et al. 02), integrated into the free-text answers assessor Atenea… (More)
The paper presents a method of building the discourse structure of a discourse by combining indications on local structure given by cue-phrases with indications on global structure given by references found in the text. Then the discourse structure is used to obtain focused summaries.