Computing with Word Meanings
This event took place on Monday 05 December 2005 at 12:30
Dr. John Carroll Department of Informatics, University of Sussex, United Kingdom
Many language processing applications could benefit from knowing the intended meaning of each word in a piece of text. For example, one would not expect a question answering system when faced with the question 'Which plants thrive in chalky soil?' even to consider returning information about factories (the industrial rather than floral sense of 'plant').
Currently, the most successful approach to disambiguating word meaning involves training machine learning algorithms on text in which each word has been tagged by hand with its intended meaning. Unfortunately, manual tagging is extremely expensive, and there is only one large hand-tagged resource currently in existence, for English and containing text in a mixture of domains. Because even this resource contains sufficient information only for commonly occuring words and since word sense distributions are often highly skewed, systems have to fall back to always guessing the first, or predominant sense for many words.
Predominant sense information could be derived from hand-tagged resources, but this is only practical for English, and even then the predominant sense of a word can depend on the domain or source of a document. (The first sense of 'star' for example would be different in the popular press and scientific journals).
In this talk, I will describe a method for determining the predominant sense of a word in any given domain automatically from raw text, and report some experiments which show that the automatically inferred sense information can in some cases be more accurate than similar information derived from hand-annotated text.
Download powerpoint presentation (464kb ZIP file)
This event took place on Monday 05 December 2005 at 12:30
Many language processing applications could benefit from knowing the intended meaning of each word in a piece of text. For example, one would not expect a question answering system when faced with the question 'Which plants thrive in chalky soil?' even to consider returning information about factories (the industrial rather than floral sense of 'plant').
Currently, the most successful approach to disambiguating word meaning involves training machine learning algorithms on text in which each word has been tagged by hand with its intended meaning. Unfortunately, manual tagging is extremely expensive, and there is only one large hand-tagged resource currently in existence, for English and containing text in a mixture of domains. Because even this resource contains sufficient information only for commonly occuring words and since word sense distributions are often highly skewed, systems have to fall back to always guessing the first, or predominant sense for many words.
Predominant sense information could be derived from hand-tagged resources, but this is only practical for English, and even then the predominant sense of a word can depend on the domain or source of a document. (The first sense of 'star' for example would be different in the popular press and scientific journals).
In this talk, I will describe a method for determining the predominant sense of a word in any given domain automatically from raw text, and report some experiments which show that the automatically inferred sense information can in some cases be more accurate than similar information derived from hand-annotated text.
Download powerpoint presentation (464kb ZIP file)
Future Internet
KnowledgeManagementMultimedia &
Information SystemsNarrative
HypermediaNew Media SystemsSemantic Web &
Knowledge ServicesSocial Software
Semantic Web and Knowledge Services is...
Our research in the Semantic Web area looks at the potentials of fusing together advances in a range of disciplines, and applying them in a systemic way to simplify the development of intelligent, knowledge-based web services and to facilitate human access and use of knowledge available on the web. For instance, we are exploring ways in which tnatural language interfaces can be used to facilitate access to data distributed over different repositories. We are also developing infrastructures to support rapid development and deployment of semantic web services, which can be used to create web applications on-the-fly. We are also investigating ways in which semantic technology can support learning on the web, through a combination of knowledge representation support, pedagogical theories and intelligent content aggregation mechanisms. Finally, we are also investigating the Semantic Web itself as a domain of analysis and performing large scale empirical studies to uncover data about the concrete epistemologies which can be found on the Semantic Web. This exciting new area of research gives us concrete insights on the different conceptualizations that are present on the Semantic Web by giving us the possibility to discover which are the most common viewpoints, which viewpoints are mutually inconsistent, to what extent different models agree or disagree, etc...
Our aim is to be at the forefront of both theoretical and practical developments on the Semantic Web not only by developing theories and models, but also by building concrete applications, for a variety of domains and user communities, including KMi and the Open University itself.
List all Semantic Web and Knowledge Services Projects
Check out these Hot Semantic Web and Knowledge Services Technologies:
List all Semantic Web and Knowledge Services Technologies
