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.

The central claim of this dissertation is that an elliptical VP is a proform. This claim has two primary consequences: first, the elliptical VP can have no internal syntactic structure. Second, the interpretation of VP ellipsis must be governed by the same general conditions governing other proforms, such as pronouns. The basic condition governing the interpretation of a proform is that it must be semantically identified with its antecedent. A computational model is described in which this identification is mediated by store and retrieve operations defined with respect to a discourse model. Because VP ellipsis is treated on a par with other proforms, the ambiguity arising from “sloppy identity ” becomes epiphenomenal, resulting from the fact that the store and retrieve operations are freely ordered. A primary argument for the proform theory of VP ellipsis concerns syntactic constraints on variables within the antecedent. I examine many different types of variables, including reflexives, reciprocals, negative polarity items, and wh-traces. In all these cases, syntactic constraints are not respected under ellipsis. This indicates that the relation governing VP ellipsis is semantic rather than syntactic. In further support of the proform theory, I show that there is a striking similarity in the antecedence possibilities for VP ellipsis and those for pronouns. Two

In this thesis, we present analyses and algorithms for resolving a variety of cohesive phenomena in natural language, including VP-ellipsis, gapping, event reference, tense, and pronominal reference. Past work has attempted to explain the complicated behavior of these expressions with theories that operate within a single module of language processing. We argue that such approaches cannot be maintained; in particular, the data we present strongly suggest that the nature of the coherence relation operative between clauses needs to be taken into account. We provide a theory of coherence relations and the discourse inference processes that underly their recognition. We utilize this theory to break the deadlock between syntactic and semantic approaches to resolving VP-ellipsis. We show that the data exhibits a pattern with respect to our categorization of coherence relations, and present an account which predicts this pattern. We extend our analysis to gapping and event reference, and sho...

We provide a general account of parallelism in discourse, and apply it to the special case of resolving possible readings for instances of VP ellipsis. We show how seyeral problematic examples are accounted for in a natural and straightforward fashion. The generality of the approach makes it directly applicable to a variety of other types of ellipsis and reference.

We provide a unified account of sentence-level and text-level anaphora within the framework of a dependency-based grammar model. Criteria for anaphora resolution within sentence boundaries rephrase major concepts from GB's binding theory, while those for text-level anaphora incorporate an adapted version of a Grosz-Sidner-style focus model. I

This paper reports on an empirically based system that automatically resolves VP ellipsis in the 644 examples identified in the parsed Penn Treebank. The results reported here represent the first systematic corpus-based study of VP ellipsis resolution, and the performance of the system is comparable to the best existing systems for pronoun resolution. The methodology and utilities described can be applied to other discourse-processing problems, such as other forms of ellipsis and anaphora resolution. The system determines potential antecedents for ellipsis by applying syntactic constraints, and these antecedents are ranked by combining structural and discourse preference factors such as recency, clausal relations, and parallelism. The system is evaluated by comparing its output to the choices of human coders. The system achieves a success rate of 94.8%, where success is defined as sharing of a head between the system choice and the coder choice, while a baseline recency-based scheme achieves a success rate o,I:75.0 % by this measure. Other criteria for success are also examined. When success is defined as an exact, word-for-word match with the coder choice, the system performs with 76.0 % accuracy, and the baseline approach achieves only 14.6% accuracy. Analysis of the individual components of the system shows that each of the structural and discourse constraints used are strong predictors of the antecedent of VP ellipsis. 1.

We present an algorithm which assigns interpretations to several major types of ellipsis structures through a generalized procedure of syntactic reconstruction. Ellipsis structures are taken to be sequences of lexically realized arguments and/or adjuncts of an empty verbal head. Reconstruction is characterized as the specification of a (partial) correspondence relation between the unrealized head verb of an elided clause and its argument and adjuncts on one hand, and the head of a non-elided antecedent sentence and its arguments and adjuncts on the other. The algorithm generates appropriate interpretations for cases of VP ellipsis, pseudo-gapping, bare ellipsis (stripping), and gapping. It provides a uniform computational approach to a wide range of ellipsis phenomena, and it has significant advantages over several other approaches to ellipsis which have recently been suggested in the computational and linguistic literature. 1 Introduction Ellipsis structures pose an important proble...

We describe the authoring tool, EasyEnglish, which is part of IBM's internal SGML editing environment, Information Development Workbench. EasyEnglish helps writers produce clearer and simpler English by pointing out ambiguity and complexity as well as performing some standard grammar checking. Where appropriate, EasyEnglish makes suggestions for rephrasings that may be substituted directly into the text by using the editor interface. EasyEnglish is based

Most traditional approaches to anaphora resolution rely heavily on linguistic and domain knowledge. One of the disadvantages of developing a knowledge-based system, however, is that it is a very labour- and time-consuming task. This paper presents a robust, knowledgepoor approach to resolving pronouns in technical manuals in both English and Polish. This approach is a modification of the practical approach reported in [Mitkov 97] and operates on texts pre-processed by a part-of-speech tagger. Input is checked against agreement and tested for a number of antecedent indicators. Candidates are assigned scores by each indicator and the candidate with the highest score is returned as the antecedent. Preliminary evaluation reports precision of over 90%. 1. Introduction For the most part, anaphora resolution has focussed on traditional linguistic methods ([Barros & Deroeck 94], [Carbonell & Brown 88], [Carter 86], [Dahl & Ball 90], [Hayes 81], [Hobbs 78], [Ingria & Stallard 89], [La...

mbedded. Central Design Goals. The design of our parsing system was governed by two main goals: On the one hand syntactic and semantic representations should be constructed in parallel , on the other hand input text should be analyzed incrementally , which is also extended to anaphora resolution. We chose a co-descriptive approach using a different formalism for each level. Incrementality. A problem of any compositional semantics construction is that the order of construction steps may be disadvantageous for anaphora resolution, because, e.g., the construction for a supposed intrasentential antecedent would have been completed before the anaphoric NP is considered (c.f. [Johnson 1986]). Due to the incrementality of the parsing process it is guaranteed that information progresses from left to right. -DRT. For the semantic formalism a combination of -calculus and DRT as de