Andrew Hippisley

The head-modifier principle and multilingual term extraction

Advances in language engineering may be dependent on theoretical principles originating from linguistics, since both share a common object of enquiry, natural language structures. We outline an approach to term extraction that rests on theoretical claims about the structure of words. We use the structural properties of compound words to specifically elicit the sets of terms defined by type hierarchies such as hyponymy and meronymy. The theoretical claims revolve around the head-modifier principle, which determines the formation of a major class of compounds. Significantly it has been suggested that the principle operates in languages other than English. To demonstrate the extendibility of our approach beyond English, we present a case study of term extraction in Chinese, a language whose written form is the vehicle of communication for over 1.3 billion language users, and therefore has great significance for the development of language engineering technologies.

Network Morphology: A Defaults-based Theory of Word Structure

1. Options in constructing a morphological framework 2. A framework for morphological defaults 3. Inflectional classes 4. Syncretism 5. Morphological mismatch and extended deponency 6. Defaults and paradigmatic restructuring 7. Derivation 8. Conclusion.

Word formation rules in a default inheritance framework: a Network Morphology account of Russian personal nouns

The notion of Word Formation Rule (WFR) has been central to approaches to derivational morphology since Chomsky’s Remarks on Nominalization (Chomsky 1970), and his emphasis on a structured lexicon. Following on the heals of Chomsky a number of different versions were offered (Halle 1973, Jackendoff 1975, Aronoff 1976) all with the common two-fold aim On the one hand derivational morphology must be restricted to the lexicon, because in terms of regularity its behaviour is clearly at odds with the syntactic and phonological components; and on the other hand, in the spirit of the generative programme what regularity there is must certainly be captured. This was met by locating any redundancy in the lexicon and reducing it where possible. Redundancy was located by observing repeated patterns in the set of derived words (the combination of affix and syntactico-semantic properties is repeated for a group of items); it was reduced by creating rules relating Base lexical items to their Derivatives. This is the role of the WFR, and at its heart therefore lies the treatment of the relationship between a Base lexical item and its Derivative. These WFRs were also housed in the lexicon.

The Mood of the (Financial) Markets: In a Corpus of Words and of Pictures

Corpora of texts are used typically to study the structure and function of language. The distribution of various linguistic units, comprising texts in a corpus are used to make and test hypotheses relevant to different linguistic levels of description. News reports and editorials have been used extensively to populate corpora for studying language, for making dictionaries and for writing grammar books. News reports of financial markets are generally accompanied by time-indexed series of values of shares, currencies and so on, reflecting the change in value over a period of time. A corpus linguistic method for extracting sentiment indicators, e.g. shares going up or a currency falling down, is presented together with a technique for correlating the quantitative time-series of values with a time series of sentiment indicators. The correlation may be used in the analysis of the movement of shares, currencies and other financial instruments.

Indexed stems and Russian word formation : a network-morphology account of Russian personal nouns

Recent lexeme-based models have proposed that a lexeme carries an inventory of stems on which morphological rules operate, The various stems in the inventory are associated with different morphological rules, of both inflection and derivation. Furthermore, one stem may be selected by more than one rule. For this reason stems in the inventory are labeled with indexes, rather than being directly associated with a particular morphological function. It is claimed that an indexed-stem approach captures generalizations in the morphological system that would otherwise be missed. We argue that such an approach provides for greater generalization in the Russian morphological system. One area of Russian derivation that particularly lends itself to an indexed-stem approach is the highly productive system of personal-noun formation. We present a declarative account of Russian personal nouns that assumes indexed stems and show how such an account on the one hand obviates the need to posit either compound suffixes or concatenators and on the other dispenses with truncating/deleting rules. The account is couched within network morphology, a declarative lexeme-based framework that rests on the concept of default inheritance and is expressed in the computable lexical knowledge representation language DATR

Grammatical Typology and Frequency Analysis: Number Availability and Number Use

The Smith-Stark hierarchy, a version of the Animacy Hierarchy, offers a typology of the cross-linguistic availability of number. The hierarchy predicts that the availability of number is not arbitrary. For any language, if the expression of plural is available to a noun, it is available to any noun of a semantic category further to the left of the hierarchy. In this article we move one step further by showing that the structure of the hierarchy can be observed in a statistical model of number use in Russian. We also investigate three co-variates: plural preference, pluralia tantum and irregularity effects; these account for an items behaviour being different than that solely expected from its animacy position.

A method for automating the extraction of specialized information from the web

The World Wide Web can be viewed as a gigantic distributed database including millions of interconnected hosts some of which publish information via web servers or peer-to-peer systems. We present here a novel method for the extraction of semantically rich information from the web in a fully automated fashion. We illustrate our approach via a proof-of-concept application which scrutinizes millions of web pages looking for clues as to the trend of the Chinese stock market. We present the outcomes of a 210-day long study which indicates a strong correlation between the information retrieved by our prototype and the actual market behavior.

Morphology in Constraint-based Lexical Approaches to Grammar

Strong lexicalism Morphology and syntax are separate dimensions of language, modelled by discrete components of a theory of grammar. The word is the interface between morphology and syntax: words are atoms of syntactic description, while morphology describes relations between words and/or relations between words and more abstract lexical entities (roots, stems, lexemes, affixes, morphophonological processes, etc.).

Morphology and Language Acquisition

Morphology is language specific and must be acquired on the basis of particular linguistic data. This chapter addresses three central issues for the understanding of morphological acquisition: the distributional properties of morphology, the mechanisms of learning from data, and the developmental patterns and trajectories in child language. First, corpus studies of child directed language reveal a systematic pattern of data sparsity: in general, only a (small) fraction of possible morphological forms will be attested in the acquisition data. The child learner, then, must be able to form wide ranging generalizations from early on, and on very partial corners of the morphological paradigm. Second, we review evidence from morphological development, especially the study of English past tense, and draw two broad conclusions: (a) morphologically complex forms appear not memorized by association but are learned in relation to their morpho-phonological classes, lexicalized or otherwise, and (b) as far as child language is concerned, morphological productivity appears categorical, where children often over-use productive processes but almost never commit analogical errors. Third, we situate morphological learning models in the context of language acquisition, where psychological considerations pose additional challenges and constraints. The child must proceed in an incremental and unsupervised fashion, which deprives them of assumptions (such as stem and derived pairs) that are taken for granted in theoretical analysis. Along the way, we discuss how language acquisition may provide useful insight for the theoretical study of morphology.

A Fox Knows Many Things but a Hedgehog One Big Thing

[T]akenfiguratively, thewords canbemade to yield a sense inwhich theymark one of the deepest differences which divide writers and thinkers, and, it may be, human beings in general. For there exists a great chasm between those, on one side, who relate everything to a single central vision, one system less or more coherent or articulate, in terms of which they understand, think, and feel—a single, universal, organizing principle in terms of which alone all that they are and say has significance—and, on the other side, those who pursue many ends, often unrelated and even contradictory, connected, if at all, only in some de factoway, for some psychological or physiological cause, related by no moral or aesthetic principle; these last lead lives, perform acts, and entertain ideas that are centrifugal rather than centripetal, their thought is scattered or diffused, moving on many levels, seizing upon the essence of a vast variety of experiences and objects for what they are in themselves, without, consciously or unconsciously, seeking to fit them into, or exclude them from, any one unchanging, all-embracing, sometimes self-contradictory and incomplete, at times fanatical, unitary vision. The first kind of intellectual and artistic personality belongs to the hedgehogs, the second to the foxes; and without insisting on a rigid classification, wemay, without toomuch fear of contradiction, say that, in this sense, Dante belongs to the first category, Shakespeare to the second; Plato, Lucretius, Pascal, Hegel, Dostoevsky, Nietzsche, Ibsen, Proust are, in varying degrees, hedgehogs; Herodotus, Aristotle, Montaigne, Erasmus, Molière, Goethe, Pushkin, Balzac, Joyce are foxes.