Skip to main content

Über dieses Buch

Cognitive and Computational Strategies for Word Sense Disambiguation examines cognitive strategies by humans and computational strategies by machines, for WSD in parallel.

Focusing on a psychologically valid property of words and senses, author Oi Yee Kwong discusses their concreteness or abstractness and draws on psycholinguistic data to examine the extent to which existing lexical resources resemble the mental lexicon as far as the concreteness distinction is concerned. The text also investigates the contribution of different knowledge sources to WSD in relation to this very intrinsic nature of words and senses.



Chapter 1. Word Senses and Problem Definition

This book is about word sense disambiguation, the process of figuring out word meanings in a discourse which is an essential task in natural language processing. Computational linguists’ efforts over several decades have led to an apparently plateaued performance in state-of-the-art systems, but considerable unknowns regarding the lexical sensitivity of the task still remain. We propose to address this issue through a better synergy between the computational and cognitive paradigms, which had once closely supported and mutually advanced each other. We start off with an introduction to the word sense disambiguation problem and the notion of word senses in this chapter. While the psychological reality of word senses is beyond doubt, the boundaries between senses could be fuzzy. We discuss various models for representing senses and suggest that the discreteness assumption held by most mainstream systems is relevant to the perception of word senses rather than their definition.
Oi Yee Kwong

Chapter 2. Methods for Automatic WSD

Research in automatic word sense disambiguation has a long history on a par with computational linguistics itself. In this chapter, we take a two-dimensional approach to review the development and state of the art of the field, by the knowledge sources used for disambiguation on the one hand, and the algorithmic mechanisms with which the knowledge sources are actually deployed on the other. The trend for the latter is relatively clear, correlating closely with the historical development of many other natural language processing subtasks, where conventional knowledge-based methods gradually give way to scalable, corpus-based statistical and supervised methods. While the importance of multiple knowledge sources has been realised at the outset, their effective use in disambiguation systems has nevertheless been constrained by the notorious problem of “knowledge acquisition bottleneck” and is therefore very much dependent on the availability of suitable lexical resources.
Oi Yee Kwong

Chapter 3. Lessons Learned from Evaluation

The performance evaluation of word sense disambiguation systems has only been more or less standardised in the last decade with the first three SENSEVAL and the more recent SEMEVAL exercises. These exercises have pointed to the superiority of supervised methods using multiple knowledge sources and ensembles of classifiers. Behind the apparently plateaued performance of state-of-the-art systems, some fundamental issues including sense granularity, sparseness of sense-tagged data, and contribution to real applications, still remain. But more importantly, evaluation results also suggest that there is something about the target words themselves which is responsible for the differential performance among systems trained on the same feature sets, and within systems on different target words. We suggest that such intrinsic nature of the target words has a direct impact on the accuracy of sense disambiguation, which cannot be addressed solely from the computational perspective.
Oi Yee Kwong

Chapter 4. The Psychology of WSD

How do humans resolve semantically ambiguous words? It happens that we will not find a direct answer from psycholinguistic studies. Nevertheless, through probing the organisation of words in the mental lexicon and the access of words, particularly those with multiple meanings, in the human mind, useful hints might be found. In this chapter, we focus our attention on the cognitive aspects of word sense disambiguation. We first review the psychological findings on the mental lexicon, including the storage of words, the representation of meanings, and sense distinction. Mechanisms of lexical access will then be discussed, especially with reference to the different factors which might affect semantic activation. Where appropriate, how such psychological models have been realised computationally in automatic word sense disambiguation will be highlighted.
Oi Yee Kwong

Chapter 5. Sense Concreteness and Lexical Activation

Psycholinguistic evidence has thus suggested the differential processing of concrete and abstract concepts by the human mind. This chapter further explores the mental lexicon with respect to the concreteness and abstractness of concepts based on word association data. Since lexical resources including computational semantic lexicons play a critical role in automatic word sense disambiguation, we aim at investigating to what extent such concreteness distinction is modelled in existing lexical resources. It was observed that concrete and abstract noun senses tend to exhibit consistently different lexical activation patterns, and the results suggest that sense concreteness may serve as a possible alternative classification of word senses relevant to the lexical sensitivity of word sense disambiguation, as well as to the contributions of different knowledge sources in the task.
Oi Yee Kwong

Chapter 6. Lexical Sensitivity of WSD: An Outlook

We have tried to show from our discussion in the previous chapters that while ensembles of classifiers based on supervised learning methods trained on multiple contextual features have proved to perform superiorly in current mainstream automatic word sense disambiguation, and their performance might have apparently reached a plateau, there are still considerable unknowns as far as the lexical sensitivity of the task is concerned. We have also suggested that these under-explored parts cannot be adequately addressed from the computational perspective alone, as they probably involve some intrinsic properties of words and senses, like concept concreteness, which may be cognitively based. In this final chapter, we put forth some preliminary evidence regarding the impact of concept concreteness on the information demand in disambiguation, and conclude with a research agenda which attempts to bring the two camps closer to advance the research on an area of their mutual concern.
Oi Yee Kwong


Weitere Informationen

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Globales Erdungssystem in urbanen Kabelnetzen

Bedingt durch die Altersstruktur vieler Kabelverteilnetze mit der damit verbundenen verminderten Isolationsfestigkeit oder durch fortschreitenden Kabelausbau ist es immer häufiger erforderlich, anstelle der Resonanz-Sternpunktserdung alternative Konzepte für die Sternpunktsbehandlung umzusetzen. Die damit verbundenen Fehlerortungskonzepte bzw. die Erhöhung der Restströme im Erdschlussfall führen jedoch aufgrund der hohen Fehlerströme zu neuen Anforderungen an die Erdungs- und Fehlerstromrückleitungs-Systeme. Lesen Sie hier über die Auswirkung von leitfähigen Strukturen auf die Stromaufteilung sowie die Potentialverhältnisse in urbanen Kabelnetzen bei stromstarken Erdschlüssen. Jetzt gratis downloaden!