Richly interlinked, machine-understandable data constitute the basis for the Semantic Web. We provide a framework, S-CREAM, that allows for creation of metadata and is trainable for a specific domain. Annotating web

This paper considers the problem of automatic assessment of local coherence. We present a novel entity-based representation of discourse which is inspired by Centering Theory and can be computed automatically from raw text. We view coherence assessment as a ranking learning problem and show that the proposed discourse representation supports the effective learning of a ranking function. Our experiments demonstrate that the induced model achieves significantly higher accuracy than a state-of-the-art coherence model. 1

In this paperwe compare pronoun resolution algorithmsand introduce a centering algorithm(Left-Right Centering) that adheres to the constraints and rules of centering theory and is an alternative to Brennan, Friedman, and Pollard’s (1987) algorithm. We then use the Left-Right Centering algorithm to see if two psycholinguistic claims on Cf-list ranking will actually improve pronoun resolution accuracy. Our results from this investigation lead to the development of a new syntaxbased ranking of the Cf-list and corpus-based evidence that contradicts the psycholinguistic claims. 1.

Introduction The application of methods from the eld of natural language processing to biological data has long been restricted to the parsing of molecular structures such as DNA ### . More recently, however, efforts have also been directed to capturing content from biological documents (research reports, journal articles, etc.), either dealing with restricted information extraction problems such as name recognition for proteins or gene products ##### ,ormore sophisticated ones which aim at the acquisition of knowledge relating to protein or enzyme interactions, molecular binding behavior, etc. ####### . Current information extraction (IE) systems, however, suffer from various weaknesses. First, their range of understanding is bounded by rather limited domain knowledge. The templates these systems are supplied with allow only factual information about particular, a priori chosen entities (cell type, virus type, protein group, etc.) to be assembled from the analyzed documents.

We present a novel method for resolving non-pronominal anaphora. Instead of using handcrafted lexical resources, we search the Web with shallow patterns which can be predetermined for the type of anaphoric phenomenon. In experiments for other-anaphora and bridging, our shallow, almost knowledge-free and unsupervised method achieves state-of-the-art results.

Abstract. In this paper the Centering model of anaphora resolution and discourse coherence (Grosz, Joshi and Weinstein, 1983, 1995) is reformulated in terms of Optimality Theory (ot) (Prince and Smolensky 1993). One version of the reformulated model is proven to be descriptively equivalent to an earlier algorithmic statement of Centering due to Brennan, Friedman and Pollard (1987). However, the new model is stated declaratively, and makes clearer the status of the various constraints used in the theory. In the second part of the paper, the model is extended, demonstrating the advantages of the ot reformulation, and capturing formally ideas originally described by Grosz, Joshi and Weinstein. Three new applications of the extended ot Centering model are described: generation of linguistic forms from meanings, the evaluation and optimization of extended texts, and the interpretation of accented pronouns.

The definitions of the basic concepts, rules, and constraints of centering theory involve underspecified notions such as ‘previous utterance’, ‘realization’, and ‘ranking’. We attempted to find the best way of defining each such notion among those that can be annotated reliably, and using a corpus of texts in two domains of practical interest. Our main result is that trying to reduce the number of utterances without a backwardlooking center (CB) results in an increased number of cases in which some discourse entity, but not the CB, gets pronominalized, and viceversa. 1

Pronominalization has been related to the idea of a local focus - a set of discourse entities in the speakcr's centre of attention, for example in Gundel et al. (1993)'s givenness hierarchy or in centering theory. Both accounts say that the determination of the tbcus depends on syntactic as well as pragmatic factors, but have not been able to pin those factors down. In this paper, we uncover the major factors which determine the focus set in descriptive texts. This new ibcus definition has been ewduated with re- spect to two corpora: lnUSeUlll exhibit labels, and newsimper articles. It provides an operationalizable basis for pronorm production, and has been implemented as the reusable module gnome-np. The algorithm behind gnome-np is compared with the most recent pronoun gener- ation algorithm of McCoy and Strube (1999).

Centering theory (CT) has been mostly discussed from the point of view of interpretation rather than generation, and research has tended to concentrate on problems of anaphora resolution. This paper examines how centering could fit into the generation task, separating out components of the theory which are concerned with planning and lexical choice. We argue that it is a mistake to define a total ordering on the transitions CONTINUE, RETAIN, SHIFT and that they are in fact epiphenomenal; a partial ordering emerges from the interaction between cohesion (maintaining the same center) and salience (realising the center as Subject). CT has generally been neglected by NLG practitioners, possibly because it appears to assume that the center is determined according to feedback from the surface grammar to text planning, but we argue that this is an artefactual problem which can be eliminated on an appropriate interpretation of the CT rules. 1 What is Centering? Centering theory (CT)...

We use a reliably annotated corpus to compare metrics of coherence based on Centering Theory with respect to their potential usefulness for text structuring in natural language generation. Previous corpus-based evaluations of the coherence of text according to Centering did not compare the coherence of the chosen text structure with that of the possible alternatives. A corpusbased methodology is presented which distinguishes between Centering-based metrics taking these alternatives into account, and represents therefore a more appropriate way to evaluate Centering from a text structuring perspective.