Lexical database enrichment through semi-automated morphological analysis

Derivational morphology proposes meaningful connections between words and is largely unrepresented in lexical databases. This thesis presents a project to enrich a lexical database with morphological links and to evaluate their contribution to disambiguation. A lexical database with sense distinctions was required. WordNet was chosen because of its free availability and widespread use. Its suitability was assessed through critical evaluation with respect to specifications and criticisms, using a transparent, extensible model. The identification of serious shortcomings suggested a portable enrichment methodology, applicable to alternative resources. Although 40% of the most frequent words are prepositions, they have been largely ignored by computational linguists, so addition of prepositions was also required. The preferred approach to morphological enrichment was to infer relations from phenomena discovered algorithmically. Both existing databases and existing algorithms can capture regular morphological relations, but cannot capture exceptions correctly; neither of them provide any semantic information. Some morphological analysis algorithms are subject to the fallacy that morphological analysis can be performed simply by segmentation. Morphological rules, grounded in observation and etymology, govern associations between and attachment of suffixes and contribute to defining the meaning of morphological relationships. Specifying character substitutions circumvents the segmentation fallacy. Morphological rules are prone to undergeneration, minimised through a variable lexical validity requirement, and overgeneration, minimised by rule reformulation and restricting monosyllabic output. Rules take into account the morphology of ancestor languages through co-occurrences of morphological patterns. Multiple rules applicable to an input suffix need their precedence established. The resistance of prefixations to segmentation has been addressed by identifying linking vowel exceptions and irregular prefixes. The automatic affix discovery algorithm applies heuristics to identify meaningful affixes and is combined with morphological rules into a hybrid model, fed only with empirical data, collected without supervision. Further algorithms apply the rules optimally to automatically pre-identified suffixes and break words into their component morphemes. To handle exceptions, stoplists were created in response to initial errors and fed back into the model through iterative development, leading to 100% precision, contestable only on lexicographic criteria. Stoplist length is minimised by special treatment of monosyllables and reformulation of rules. 96% of words and phrases are analysed. 218,802 directed derivational links have been encoded in the lexicon rather than the wordnet component of the model because the lexicon provides the optimal clustering of word senses. Both links and analyser are portable to an alternative lexicon. The evaluation uses the extended gloss overlaps disambiguation algorithm. The enriched model outperformed WordNet in terms of recall without loss of precision. Failure of all experiments to outperform disambiguation by frequency reflects on WordNet sense distinctions.

Society

What is the nature of our current societies? Do we see a clash of civilizations, or the end of history? The advent of globalization, or the birth of the network society? Are we witnessing the emergence of a risk society, or the advent of the knowledge society? More fundamentally, is ‘society’ an ideological construct that should be abandoned? Coming into English from the Latin term ‘societas’ via Old French ‘société’, the etymology of ‘society,’ in the sense of a system adopted by a group of co-existing individuals for mutually beneficial purposes, can be traced back at least to the mid-sixteenth century. By the Age of Enlightenment, ‘society’ was increasingly used in intellectual discourse to characterize human relations, often in contrast to notions of ‘the state’. During the nineteenth century, the concept was subject to highly elaborate treatment in various intellectual fields, such as political economy, philosophy, and legal thought; and ‘society’ continues to be a central conceptual tool, not only for sociology, but also for many other social-science disciplines, such as anthropology, economics, political sciences, and law. The notion resonates beyond the social sciences into the humanities; it is a fundamental concept, like nature, the universe, or the economy. Moreover, ‘society’ remains a highly contested concept, as was demonstrated, for example, by the controversy surrounding the former British prime minister Margaret Thatcher’s pithy assertion of the neoliberal economic wisdom that ‘there is no such thing as society’ (Woman’s Own, 31 October 1987); and by the term’s rehabilitation at the turn of the twenty-first century, not least with the ascendancy of the notion of ‘civil society’. This four-volume collection, a new title in the Routledge Critical Concepts in Sociology series, brings together both canonical and the best cutting-edge research to document the intellectual origins and development of what remains a key framework within which contemporary work in the social sciences in general, and sociology in particular, proceeds. Edited by Reiner Grundmann and Nico Stehr, two leading scholars in the field, this Routledge Major Work makes available the most useful, important and representative treatments of the subject matter, and helps to make sense of the great variety of perspectives and approaches in which social scientists and other thinkers have understood, and continue to understand, society. Fully indexed and with a comprehensive introduction newly written by the editors, which places the collected material in its historical and intellectual context, Society is an essential reference work, destined to be valued by scholars and students as a vital research resource.