Rodger Kibble

On coreferring: coreference in MUC and related annotation schemes

In this paper, it is argued that coreference annotations, as performed in the MUC community for example, go well beyond annotation of the relation of coreference proper. As a result, it is not always clear what semantic relation these annotations are encoding. The paper discusses a number of problems with these annotations and concludes that rethinking of the coreference task is needed before the task is expanded. In particular, it suggests a division of labor whereby annotation of the coreference relation proper is separated from other tasks such as annotation of bound anaphora and of the relation between a subject and a predicative NP.

Optimizing Referential Coherence in Text Generation

This article describes an implemented system which uses centering theory for planning of coherent texts and choice of referring expressions. We argue that text and sentence planning need to be driven in part by the goal of maintaining referential continuity and thereby facilitating pronoun resolution: Obtaining a favorable ordering of clauses, and of arguments within clauses, is likely to increase opportunities for nonambiguous pronoun use. Centering theory provides the basis for such an integrated approach. Generating coherent texts according to centering theory is treated as a constraint satisfaction problem. The well-known Rule 2 of centering theory is reformulated in terms of a set of constraintscohesion, salience, cheapness, and continuityand we show sample outputs obtained under a particular weighting of these constraints. This framework facilitates detailed research into evaluation metrics and will therefore provide a productive research tool in addition to the immediate practical benefit of improving the fluency and readability of generated texts. The technique is generally applicable to natural language generation systems, which perform hierarchical text structuring based on a theory of coherence relations with certain additional assumptions.

An integrated framework for text planning and pronominalisation

This paper describes an implemented system which uses centering theory for planning of coherent texts and choice of referring expressions. We argue that text and sentence planning need to be driven in part by the goal of maintaining referential continuity and thereby facilitating pronoun resolution: obtaining a favourable ordering of clauses, and of arguments within clauses, is likely to increase opportunities for non-ambiguous pronoun use. Centering theory provides the basis for such an integrated approach. Generating coherent texts according to centering theory is treated as a constraint satisfaction problem.

A reformulation of Rule 2 of centering theory

The standard preference ordering on the well-known centering transitions Continue, Retain, Shift is argued to be unmotivated: a partial, context-dependent ordering emerges from the interaction between principles dubbed cohesion (maintaining the same center of attention) and salience (realizing the center of attention as the most prominent NP). A new formulation of Rule 2 of centering theory is proposed that incorporates these principles as well as a streamlined version of Strube and Hahns (1999) notion of cheapness. It is argued that this formulation provides a natural way to handle topic switches that appear to violate the canonical preference ordering.

Speech acts, commitment and multi-agent communication

The principle aim of this paper is to reconsider the suitability of Austin and Searle’s Speech Act theory as a basis for agent communication languages. Two distinct computational interpretations of speech acts are considered: the standard “mentalistic” approach associated with the work of Cohen and Levesque which involves attributing beliefs and intentions to artificial agents, and the “social semantics” approach originating (in the context of MAS) with Singh which aims to model commitments that agents undertake as a consequence of communicative actions. Modifications and extensions are proposed to current commitment-based analyses, drawing on recent philosophical studies by Brandom, Habermas and Heath. A case is made for adopting Brandom’s framework of normative pragmatics, modelling dialogue states as deontic scoreboards which keep track of commitments and entitlements that speakers acknowledge and hearers attribute to other interlocutors. The paper concludes by outlining an update semantics and protocol for selected locutions.

Generating Coherence Relations via Internal Argumentation

A key requirement for the automatic generation of argumentative or explanatory text is to present the constituent propositions in an order that readers will find coherent and natural, to increase the likelihood that they will understand and accept the author’s claims. Natural language generation systems have standardly employed a repertoire of coherence relations such as those defined by Mann and Thompson’s Rhetorical Structure Theory. This paper models the generation of persuasive monologue as the outcome of an “inner dialogue”, where the author attempts to anticipate potential challenges or clarification requests. It is argued that certain RST relations such as Motivate, Evidence and Concession can be seen to emerge from various pre-empting strategies.

Book reviews: Natural language semantics

This is a large volume, and it contains multitudes. Semantics is construed in a broad sense as the study of how meaning is communicated through the medium of language in a social context, taking account of inferences the hearer is expected to make on the basis of such factors as linguistic knowledge per se, context and “co-text,” encyclopedic knowledge, conventions of politeness and cooperative behavior, and the relative social status of speaker and hearer. The book ranges over a variety of approaches that have addressed these issues, including philosophy of language, lexicography, formal (logicbased) and cognitive semantics, frame-based knowledge representation, pragmatics, and anthropology. However, the result is more than a catalogue of theoretical tools and frameworks; throughout the book, Allan keeps in view an underlying philosophy that “meaning is cognitively and functionally motivated.” Chapters 1 and 2 introduce fundamental notions such as sense and reference, extension and intension, compositionality, and speech acts. Chapters 3–5 deal with aspects of lexical semantics: Chapter 3 concerns the structure and content of lexical entries, Chapter 4 investigates the extent to which individual morphemes can be assigned semantic interpretations, and Chapter 5 contains an illuminating discussion of aspects of nonliteral word meaning such as connotation, euphemism, dysphemism, and jargon. Chapters 6 and 7 introduce the formal apparatus of propositional and predicate logic and the lambda calculus, and discuss notions of consequence such as semantic entailment and conversational and conventional implicatures. Chapters 8–10 are concerned with “cognitive and functional approaches to semantics,” that is, approaches whose theoretical constructs are claimed to have some form of “psychological reality” or are motivated in terms of their “communicative functions.” These chapters review topics such as frames and scripts, componential analysis, classifiers, color categories across languages, prototypes, and stereotypes. Chapters 11–13 address various issues in clausal and nominal semantics. Chapter 11 concerns modality, tense, and thematic roles, whereas Chapter 12 discusses different approaches to the semantics of verbs and other predicates. Chapter 13 grapples with some of the intricacies of quantification, number, and countability in English noun phrases, using generalized quantifier theory and a variant of ensemble theory. As far as I know, this is the first published tutorial account of the latter, which has previously only been accessible to students in Harry Bunt’s rather challenging monograph (1985). We are told that Chapters 11–13 “demonstrate the application of formal methods of semantic analysis to a corpus of data.” This section is likely to disappoint computational linguists, who will understand the term corpus in a different way, since the data in these chapters consist of a series of singlesentence (and mostly single-clause) examples apparently constructed by the author.

Natural Language Semantics Keith Allan (Monash University) Oxford: Blackwell Publishers, 2001, xix+529 pp; hardbound, ISBN 0-631-19296-4,

This is a large volume, and it contains multitudes. Semantics is construed in a broad sense as the study of how meaning is communicated through the medium of language in a social context, taking account of inferences the hearer is expected to make on the basis of such factors as linguistic knowledge per se, context and “co-text,” encyclopedic knowledge, conventions of politeness and cooperative behavior, and the relative social status of speaker and hearer. The book ranges over a variety of approaches that have addressed these issues, including philosophy of language, lexicography, formal (logicbased) and cognitive semantics, frame-based knowledge representation, pragmatics, and anthropology. However, the result is more than a catalogue of theoretical tools and frameworks; throughout the book, Allan keeps in view an underlying philosophy that “meaning is cognitively and functionally motivated.” Chapters 1 and 2 introduce fundamental notions such as sense and reference, extension and intension, compositionality, and speech acts. Chapters 3–5 deal with aspects of lexical semantics: Chapter 3 concerns the structure and content of lexical entries, Chapter 4 investigates the extent to which individual morphemes can be assigned semantic interpretations, and Chapter 5 contains an illuminating discussion of aspects of nonliteral word meaning such as connotation, euphemism, dysphemism, and jargon. Chapters 6 and 7 introduce the formal apparatus of propositional and predicate logic and the lambda calculus, and discuss notions of consequence such as semantic entailment and conversational and conventional implicatures. Chapters 8–10 are concerned with “cognitive and functional approaches to semantics,” that is, approaches whose theoretical constructs are claimed to have some form of “psychological reality” or are motivated in terms of their “communicative functions.” These chapters review topics such as frames and scripts, componential analysis, classifiers, color categories across languages, prototypes, and stereotypes. Chapters 11–13 address various issues in clausal and nominal semantics. Chapter 11 concerns modality, tense, and thematic roles, whereas Chapter 12 discusses different approaches to the semantics of verbs and other predicates. Chapter 13 grapples with some of the intricacies of quantification, number, and countability in English noun phrases, using generalized quantifier theory and a variant of ensemble theory. As far as I know, this is the first published tutorial account of the latter, which has previously only been accessible to students in Harry Bunt’s rather challenging monograph (1985). We are told that Chapters 11–13 “demonstrate the application of formal methods of semantic analysis to a corpus of data.” This section is likely to disappoint computational linguists, who will understand the term corpus in a different way, since the data in these chapters consist of a series of singlesentence (and mostly single-clause) examples apparently constructed by the author.

73.95, £65.00; paperbound, ISBN 0-631-19297-2,

This is a large volume, and it contains multitudes. Semantics is construed in a broad sense as the study of how meaning is communicated through the medium of language in a social context, taking account of inferences the hearer is expected to make on the basis of such factors as linguistic knowledge per se, context and “co-text,” encyclopedic knowledge, conventions of politeness and cooperative behavior, and the relative social status of speaker and hearer. The book ranges over a variety of approaches that have addressed these issues, including philosophy of language, lexicography, formal (logicbased) and cognitive semantics, frame-based knowledge representation, pragmatics, and anthropology. However, the result is more than a catalogue of theoretical tools and frameworks; throughout the book, Allan keeps in view an underlying philosophy that “meaning is cognitively and functionally motivated.” Chapters 1 and 2 introduce fundamental notions such as sense and reference, extension and intension, compositionality, and speech acts. Chapters 3–5 deal with aspects of lexical semantics: Chapter 3 concerns the structure and content of lexical entries, Chapter 4 investigates the extent to which individual morphemes can be assigned semantic interpretations, and Chapter 5 contains an illuminating discussion of aspects of nonliteral word meaning such as connotation, euphemism, dysphemism, and jargon. Chapters 6 and 7 introduce the formal apparatus of propositional and predicate logic and the lambda calculus, and discuss notions of consequence such as semantic entailment and conversational and conventional implicatures. Chapters 8–10 are concerned with “cognitive and functional approaches to semantics,” that is, approaches whose theoretical constructs are claimed to have some form of “psychological reality” or are motivated in terms of their “communicative functions.” These chapters review topics such as frames and scripts, componential analysis, classifiers, color categories across languages, prototypes, and stereotypes. Chapters 11–13 address various issues in clausal and nominal semantics. Chapter 11 concerns modality, tense, and thematic roles, whereas Chapter 12 discusses different approaches to the semantics of verbs and other predicates. Chapter 13 grapples with some of the intricacies of quantification, number, and countability in English noun phrases, using generalized quantifier theory and a variant of ensemble theory. As far as I know, this is the first published tutorial account of the latter, which has previously only been accessible to students in Harry Bunt’s rather challenging monograph (1985). We are told that Chapters 11–13 “demonstrate the application of formal methods of semantic analysis to a corpus of data.” This section is likely to disappoint computational linguists, who will understand the term corpus in a different way, since the data in these chapters consist of a series of singlesentence (and mostly single-clause) examples apparently constructed by the author.

41.95, £17.99

This paper describes a prototype implementation of a Labelled Deduction System for natural language interpretation (Gabbay and Kempson 1992), where interpretation is taken to be the process of understanding a natural language utterance. The implementation models the process of understanding wh-gap dependencies in questions and relative clauses for a fragment of English. The paper is divided in three main sections. In section 1, we introduce the basic architecture of the system. Section 2 outlines a prototype implementation of wh-binding and indicates its potential for explanation of linguistic phenomena, and in Section 3 we briefly set the model within a larger theoretical perspective, comparing it to other type-logical approaches to natural language analysis.Article