This paper presents an algorithm for identifying the noun phrase antecedents of third person pronouns and lexical anaphors (reflexives and reciprocals). The algorithm applies to the syntactic representations generated by McCord's Slot Grammar parser, and relies on salience measures derived from syntactic structure and a simple dynamic model of attentional state. Like the parser, the algorithm is implemented in Prolog. The authors have tested it extensively on computer manual texts, and conducted a blind test on manual text containing 360 pronoun occurrences. The algorithm successfully identifies the antecedent of the pronoun for 86 % of these pronoun occurrences. The relative contributions of the algorithm's components to its overall success rate in this blind test are examined. Experiments were conducted with an enhancement of the algorithm which contributes statistically modelled information concerning semantic and real world relations to the algorithm's decision procedure. Interestingly, this enhancement only marginally improves the algorithm's performance (by 2%). The algorithm is compared with other approaches to anaphora resolution which have been proposed in the literature. In particular, the search procedure of Hobbs ' algorithm was implemented in the Slot Grammar framework and applied to the sentences in the blind test set. The authors ' algorithm achieves a higher rate of success (4%) than Hobbs ' algorithm. The relation of the algorithm to the centering approach is discussed, as well as to models of anaphora resolution which invoke a variety of informational factors in ranking antecedent candidates. 1.

this paper, we present an implemented system for processing definite Universidade do Vale do Rio dos Sinos - UNISINOS, Av. Unisinos 950 - Cx. Postal 275, 93022-000

This paper is concerned with the relationship between the linguistic analysis of sentences and their interpretation in context. Our model is described as implemented in the Core Language Engine (CLE), a domain-independent system for translating natural language sentences into logical form representations. One of the characteristics of this system is that it embodies an extreme form of a staged natural language processing architecture whereby modular processing components have the function of mapping between different levels of sentence representation. Representations at the level of quasi logical form (QLF) are the result of applying declarative rules for morphological, syntactic, and semantic analysis. These QLF representations have subexpressions corresponding to unresolved referring constructions. The QLF level can be regarded as the natural level of sentence representation resulting from compositional semantic analysis independently of the influence of context: Serttertce-LINGUISTIC ANALYSIS --- QLFs-QLF RESOLUTION IN CONTEXT---LF

Centering was formulated as a model of the relationship between attentional state, the form of referring expressions, and the coherence of an utterance within a discourse segment (Grosz, Joshi and Weinstein, 1986; Grosz, Joshi and Weinstein, 1995). In this chapter, I argue that the restriction of centering to operating within a discourse segment should be abandoned in order to integrate centering with a model of global discourse structure. The within-segment restriction causes three problems. The first problem is that centers are often continued over discourse segment boundaries with pronominal referring expressions whose form is identical to those that occur within a discourse segment. The second problem is that recent work has shown that listeners perceive segment boundaries at various levels of granularity. If centering models a universal processing phenomenon, it is implausible that each listener is using a different centering algorithm.The third issue is that even for utterances within a discourse segment, there are strong contrasts between utterances whose adjacent utterance within a segment is hierarchically recent and those whose adjacent utterance within a segment is linearly recent. This chapter argues that these problems can be eliminated by replacing Grosz and Sidner's stack model of attentional state with an alternate model, the cache model. I show how the cache model is easily integrated with the centering algorithm, and provide several types of data from naturally occurring discourses that support the proposed integrated model. Future work should provide additional support for these claims with an examination of a larger corpus of naturally occurring discourses.

We present a language model consisting of a collection of costed bidirectional finite state automata associated with the head words of phrases. The model is suitable for incremental application of lexical associations in a dynamic programming search for optimal dependency tree derivations. We also

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

this paper we present a single model that accounts for referent resolution of deictic and anaphoric expressions in a research prototype of a multimodal user interface called EDWARD. The linguistic expressions are keyed in by a user and are possibly accompanied by pointing gestures. The proposed model for reference resolution elaborates on Alshawi's (1987) notions of context factors and salience and integrates both linguistic and perceptual context effects. The model is contrasted with two alternative referent resolution models, namely, a simplistic one and the more sophisticated model proposed by Grosz and Sidner (1986). Based on empirical and analytical grounds, we conclude that the model we propose is preferable from a computational and engineering point of view

In their interesting 1995 paper, Dale & Reiter present various algorithms they developed alone or in tandem to determine the content of a distinguishing description. That is: a definite description which is an accurate characterization of the object being referred to, but not of any other object in the current `context set'. They argue that their Incremental Algorithm, discussed in more detail below, is the best one from a computational point of view (it has a low complexity and is fast) as well as from a psychological point of view (humans appear to do it in a similar way). Even though Dale & Reiter (1995) primarily aimed at investigating the computational implications of obeying the Gricean maxims, 89 the Incremental Algorithm has become more or less accepted as the state of the art for generating descriptions. However, due to their original motivation, various other aspects of the generation of definites remaine

Abstract not found

This dissertation examines the role of salience in natural language generation (NLG). The salience of an entity, in intuitive terms, refers to its prominence, and is interpreted as a measure of how well an entity stands out from other entities and biases the preference of the generator in selecting words and complex constructs. Through an analysis of previous work in diverse disciplines, we show the variety of salience effects in NLG. Next, we classify several important determinants of salience, corresponding to different factors contributing to salience. We then delineate two theoretically-significant categories: canonical salience and instantial salience. The former is characterized as a built-in preference in the general conceptual- and linguistic knowledge of the speaker. The latter refers to the salience of specific objects in the context of NLG, and may accrue through such determinants as vividness and recency of mention. Psycholinguistic results of Osgood and Bock are highligh...