This paper concerns relationships among focus of attention, choice of referring expression, and perceived coherence of utterances within a discourse segment. It presents a framework and initial theory of centering intended to model the local component of attentional state. The paper examines interactions between local coherence and choice of referring expressions; it argues that differences in coherence correspond in part to the inference demands made by different types of referring expressions, given a particular attentional state. It demonstrates that the attentional state properties modeled by centering can account for these differences

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 order to take steps towards establishing a methodology for evaluating Natural Language systems, we conducted a case study. We attempt to evaluate two different approaches to anaphoric processing in discourse by comparing the accuracy and coverage of two published algorithms for finding the co-specifiers of pronouns in naturally occurring texts and dialogues. We present the quantitative results of handsimulating these algorithms, but this analysis naturally gives rise to both a qualitative evaluation and recommendations for performing such evaluations in general. We illustrate the general difficulties encountered with quantitative evaluation. These are prob- lems with: (a) allowing for underlying assumptions, (b) determining how to handle underspecifications, and (c) evaluating the contribution of false positives and error chaining.

Centering Theory is the best known framework for theorizing about local coherence and salience; however, its claims are articulated in terms of notions which are only partially specified, such as ‘utterance’, ‘realization’, or ‘ranking’. A great deal of research has attempted to arrive at more detailed specifications of these PARAMETERS of the theory; as a result, the claims of Centering can be INSTANTIATED in many different ways. We investigated in a systematic fashion the effect of these different ways of setting the parameters on the theory’s claims. Doing this required, first of all, to clarify what the theory’s claims are (one of our conclusions being that what has become known as ’Constraint 1 ’ is actually a central claim of the theory). Secondly, we had to clearly identify these parametric aspects: e.g., we argue that the notion of ‘pronoun ’ used in Rule 1 should be considered a parameter. Thirdly, we had to find appropriate methods for evaluating these claims. We found that while the theory’s main claim about salience and pronominalization, Rule 1–a preference for pronominalizing the CB–is verified with most instantiations, Constraint 1–a claim about (entity) coherence and CB uniqueness–is much more instantiation-dependent: it is not verified if the parameters are instantiated according to very mainstream views (‘Vanilla instantiation’), it only holds if indirect realization is allowed, and is violated by between 20

A number of recent studies have demonstrated that groups benefit considerably from access to shared visual information. This is due, in part, to the communicative efficiencies provided by the shared visual context. However, a large gap exists between our current theoretical understanding and our existing models. We address this gap by developing a computational model that integrates linguistic cues with visual cues in a way that effectively models reference during tightly-coupled, task-oriented interactions. The results demonstrate that an integrated model significantly outperforms existing language-only and visual-only models. The findings can be used to inform and augment the development of conversational agents, applications that dynamically track discourse and collaborative interactions, and dialogue managers for natural language interfaces. Author Keywords Shared visual information, multimodal interaction, language

and by an IBM Ph.D. Fellowship. Any opinions, findings, conclusions, or recommendations expressed in this material

Ellen Prince, and Lyn Walker for their valuable comments which helpedusimprove both the content and the presentation of our paper. We are also grateful to Carolyn Elken in helping us keep track of the various