Tech Report
Visualising Discourse Coherence in Non-Linear Documents
To produce coherent linear documents, Natural Language Generation systems have traditionally exploited the structuring role of textual discourse markers such as relational and referential phrases. These coherence markers of the traditional notion of text, however, do not work in non-linear documents: a new set of graphical devices is needed together with formation rules to govern their usage, supported by sound theoretical frameworks. If in linear documents graphical devices such as layout and...read more
User Interaction and Uptake Challenges to Successfully Deploying Semantic Web Technologies
The Semantic Web community could benefit greatly from 'eating its own dog food' in order to better understand the challenges and opportunities of a Semantic Web from the user perspective. In this paper we describe the deployment of Semantic Web applications and services at the 3rd European Semantic Web Conference (ESWC2006), before presenting results of an evaluation into how these technologies were experienced by delegates. Based on themes identified in the evaluation we highlight seven user...read more
Relation Extraction for Semantic Intranet Annotations
We present an approach for ontology driven extraction of relations from texts aimed mainly to produce enriched semantic annotations for the Semantic Web. The approach exploits linguistic and empirical strategies, by means of a pipeline method involving processes such as a parser, part-of-speech tagger, named entity recognition system, and pattern-based classification, and resources including ontology, knowledge and lexical databases. A preliminary evaluation with 25 sentences showed that the...read more
Sensemaking on the Pragmatic Web: A Hypermedia Discourse Perspective
Abstract: The complexity of the dilemmas we face on an organizational, societal and global scale forces us into sensemaking activity. We need tools for expressing and contesting perspectives flexible enough for real time use in meetings, structured enough to help manage longer term memory, and powerful enough to filter the complexity of extended deliberation and debate on an organizational or global scale. This has been the motivation for a programme of basic and applied action research into...read more
ERA (Enabling Remote Activity): A KMi designed system to support remote participation by mobility disabled students in geology field trips
This paper describes the design and initial field testing of the ERA (Enabling Remote Activity) system - a mobile wireless network devised by the Knowledge Media Institute (KMi) to support participation by mobility impaired students in geology fieldwork trips. We describe our approach and its relevance in educational and network research. We describe the set of tools implemented to facilitate remote learning, report on trial tests and lessons learnt. Finally we suggest future possible...read more
Modelling Discourse in Contested Domains: A Semiotic and Cognitive Framework
This paper examines the representational requirements for interactive, collaborative systems intended to support sensemaking and argumentation over contested issues. We argue that a perspective supported by semiotic and cognitively oriented discourse analyses offers both theoretical insights and motivates representational requirements for the semantics of tools for contesting meaning. We introduce our semiotic approach, highlighting its implications for discourse representation, before...read more
A Document-Centric Semantic Annotation Environment to Support Sense-Making
Prototype Internet infrastructures for scholarly publishing are offering powerful new services over the interconnected ideas and arguments in a literature. However, such services depend on documents being semantically annotated with readers' interpretations, which up until now has been a manual process due to the complexity of such analysis. This thesis investigates the challenge of designing computer-support for document annotation in the context of potentially diverse, contested views about a...read more
Fusing automatically extracted annotations for the Semantic Web
One of the necessary preconditions of the Semantic Web initiative is the availability of semantic data. The Web already contains large amounts of information intended for human users. This information is mainly stored as hypertext, which must be semantically annotated to make it accessible for software agents. The amount of information on the Web makes it impossible to solve the annotation task manually. Therefore the use of automatic information extraction algorithms is essential. These...read more
SemSearch: A Search Engine for the Semantic Web
Semantic search promises to produce precise answers to user queries by taking advantage of the availability of explicit semantics of information in the context of the semantic web. Existing tools have been primarily designed to enhance the performance of traditional search technologies but with little support for naive users, i.e., ordinary end users who are not necessarily familiar with domain specific semantic data, ontologies, or SQL-like query languages. This paper presents SemSearch, a...read more
Knowledge work in nursing and midwifery: an evaluation through computer mediated communication
Recent changes in policy and culture require health workers to incorporate ??knowledge work?? as a routine component of professional practice. Innovative computer-mediated communication technologies provide the opportunity to evaluate the nature of ??knowledge work?? within nursing and midwifery. This study embedded an online discussion system into an acute NHS Trust to support interaction within communities of practice. The complete record of online communications was analysed. Nurses were...read more
LRD: Latent Relation Discovery for Vector Space Expansion and Information Retrieval
In this paper, we propose a text mining method called LRD (latent relation discovery), which extends the traditional vector space model of document representation in order to improve information retrieval (IR) on documents and document clustering. Our LRD method extracts terms and entities, such as person, organization, or project names, and discovers relationships between them by taking into account their co-occurrence in textual corpora. Given a target entity, LRD discovers other entities...read more
ID: kmi-06-09
Date: 2006
Author(s): Alexandre Gonçalves, Jianhan Zhu, Dawei Song, Victoria Uren, Roberto Pacheco
Resources:
Probabilistic Methods for Data Integration in a Multi-Agent Query Answering System
This report describes a proposal for a multi agent ontology-mapping framework that makes use of probabilistic information in order to enhance the correctness of the mapping. The proposed research focuses on two correlated areas namely similarity measures with its representation as a Dempster-Shafer belief function and usability of different optimalisation methods for combining these belief functions in a distributed environment. The main goal of our proposed research is to establish a multi...read more
Co-OPR: Design and Evaluation of Collaborative Sensemaking and Planning Tools for Personnel Recovery
Personnel recovery teams must operate under intense pressure, taking into account not only hard logistics, but 'messy' factors such as the social or political implications of a decision. The Collaborative Operations for Personnel Recovery (Co-OPR) project has developed decision-support for sensemaking in such scenarios, seeking to exploit the complementary strengths of human and machine reasoning. Co-OPR integrates the Compendium sensemaking-support tool for real time information and...read more
ID: KMI-06-07
Date: 2006
Author(s): Austin Tate, Simon Buckingham Shum, Jeff Dalton, Clara Mancini, Albert Selvin
Resources: Memetic: An Infrastructure for Meeting Memory
This paper introduces the Memetic toolkit for recording the normally ephemeral interactions conducted via internet video conferencing, and making these navigable and manipulable in linear and non-linear ways. We introduce two complementary interaction visualizations: argumentation-based concept maps to elucidate the conceptual structure of the discourse using a visual language, and interactive event timelines generated from the meeting metadata. We discuss in detail the affordances of Memetics...read more
ID: KMI-06-02
Date: 2006
Author(s): Simon Buckingham Shum, Roger Slack, Michael Daw, Ben Juby, Andrew Rowley, Michelle Bachler, Clara Mancini, Danius Michaelides, Rob Procter, David De Roure, Tim Chown, Terry Hewitt
Resources: Exploiting Semantic Association To Answer Vague Queries
Although today's web search engines are very powerful, they still fail to provide intuitively relevant results for many types of queries, especially ones that are vaguely-formed in the user's own mind. We argue that associations between terms in a search query can reveal the underlying information needs in the users' mind and should be taken into account in search. We propose a multi-faceted approach to detect and exploit such associations. The CORDER method measures the association strength...read more
ID: KMI-06-01
Date: 2006
Author(s): Jianhan Zhu, Marc Eisenstadt, Dawei Song, Chris Denham
Resources: 
