this paper, we'll consider three examples where this occurs: logical metonymy (e.g., enjoy the book means enjoy reading the book), adjectives (e.g., the interpretation of fast in fast car, fast motorway, fast typist etc.), and noun-verb agreement. We'll argue for a new version of default inheritance, which allows default results of lexical generalisations to persist as default beyond the lexicon. We'll show that this persistence can be exploited by the pragmatic component, to reason about when generalisations encoded in the lexicon survive in a discourse context. We'll represent the link between the lexicon and pragmatics via two axioms. These will predict the pragmatic exceptions to lexical generalisations that arise in a discourse context. We thereby explain how words are interpreted in discourse, in a way that neither the lexicon nor pragmatics could achieve on their own.

this paper allows any defaults to be overridden by defaults which are associated with more specific types: thus priority ordering reflects the type hierarchy ordering. (In 6.2, we will mention other possibilities for imposing a priority order on defaults.) Barring criterion 6, all of the above properties are necessary for making default unification behave as much like normal unification as possible, save that (default) information can be overridden. These criteria ensure that the default unification operation has properties familiar from monotonic unification, such as determinacy, the way information is accumulated, the conditions when unification fails, and order independence. Since this guarantees that default unification shares many of the properties of normal unification, a `seamless transition' is possible between the monotonic approach to linguistic analysis supplied by normal unification, and the extension to these analyses provided by supplying default constraints and default unification operating over them. We will justify these assumptions with respect to particular linguistic examples in 4

This thesis describes a proposal for the treatment of derivation as part of a lexical component for HPSG. The system is not based on a `syntax of words', but solely on a hierarchical structure of the lexicon. The approach is motivated by a detailed study of bar-adjectives in German. The analysis of data from corpora has shown that a word-syntax alone is not sufficient to cover the data. The proposed alternative explains phenomena of affixation by multiple inheritance in a hierarchy of lexical types (cf. Pollard & Sag 1987 or Krieger & Nerbonne 1992), without assuming categorymarked lexical entries for affixes. The lexical types express generalizations about existing words and thus have the effect of eliminating redundant information in lexical entries. They explicitly serve as redundancy rules (cf. Jackendoff 1975), mainly giving structure to the lexicon and only secondarily being activated for productive word formation. By exploiting the fact that feature structures in HPSG are typed ...

This thesis is an investigation of the representation of lexical semantic information from a computational linguistic perspective. An implemented representation language is described which is not specic to lexical semantics, but is based on the use of typed feature structures augmented with default operations. This language, which is formally specied, allows the lexical semantic representations to be tightly integrated with the syntactic component of the lexical sign, capturing generalisations by use of inheritance, while allowing for exceptions with the default mechanism. Default inheritance and default unication are discussed in detail. Grammar rules and lexical rules can be specied in the same formalism and thus the paradigmatic treatment of lexical semantics can be integrated with an account at the syntagmatic level. The use of the language is illustrated with some examples of the representation of verbs, the treatment of logical metonymy and of sense extension. This is followe...

A formalism is presented for lexical specification in unification-based grammars which exploits defeasihie multiple inheritance to express regularity, subregularity, and exceptions in classifying the properties of words. Such systems are in the general case intractable; the present proposal represents an attempt to reduce complexity while retaining sufficient expressive power for the task at hand. Illustrative examples are given of morphological analyses from English and German.

We describe a compiler which translates a set of hpsg lexical rules and their interaction into definite relations used to constrain lexical entries. The compiler ensures automatic transfer of properties unchanged by a lexical rule. Thus an operational semantics for the full lexical rule mechanism as used in HPSG linguistics is provided. Program transformation techniques are used to advance the resulting encoding. The final output constitutes a computational counterpart of the linguistic generalizations captured by lexical rules and allows "on the fly" application. Keywords: lexical rules, hpsg, off-line compilation, program transformation. 1 Introduction In the paradigm of hpsg, lexical rules (henceforth lr) have become one of the key mechanisms used in current analysis. Among logicians and computational linguists, lrs have been far less popular. The intuitive idea behind lrs is based on notions such as matching, copying, and automatic transfer of the properties unchanged by a lr, ...

Abstract not found

Approaches to morphology typically account for regular, completely productive affixation, while ignoring subregular and semiproductive schemata. The alternative approach to derivational morphology presented here relates exceptions and subregularities to productive rules. It accounts for the contribution lexicalized words make to the rule, and for the fact that not all new formations follow the `rules'. It also captures linguistically relevant generalizations that cannot be expressed in other theories. The approach is formalized in terms of complex recursive schemata structured in a multiple inheritance hierarchy, without positing lexical rules or lexical entries for affixes. These schemata structure the existing lexicon, reducing redundancy, and at the same time serve as the basis for productive word formation. The approach handles zero-derivation and other nonconcatenative morphology straightforwardly.

Abstract. Increasingly, inheritance hierarchies are being used to reduce redundancy in natural language processing lexicons. Systems that utilize inheritance hierarchies need to be able to insert words under the optimal set of classes in these hierarchies. In this paper, we formalize this problem for feature-based default inheritance hierarchies. Since the problem turns out to be NP-complete, we present an approximation algorithm for it. We show that this algorithm is efficient and that it performs well with respect to a number of standard problems for default inheritance. A prototype implementation has been tested on lexical hierarchies and it has produced encouraging results. The work presented here is also relevant to other types of default hierarchies. Abstract. In zunehmendem Masse werden Erbschaftshierarchien zur kompakten Beschreibung von Worteigenschaften in Sprachverarbeitungslexica verwendet. Systeme, die Erbschaftshierarchien benützen, müssen Worte in die optimale Klasse (oder Menge von Klassen) der Hierarchien einfügen können. Dieser Beitrag formalisiert das Problem für merkmalsbasierte default-Hierarchien. Da das Problem NP-vollständig ist, wird hier ein Approximationsalgorithmus vorgeschlagen. Es wird gezeigt, daß der Algorithmus effizient ist und daß er in Hinsicht auf einige Standardprobleme der default-Hierarchien gut funktioniert. Eine Prototypimplementierung zeigt gute Resultate an einigen Hierarchien, die für Lexica der Computerlinguistik geschrieben wurden. Diese Forschung kann auch für andere Arten von default-Hierarchien angewendet werden. 1

The paper presents a prototype lexicalist Machine Translation system (based on the so-called `Shake-and-Bake' approach of Whitelock (1992)) consisting of an analysis component, a dynamic bilingual lexicon, and a generation component, and shows how it is applied to a range of MT problems. Multi-Lexeme translations are handled through bi-lexical rules which map bilingual lexical signs into new bilingual lexical signs. It is argued that much translation can be handled by equating translationally equivalent lists of lexical signs, either directly in the bilingual lexicon, or by deriving them through bi-lexical rules. Lexical semantic information organized as Qualia structures (Pustejovsky 1991) is used as a mechanism for restricting the domain of the rules. 1 Introduction Transfer based approaches to machine translation (MT) involve three main phases: analysis, transfer and generation. During analysis, the syntactic and semantic structure of a sentence is made explicit through a source la...