Yorick Wilks

Position Paper (2009)

Kalina Bontcheva, Christopher Brewster, Fabio Ciravegna, Hamish Cunningham, Louise Guthrie, Robert Gaizauskas, ...

AKT is a major research project applying a variety of technologies to knowledge management. Knowledge is a dynamic, ubiquitous resource, which is to be found equally in an expert's head, under...

So, in: (2009)

John Bought, The Book, That I Had, Been Try, Yorick Wilks, Xiuming Huang, ...

The paper claims that the right attachment rules for phrases originally suggested by Frazier and Fodor are wrong, and that none of the subsequent patchings of the rules by syntactic methods have...

The Learning Companion: an Embodied Conversational Agent for Learning (2009)

Eynon, Rebecca, Davies, Chris, Wilks, Yorick

The possibilities for adults to learn using the World Wide Web are numerous and exciting. Yet while those individuals, who have the skills to navigate, locate, create and make use of these resources...

To appear in the International Journal of Web Semantics. The Semantic Web as the apotheosis of annotation, but what are its semantics? (2008)

Yorick Wilks

“In the middle of a cloudy thing is another cloudy thing, and within that another cloudy and thing, inside which is yet another cloudy thing………… ………………and in that is yet another...

Clustering-Based Language Independent Multiple-Document Summarizer at MSE 2006 (2008)

Angelo Dalli, Roberta Catizone, Yorick Wilks

We describe our participation in the Multilingual Summarization Evaluation MSE 2006 where multiple documents in English, Arabic and Arabic-English machine translations are used to create a brief 100...

Cross-linguistic Discovery of Semantic Regularity (2008)

Wim Peters, Louise Guthrie, Yorick Wilks

The question of whether metonymy carries across languages has always been interesting for language representation and processing. Until now attempts to answer this question have always been based on...

�Computational Linguistics Society of R.O.C. Information Extraction: Beyond Document Retrieval (2008)

Robert Gaizauskas, Yorick Wilks

In this paper we give a synoptic view of the growth text processing technology of information extraction (IE) whose function is to extract information about a pre-specified set of entities, relations...

214 Automatic Report Generation from Ontologies: the MIAKT approach (2008)

Kalina Bontcheva, Yorick Wilks

Abstract. This paper presented an approach for automatic generation of reports from domain ontologies encoded in Semantic Web standards like OWL. The paper identifies the challenges that need to be...

Event-coreference across Multiple Multi-lingual Sources in the MUMIS Project ∗ (2008)

Jan Kuper, Horacio Saggion, Hamish Cunningham, Thierry Declerck, Marco Puts, Franciska De Jong, ...

This paper describes work done in the context of the MUMIS project, especially on multi-document information extraction. The MUMIS project aims at searching and indexing video material on the domain...

American Journal of Computational Linguistics Microf ichc 56 (2008)

Yorick Wilks

This paper has three purposes: firstly, to describe how case information IS distributed in the preference semantics system of language understahding, and tc show what practical use is made of that...

Emotion in Human-Agent Interfaces (2008)

Peter Wallis, Roger Moore, Petra Fagerberg, Marc Cavazza, Yorick Wilks

Recent years have seen an upsurge of interest in the implications and applications of emotional behaviour in the human-computer interface (Picard 1997). In particular, research has focused on...

ABSTRACT Right Attachment and Preference Semantics. (2008)

Yorick Wilks

The paper claims that the right attachment rules for phrases originally suggested by Frazier and Fodor are wrong, and that none of the subsequent patchings of the rules by syntactic methods have...

A Closer Look at Skip-gram Modelling (2008)

David Guthrie, Ben Allison, Wei Liu, Louise Guthrie, Yorick Wilks

Data sparsity is a large problem in natural language processing that refers to the fact that language is a system of rare events, so varied and complex, that even using an extremely large corpus, we...

Chapter 3 MAKING SENSE ABOUT SENSE (2008)

Nancy Ide, Yorick Wilks

Abstract We suggest that the standard fine-grained division of senses and (larger) homographs by a lexicographer for use by a human reader may not be an appropriate goal for the computational WSD...

To appear in the International Journal of Web Semantics. The Semantic Web as the apotheosis of annotation, but what are its semantics? (2008)

Yorick Wilks

“In the middle of a cloudy thing is another cloudy thing, and within that another cloudy and thing, inside which is yet another cloudy thing………… ………………and in that is yet another...

‘Embedded Sensor Networks ’ by Christine Borgman Dealing with the Data Deluge (2008)

Yorick Wilks, Matthijs Den Besten

The Internet emerged from efforts to support resource sharing among computer scientists. The technologies being developed to support remote collaboration, resource sharing and other aspects of...

Chapter 3 MAKING SENSE ABOUT SENSE (2008)

Making Sense About, Nancy Ide, Yorick Wilks

We first reconsider the role of lexicographers in word-sense disambiguation as a computational task, as providers of both legacy material (dictionaries) and special test material for competitions...

The "Fodor"-FODOR fallacy bites back (2008)

Yorick Wilks

The paper argues that Fodor and Lepore are misguided in their attack on Pustejovsky's Generative Lexicon, largely because their argument rests on a traditional, but implausible and discredited,...

Engaging with artificial companions: Key social, psychological, ethical and design issues (2008)

Malcolm Peltu, Yorick Wilks

Artificial companions (ACs) are typically intelligent cognitive 'agents', implemented in software or a physical embodiment such as a robot. They can stay with their 'owner' for long periods of time,...

Large Vocabulary Word Sense Disambiguation (2007)

Mark Stevenson, Yorick Wilks

this paper) versus one that is applied to only a small trial selection of words (for example Schutze (1992) and Yarowsky (1995)). The latter researchers have obtained very high levels of success:...

Some Notes on State of the Art: Where are We Now in MT: What Works and What Doesn't? and The Role of MT as an International Collaborative Activity (2007)

Yorick Wilks

The paper examines briefly the impact of the 'statistical turn' in machine translation (MT) R&D in the last decade, and particularly the way in which it has made large scale language...

Event-coreference across Multiple, Multi-lingual Sources in the Mumis (2007)

Marco Puts, Eduard Hoenkamp, Franciska De Jong, Yorick Wilks

yorick @ dcs.shefiac.uk- fdejong @ cs.utwente.nl puts @ nici.kun.nl- hoenkamp @ acm.org We present our work on information extraction from multiple, multi-lingual sources for the Multimedia Indexing...

and Wilks Implementing a Sense Tagger (2007)

Hamish Cunningham, Mark Stevenson, Yorick Wilks

We describe two systems: GATE (General Ar-chitecture for Text Engineering), an architec-ture to aid in the production and delivery of language engineering systems which signifi-cantly reduces...

MUSE: a MUlti-Source Entity recognition system (2007)

Diana Maynard, Valentin Tablan, Kalina Bontcheva, Hamish Cunningham, Yorick Wilks

Abstract. This paper describes a robust and easily adaptable system for named entity recognition from a variety of different text types. Most information extraction systems need to be customised...

Knowledge Acquisition for Knowledge Management: Position Paper (2007)

Christopher Brewster Fabio, Fabio Ciravegna, Yorick Wilks

this paper, we propose a set of techniques to largely automate the process of KA, by using technologies based on Information Extraction (IE), Information Retrieval and Natural Language Processing. We...

Computational Linguistics Society of R.O.C. Information Extraction: Beyond Document Retrieval (2007)

Robert Gaizauskas, Yorick Wilks

In this paper we give a synoptic view of the growth text processing technology of information extraction (IE) whose function is to extract information about a pre-specified set of entities, relations...

Artificial Companions as a new kind of interface to the future Internet (2007)

Yorick Wilks

This research report seeks to connect the future of the Internet to a new, even though relatively developed, technology; that of computer speech and language and its embodiment in a concept the...

Image annotation with Photocopain (2006)

Tuffield, Mischa, Harris, Stephen, Dupplaw, David P., Chakravarthy, Ajay, Brewster, Christopher, Gibbins, Nicholas, ...

Photo annotation is a resource-intensive task, yet is increasingly essential as image archives and personal photo collections grow in size. There is an inherent conflict in the process of describing...

Photocopain - Annotating Memories For Life (2006)

Tuffield, Mischa M, Dupplaw, David P, O'Hara, Kieron, Shadbolt, Nigel R, Chakravarthy, Ajay, Brewster, Christopher, ...

Photo annotation is a resource-intensive task, yet is increasingly essential as image archives and personal photo collections grow in size. There is an inherent conflict in the process of describing...

Image annotation with Photocopain (2006)

Tuffield, Mischa, Harris, Stephen, Dupplaw, David P., Chakravarthy, Ajay, Brewster, Christopher, Gibbins, Nicholas, ...

Photo annotation is a resource-intensive task, yet is increasingly essential as image archives and personal photo collections grow in size. There is an inherent conflict in the process of describing...

Image annotation with Photocopain (2006)

Tuffield, Mischa M., Harris, Stephen, Duplaw, David P., Chakravarthy, Ajay, Brewester, Christopher, Gibbins, Nicholas, ...

Photo annotation is a resource-intensive task, yet is increasingly essential as image archives and personal photo collections grow in size. There is an inherent conflict in the process of describing...

Photocopain - Annotating Memories For Life (2006)

Tuffield, Mischa M, Dupplaw, David P, O'Hara, Kieron, Shadbolt, Nigel R, Chakravarthy, Ajay, Brewster, Christopher, ...

Photo annotation is a resource-intensive task, yet is increasingly essential as image archives and personal photo collections grow in size. There is an inherent conflict in the process of describing...

Image annotation with Photocopain (2006)

Tuffield, Mischa, Harris, Stephen, Dupplaw, David P., Chakravarthy, Ajay, Brewster, Christopher, Gibbins, Nicholas, ...

Photo annotation is a resource-intensive task, yet is increasingly essential as image archives and personal photo collections grow in size. There is an inherent conflict in the process of describing...

Photocopain - Annotating Memories For Life (2006)

Tuffield, Mischa M, Dupplaw, David P, O'Hara, Kieron, Shadbolt, Nigel R, Chakravarthy, Ajay, Brewster, Christopher, ...

Photo annotation is a resource-intensive task, yet is increasingly essential as image archives and personal photo collections grow in size. There is an inherent conflict in the process of describing...

Image annotation with photocopain (2006)

Mischa M. Tuffield, Stephen Harris, Christopher Brewster, Nicholas Gibbins, Fabio Ciravegna, Derek Sleeman, ...

Abstract. Photo annotation is a resource-intensive task, yet is increasingly essential as image archives and personal photo collections grow in size. There is an inherent conflict in the process of...

Image annotation with photocopain (2006)

Mischa M. Tuffield, Stephen Harris, Christopher Brewster, Nicholas Gibbins, Fabio Ciravegna, Derek Sleeman, ...

Abstract. Photo annotation is a resource-intensive task, yet is increasingly essential as image archives and personal photo collections grow in size. There is an inherent conflict in the process of...

The Semantic Web as the apotheosis of annotation, but what are its (2006)

Semantics Yorick Wilks, Yorick Wilks

The paper discussed what kind of entity the proposed Semantic Web (SW) is, in terms of the relationship of language to knowledge representation (KR). It argues that there are three views: first, that...

Y.: An Incremental Tri-partite Approach to Ontology Learning (2006)

José Iria, Christopher Brewster, Fabio Ciravegna, Yorick Wilks

In this paper we present a new approach to ontology learning. Its basis lies in a dynamic and iterative view of knowledge acquisition for ontologies. The Abraxas approach is founded on three...

COMPANIONS Consortium: State Of The Art Papers (2006)

Yorick Wilks, Roberta Catizone, Markku Turunen

systems have been around since the 1960’s, the best known are conversation programs such as Eliza (Weizenbaum 1966) and Parry (Colby 1973). The approaches we describe are categorised as follows:...

Journal publishing and author self-archiving: peaceful co-existence and fruitful collaboration (2005)

Berners-Lee, Tim, De Roure, Dave, Harnad, Stevan, Law, Derek, Murray-Rust, Peter, Oppenheim, Charles, ...

The UK Research Funding Councils (RCUK) have proposed that all RCUK fundees should self-archive on the web, free for all, their own final drafts of journal articles reporting their RCUK-funded...

Journal publishing and author self-archiving: peaceful co-existence and fruitful collaboration (2005)

Berners-Lee, Tim, De Roure, Dave, Harnad, Stevan, Law, Derek, Murray-Rust, Peter, Oppenheim, Charles, ...

The UK Research Funding Councils (RCUK) have proposed that all RCUK fundees should self-archive on the web, free for all, their own final drafts of journal articles reporting their RCUK-funded...

Journal publishing and author self-archiving: peaceful co-existence and fruitful collaboration (2005)

Berners-Lee, Tim, De Roure, Dave, Harnad, Stevan, Law, Derek, Murray-Rust, Peter, Oppenheim, Charles, ...

The UK Research Funding Councils (RCUK) have proposed that all RCUK fundees should self-archive on the web, free for all, their own final drafts of journal articles reporting their RCUK-funded...

SEMANTIC BASIS OF COMMUNICATION. (2005)

Wilks,Yorick, Shillan,David, Dobson,John, Jones,K. Sparck

A semantic recognition procedure is defined in which interlingually coded text is machine searched with an inventory of semantic targets. From the result of this search a final message structure for...

Error Analysis of Dialogue Act Classification (2005)

Nick Webb, Mark Hepple, Yorick Wilks

We are interested in the area of Dialogue Act (da) tagging.

Dialogue Act Classification Based on Intra-Utterance Features (2005)

Nick Webb, Mark Hepple, Yorick Wilks

We present recent work in the area of Dialogue Act (DA) tagging. Identifying the dialogue acts of utterances is recognised as an important step towards understanding the content and nature of what...

Data-Driven Language Understanding for Spoken Language Dialogue (2005)

Nick Webb, Cristian Ursu, Yorick Wilks, Hilda Hardy, Min Wu

We present a natural-language customer service application for a telephone banking call center, developed as part of the AMITIES dialogue project (Automated Multilingual Interaction with Information...

Empirical Determination of Thresholds for Optimal Dialogue Act Classification (2005)

Nick Webb, Mark Hepple, Yorick Wilks

We present recent experiments which build on our work in the area of Dialogue Act (da) tagging.

Advances in Natural Multimodal Dialogue Systems (2005)

Jan Van Kuppevelt, Laila Dybkjær, Laila Dybkjær, Niels Ole Bernsen, Yorick Wilks, Nick Webb, ...

We describe two major dialogue system segments: the first is an analysis module that learns to assign dialogue acts from corpora, but on the basis of limited quantities of data, and up to what seems...

A Retrospective view of Synonymy and Semantic Classification (2005)

Yorick Wilks And, Yorick Wilks, John Tait

this paper we discuss the implications of that assumption of classification as a form of synonymy but here we simply note that, in TC terms, co-row words were features of any given member word, where...

Learning to Harvest Information for the Semantic Web (2004)

Ciravegna, Fabio, Chapman, Sam, Dingli, Alexiei, Wilks, Yorick

In this paper we describe a methodology for harvesting information from large distributed repositories (e.g. large Web sites) with minimum user intervention. The methodology is based on a combination...

Ontologies, Taxonomies, Thesauri: Learning from Texts (2004)

Brewster, Mr. Christopher, Wilks, Prof. Yorick

The use of ontologies as representations of knowledge is widespread but their construction, until recently, has been entirely manual. We argue in this paper for the use of text corpora and automated...

Data Driven Ontology Evaluation (2004)

Brewster, Christopher, Alani, Harith, Dasmahapatra, Srinandan, Wilks, Yorick

The evaluation of ontologies is vital for the growth of the Semantic Web. We consider a number of problems in evaluating a knowledge artifact like an ontology. We propose in this paper that one...

Data Driven Ontology Evaluation (2004)

Brewster, Christopher, Alani, Harith, Dasmahapatra, Srinandan, Wilks, Yorick

The evaluation of ontologies is vital for the growth of the Semantic Web. We consider a number of problems in evaluating a knowledge artifact like an ontology. We propose in this paper that one...

Data Driven Ontology Evaluation (2004)

Brewster, Christopher, Alani, Harith, Dasmahapatra, Srinandan, Wilks, Yorick

The evaluation of ontologies is vital for the growth of the Semantic Web. We consider a number of problems in evaluating a knowledge artifact like an ontology. We propose in this paper that one...

munication,s m Statistics - Theo*'y and Methods (2004)

Nigel Shadbolt, Fabio Ciravegna, John Domingue, Wendy Hall, Enrico Motta, David Robertson, ...

In a celebrated essay on the new electronic media, Marshall McLuhan wrote in 1962: Our private senses are not closed systems but are endlessly translated into each other in that experience which we...

Image-Language Multimodal Corpora: needs, lacunae and an AI synergy for (2004)

Annotation Katerina Pastra, Katerina Pastra, Yorick Wilks

The growing demand for intelligent multimedia systems has led to the development of various multimodal resources and corresponding annotation schemes and processing tools. In this paper, we argue...

Learning to Harvest Information for the Semantic Web (2004)

Fabio Ciravegna, Sam Chapman, Alexiei Dingli, Yorick Wilks

In this paper we describe a methodology for harvesting information from large distributed repositories (e.g. large Web sites) with minimum user intervention. The methodology is based on a combination...

munication,s m Statistics - Theo*'y and Methods (2004)

Nigel Shadbolt, Fabio Ciravegna, John Domingue, Wendy Hall, Enrico Motta, David Robertson, ...

In a celebrated essay on the new electronic media, Marshall McLuhan wrote in 1962: Our private senses are not closed systems but are endlessly translated into each other in that experience which we...

Automatic Report Generation from Ontologies: The MIAKT Approach (2004)

Kalina Bontcheva, Yorick Wilks

This paper presented an approach for automatic generation of reports from domain ontologies encoded in Semantic Web standards like OWL. The paper identifies the challenges that need to be addressed...

Mining Web Sites Using Unsupervised Adaptive Information Extraction (2003)

Ciravegna, Dr. Fabio, Dingli, Mr. Alexeie, Guthrie, Mr. David, Wilks, Prof. Yorick

Adaptive Information Extraction systems (IES) are currently used by some Semantic Web (SW) annotation tools as support to annotation (Handschuh et al., 2002; Vargas-Vera et al., 2002). They are...

P.: Intelligent multimedia indexing and retrieval through multi-source information extraction and merging (2003)

Jan Kuper, Horacio Saggion, Hamish Cunningham, Thierry Declerck, Franciska De Jong, Dennis Reidsma, ...

This paper reports work on automated meta-data creation for multimedia content. The approach results in the generation of a conceptual index of the content which may then be searched via semantic...

NLP for indexing and retrieval of captioned photographs (2003)

Katerina Pastra, Horacio Saggion, Yorick Wilks

We present a text-based approach for the automatic indexing and retrieval of digital photographs taken at crime scenes. Our research prototype, SOCIS, goes beyond keyword-based approaches and methods...

Integrating Information to Bootstrap Information Extraction from Web Sites (2003)

Fabio Ciravegna, Alexiei Dingli, David Guthrie, Yorick Wilks

In this paper we propose a methodology to learn to extract domain-specific information from large repositories (e.g. the Web) with minimum user intervention. Learning is seeded by integrating...

NLP for indexing and retrieval of captioned photographs (2003)

Katerina Pastra, Horacio Saggion, Yorick Wilks, England Uk

We present a text-based approach for the automatic indexing and retrieval of digital photographs taken at crime scenes. Our research prototype, SOCIS, goes beyond keyword-based approaches and methods...

NLP for indexing and retrieval of captioned photographs (2003)

Katerina Pastra, Horacio Saggion, Yorick Wilks

We present a text-based approach for the automatic indexing and retrieval of digital photographs taken at crime scenes. Our research prototype, SOCIS, goes beyond keyword-based approaches and methods...

Mining web sites using adaptive information extraction (2003)

Alexiei Dingli, Fabio Ciravegna, David Guthrie, Yorick Wilks

Adaptive Information Extraction systems (IES) are currently used by some Semantic Web (SW) annotation tools as support to annotation (Handschuh

Intelligent indexing of crime scene photographs (2003)

Katerina Pastra, Horacio Saggion, Yorick Wilks

Information System’s automatic image-indexing prototype goes beyond extracting keywords and syntactic relations from captions. The semantic information it gathers gives investigators an intuitive,...

SOCIS: Scene of Crime Information System - IGR Review Report (2003)

Katerina Pastra, Horacio Saggion, Yorick Wilks

This report reviews the work done by the University of She#eld on SOCIS, Scene of the Crime Information System, under EPSRC grant GR/M89676/01. The work was done in close collaboration with a grant...

Extracting Relational Facts for Indexing and Retrieval of Crime-Scene Photographs (2003)

Katerina Pastra, Horacio Saggion, Yorick Wilks

This paper presents work on text-based photograph indexing and retrieval for crime investigation, an application domain where efficient querying of large crime-scene photograph databases is of...

submitted) ‘Multi-strategy Definition of Annotation Services in Melita’ submitted to International Workshop on Human Language Technology for the Semantic Web and Web Services, held in conjunction with (2003)

Fabio Ciravegna, Alexiei Dingli, Jose Iria, Yorick Wilks

Abstract. The definition of methodologies for automatic ontology-based document annotation is a fundamental step in the Semantic Web vision. In the near future, semantic annotation services could...

L.,”Using Semantic Annotations to Cluster Lexical Relationships (2003)

David Guthrie, Yorick Wilks, Louise Guthrie

automatic derivation of preferences for both adjectives and verbs from the 26 million word semantically annotated corpus produced as part of the workshop. This corpus was enhanced by identifying...

Background and foreground knowledge in dynamic ontology construction (2003)

Christopher Brewster, Fabio Ciravegna, Yorick Wilks

Ontologies have become a key component in the Semantic Web and Knowledge management. One accepted goal is to construct ontologies from a domain specific set of texts. An ontology reflects the...

Integrating Information to Bootstrap Information Extraction from Web Sites (2003)

Fabio Ciravegna, Alexiei Dingli, David Guthrie, Yorick Wilks

In this paper we propose a methodology to learn to extract domain-specific information from large repositories (e.g. the Web) with minimum user intervention. Learning is seeded by integrating...

Background and foreground knowledge in dynamic ontology construction (2003)

Christopher Brewster, Fabio Ciravegna, Yorick Wilks

Ontologies have become a key component in the Semantic Web and Knowledge management. One accepted goal is to construct ontologies from a domain specific set of texts. An ontology reflects the...

P.: Intelligent multimedia indexing and retrieval through multi-source information extraction and merging (2003)

Jan Kuper, Horacio Saggion, Hamish Cunningham, Thierry Declerck, Franciska De Jong, Dennis Reidsma, ...

This paper reports work on automated meta-data creation for multimedia content. The approach results in the generation of a conceptual index of the content which may then be searched via semantic...

User-System Cooperation in Document Annotation based on Information Extraction (2002)

Ciravegna, Dr. Fabio, Dingli, Mr. Alexiei, Petrelli, Dr. Daniella, Wilks, Prof. Yorick

The process of document annotation for the Semantic Web is complex and time consuming, as it requires a great deal of manual annotation. Information extraction from texts (IE) is a technology used by...

User-Centred Onlology Learning for Knowledge Management (2002)

Brewster, Mr. Christopher, Ciravegna, Dr. Fabio, Wilks, Prof. Yorick

Automatic ontology building is a vital issue in many fields where they are currently built manually. This paper presents a user-centred methodology for ontology construction based on the use of...

User-system cooperation in document annotation based on information extraction (2002)

Fabio Ciravegna, Alexiei Dingli, Daniela Petrelli, Yorick Wilks

Abstract. The process of document annotation for the Semantic Web is complex and time consuming, as it requires a great deal of manual annotation. Information extraction from texts (IE) is a...

Extracting Relational Facts for Indexing and Retrieval of Crime-Scene Photographhs (2002)

Katerina Pastra, Horacio Saggion, Yorick Wilks

This paper presents work on text-based photograph indexing and retrieval for crime inves-tigation, an application domain where efficient querying of large crime-scene photograph databases is of...

User-centred ontology learning for knowledge management (2002)

Christopher Brewster, Fabio Ciravegna, Yorick Wilks

Abstract. Automatic ontology building is a vital issue in many fields where they are currently built manually. This paper presents a user-centred methodology for ontology construction based on the...

How feasible is the reuse of grammars for Named Entity Recognition (2002)

Katerina Pastra, Diana Maynard, Oana Hamza, Hamish Cunningham, Yorick Wilks

In this paper, we investigate whether reusing existing grammars for NE recognition instead of creating them from scratch is a viable solution to time constraints in developing grammars. We discuss...

Extracting Relational Facts for Indexing and Retrieval of Crime-Scene Photographhs (2002)

Katerina Pastra, Horacio Saggion, Yorick Wilks

This paper presents work on text-based photograph indexing and retrieval for crime inves-tigation, an application domain where efficient querying of large crime-scene photograph databases is of...

How feasible is the reuse of grammars for Named Entity Recognition (2002)

Katerina Pastra, Diana Maynard, Oana Hamza, Hamish Cunningham, Yorick Wilks

In this paper, we investigate whether reusing existing grammars for NE recognition instead of creating them from scratch is a viable solution to time constraints in developing grammars. We discuss...

Architectural elements of language engineering robustness (2002)

Diana Maynard, Valentin Tablan, Hamish Cunningham, Cristian Ursu, Horacio Saggion, Kalina Bontcheva, ...

We discuss robustness in LE systems from the perspective of engineering, and the predictability of both outputs and construction process that this entails. We present an architectural system that...

Extracting Information for Automatic Indexing of Multimedia Material (2002)

Horacio Saggion, Hamish Cunningham, Diana Maynard, Kalina Bontcheva, Oana Hamza, Christian Ursu, ...

This paper discusses our work on information extraction (IE) from multi-lingual, multi-media, multi-genre Language Resources, in a domain where there are many different event types. This work is...

Timely and Non-Intrusive Active Document Annotation Via Adaptive Information Extraction (2002)

Fabio Ciravegna, Alexiei Dingli, Daniela Petrelli, Yorick Wilks

The process of document annotation for the Semantic Web is complex and time consuming, as it requires a great deal of manual annotation. Information extraction from texts (IE) is a technology used by...

Timely and Non-Intrusive Active Document Annotation via Adaptive Information Extraction (2002)

Fabio Ciravegna, Alexiei Dingli, Daniela Petrelli, Yorick Wilks

The process of document annotation for the Semantic Web is complex and time consuming, as it requires a great deal of manual annotation. Information extraction from texts (IE) is a technology used by...

User-System Cooperation in Document Annotation Based on Information Extraction (2002)

Fabio Ciravegna, Alexiei Dingli, Daniela Petrelli, Yorick Wilks

The process of document annotation for the Semantic Web is complex and time consuming, as it requires a great deal of manual annotation. Information extraction from texts (IE) is a technology used by...

Ontotherapy: or, how to stop worrying about what there is (2002)

Yorick Wilks

The paper argues that Guarino is right that ontologies are different from thesauri and similar objects, but not in the ways he believes: they are distinguished from essentially linguistic objects...

User-system cooperation in document annotation based on information extraction (2002)

Fabio Ciravegna, Alexiei Dingli, Daniela Petrelli, Yorick Wilks

Abstract. The process of document annotation for the Semantic Web is complex and time consuming, as it requires a great deal of manual annotation. Information extraction from texts (IE) is a...

What is Lexical Tuning? (2002)

Wilks, Yorick, Catizone, Roberta

The paper contrasts three approaches to the extension of lexical sense: what we shall call, respectively, lexical tuning; a second based on lexical closeness and relaxation; and a third known as...

Using HLT for Acquiring, Retrieving and Publishing Knowledge in AKT: Position Paper (2001)

Boncheva, Kalina, Brewster, Christopher, Ciravegna, Fabio, Cunningham, Hamish, Guthrie, Louise, Gaizauskas, Robert, ...

AKT is a major research project applying a variety of technologies to knowledge management. Knowledge is a dynamic, ubiquitous resource, which is to be found equally in an expert's head, under...

Using HLT for Acquiring, Retrieving and Publishing Knowledge in AKT: Position Paper (2001)

Bontcheva, Dr. Kalina, Brewster, Mr. Christopher, Ciravegna, Dr. Fabio, Cunningham, Dr. Hamish, Guthrie, Dr. Louise, Gaizauskas, Dr. Rob, ...

AKT is a major research project applying a variety of technologies to knowledge management. Knowledge is a dynamic, ubiquitous resource, which is to be found equally in an expert's head, under...

Knowledge Acquisition for Knowledge Management: Position Paper (2001)

Brewster, Mr Christopher, Ciravegna, Dr. Fabio, Wilks, Prof. Yorick

Knowledge is only of value when it can be used effectively and efficiently. The management of knowledge is a key element in extracting its value. In this position paper we have outlined how we are...

Using HLT for Acquiring, Retrieving and Publishing Knowledge (2001)

Kalina Bontcheva, Christopher Brewster, Fabio Ciravegna, Hamish Cunningham, Louise Guthrie, Robert Gaizauskas, ...

AKT is a major research project applying a variety of technologies to knowledge management. Knowledge is a dynamic, ubiquitous resource, which is to be found equally in an expert's head, under...

The meter corpus: A corpus for analysing journalistic text reuse (2001)

Robert Gaizauskas, Jonathan Foster, Yorick Wilks, John Arundel, Paul Clough, Scott Piao

As a part of the METER (MEasuring TExt Reuse) project we have built a new type of comparable corpus consisting of annotated examples of related newspaper texts. Texts in the corpus were manually...

Named Entity Recognition from Diverse Text Types (2001)

Diana Maynard, Valentin Tablan, Cristian Ursu, Hamish Cunningham, Yorick Wilks

Current research in Information Extraction tends to be focused on application-specific systems tailored to a particular domain. The Muse system is a multi-purpose Named Entity recognition system...

Dealing with dependencies between content planning and surface realisation in a pipeline generation architecture (2001)

Kalina Bontcheva, Yorick Wilks

The majority of existing language generation systems have a pipeline architecture which offers efficient sequential execution of modules, but does not allow decisions about text content to be revised...

What's in a symbol: ontology, representation and language (2001)

Sergei Nirenburg, Yorick Wilks

This paper is in a form unconventional in modern journals but traditional for the discussion of foundational questions: a dialogue. It is a form that makes it possible to contrast two deeply held but...

The Interaction of Knowledge Sources in Word Sense Disambiguation (2001)

Mark Stevenson, Yorick Wilks

LOCATION N (= Non-movable solid) DATE T (= Abstract) TIME T (= Abstract) MONEY T (= Abstract) PERCENT T (= Abstract) UNKNOWN Z (= No semantic restriction) Any use of preferences for sense selection...

The interaction of knowledge sources in word sense disambiguation (2001)

Mark Stevenson, Yorick Wilks

Word sense disambiguation (WSD) is a computational linguistics task likely to benefit from the tradition of combining different knowledge sources in artificial intelligence research. An important...

Uniform Language Resource Access and Distribution (2000)

Hamish Cunningham, Wim Peters, Clare Mccauley, Kalina Bontcheva, Yorick Wilks

The reuseability and accessibility of lexical and linguistic resources often requires substantial programming overhead and detailed knowledge of the structure and nature of resource-specific...

Experience of using GATE for NLP R&D (2000)

Hamish Cunningham, Diana Maynard, Kalina Bontcheva, Valentin Tablan, Yorick Wilks

GATE, a General Architecture for Text Engineering, aims to provide a software infrastructure for researchers and developers working in NLP. GATE has now been widely available for four years. In this...

Software Infrastructure for Language Resources: a Taxonomy of Previous Work and a Requirements Analysis (2000)

Hamish Cunningham, Kalina Bontcheva, Valentin Tablan, Yorick Wilks

This paper presents a taxonomy of previous work on infrastructures, architectures and development environments for representing and processing Language Resources (LRs), corpora, and annotations. This...

Software Infrastructure for Language Resources: a Taxonomy of Previous Work and a Requirements Analysis. (2000)

Hamish Cunningham, Kalina Bontcheva, Valentin Tablan, Yorick Wilks

This paper presents a taxonomy of previous work on infrastructures, architectures and development environments for representing and processing Language Resources (LRs), corpora, and annotations. This...

Human-Computer Conversation (2000)

Yorick Wilks, Roberta Catizone

The article surveys a little of the history of the technology, sets out the main current theoretical approaches in brief, and discusses the on-going opposition between theoretical and empirical...

IR and AI: traditions of representation and anti-representation in information processing (2000)

Yorick Wilks

. The paper is concerned with the role of conceptual representations in access to information, as for example, from the World Wide Web. It contrasts two quite different traditions for doing this:...

Automatic Semantic Annotation using Unsupervised Information Extraction and Integration (2000)

Alexiei Dingli, Fabio Ciravegna, Yorick Wilks

In this paper we propose a methodology to learn to automatically annotate domain-specific information from large repositories (e.g. Web sites) with minimum user intervention. The methodology is based...

IR and AI: traditions of representation and anti-representation in information processing (2000)

Yorick Wilks

this paper, I am taking IE as a paradigm, naive though it still is, of an information processing technology separate from IR; formally separate, at least, in that one returns documents or document...

Human-Computer Conversation (1999)

Wilks, Yorick, Catizone, Roberta

The article surveys a little of the history of the technology, sets out the main current theoretical approaches in brief, and discusses the on-going opposition between theoretical and empirical...

An ascription-based approach to speech acts (1999)

Lee, Mark, Wilks, Yorick

The two principal areas of natural language processing research in pragmatics are belief modelling and speech act processing. Belief modelling is the development of techniques to represent the mental...

The "Fodor"-FODOR fallacy bites back (1999)

Wilks, Yorick

The paper argues that Fodor and Lepore are misguided in their attack on Pustejovsky's Generative Lexicon, largely because their argument rests on a traditional, but implausible and discredited, view...

Is Word Sense Disambiguation just one more NLP task? (1999)

Wilks, Yorick

This paper compares the tasks of part-of-speech (POS) tagging and word-sense-tagging or disambiguation (WSD), and argues that the tasks are not related by fineness of grain or anything like that, but...

Compacting the Penn Treebank Grammar (1999)

Krotov, Alexander, Hepple, Mark, Gaizauskas, Robert, Wilks, Yorick

Treebanks, such as the Penn Treebank (PTB), offer a simple approach to obtaining a broad coverage grammar: one can simply read the grammar off the parse trees in the treebank. While such a grammar is...

Generation of adaptive (hyper)text explanations with an agent model (1999)

Kalina Bontcheva, Yorick Wilks

A number of generation systems have chosen hypertext as a target media and study ways of adapting its content and links to the presentation context and the particular user. Our experience with...

LaSIE jumps the GATE (1999)

Yorick Wilks, Robert Gaizauskas, Kevin Humphreys, Hamish Cunningham

The benefits of the effective creation of Information Extraction (IE) in the last ten years, driven by the ARPA TIPSTER programme and the associated MUC evaluations, have been enormous, but it must...

Can we make Information Extraction more adaptive? (1999)

Yorick Wilks, Roberta Catizone

It seems widely agreed that IE (Information Extraction) is now a tested language technology that has reached precision+recall values that put it in about the same position as Information Retrieval...

What's in a Symbol: Ontology, Representation and Language (1999)

Sergei Nirenburg, Yorick Wilks

This paper is in a form unconventional in modern journals but traditional for the discussion of foundational questions: a dialogue. It is a form that makes it possible to contrast two deeply held but...

Unsupervised Learning of Word Boundary with Description Length Gain (1999)

Chunyu Kit, Yorick Wilks

This paper presents an unsupervised approach to lexical acquisition with the goodness measure description length gain (DLG) formulated following classic information theory within the minimum...

Experience with a Language Engineering Architecture: Three Years of GATE (1999)

Hamish Cunningham, Robert Gaizauskas, Kevin Humphreys, Yorick Wilks

GATE, the General Architecture for Text Engineering, aims to provide a software infrastructure for researchers and developers working in the area of natural language processing. A version of GATE has...

Combining Weak Knowledge Sources for Sense Disambiguation (1999)

Mark Stevenson, Yorick Wilks

There has been a tradition of combining different knowledge sources in Artificial Intelligence research. We apply this methodology to word sense disambiguation (WSD), a long-standing problem in...

The Goals of Linguistic Theory Revisited. (1998)

Schank,Roger C., Wilks,Yorick

An examination is made of the original goals of generative linguistic theory. It is suggested that these goals were well defined but misguided with respect to their avoidance of the problem of...

Active Knowledge Structures for Natural Language Processing. (1998)

Wilks, Yorick, Coombs, Michael, Hartley, Roger T., Qiu, Dihong

ViewGen is a dynamic beliefs management system. It generates multiple belief environments from different points of view. The basic inference mechanism in ViewGen is default reasoning That is, unless...

Word Sense Disambiguation using Optimised Combinations of Knowledge Sources (1998)

Wilks, Yorick, Stevenson, Mark

Word sense disambiguation algorithms, with few exceptions, have made use of only one lexical knowledge source. We describe a system which performs unrestricted word sense disambiguation (on all...

Eliminating deceptions and mistaken belief to infer conversational implicature (1998)

Lee, Mark, Wilks, Yorick

Conversational implicatures are usually described as being licensed by the disobeying or flouting of some principle by the speaker in cooperative dialogue. However, such work has failed to...

Implementing a Sense Tagger in General Architecture for Text Engineering (1998)

Hamish Cunningham, Mark Stevenson, Yorick Wilks

We describe two systems: GATE (General Architecture for Text Engineering), an architecture to aid in the production and delivery of language engineering systems which significantly reduces...

Is Word-sense disambiguation just one more NLP task (1998)

Yorick Wilks

The paper compares the tasks of part-of-speech (POS) tagging and word-sense-tagging or disambiguation (WSD), and argues that the tasks are not related by fineness of grain or anything like that, but...

Information Extraction: Beyond Document Retrieval (1998)

Y. Wilks, Robert Gaizauskas, Yorick Wilks

In this paper we give a synoptic view of the growth text processing technology of information extraction (IE) whose function is to extract information about a pre-specified set of entities, relations...

An empirical approach to Lexical Tuning (1998)

Roberto Basili, Roberta Catizone, Maria Teresa Pazienza, Mark Stevenson, Paola Velardi, Michele Vindigni, ...

. NLP systems crucially depend on the knowledge structures devoted to describing and representing word senses. Although automatic Word Sense Disambiguation (WSD) is now an established task within...

Implementing a Sense Tagger in a General Architecture for Text Engineering (1998)

Hamish Cunningham, Mark Stevenson, Yorick Wilks

We describe two systems: GATE (General Architecture for Text Engineering), an architecture to aid in the production and delivery of language engineering systems which significantly reduces...

The Virtual Corpus Approach to Deriving Ngram Statistics from Large Scale Corpora (1998)

Chunyu Kit, Yorick Wilks

This paper reports our implementation of the Virtual Corpus approach to deriving ngram statistics for ngrams of any length from large-scale corpora based on the suffix array data structure. In order...

Sense Tagging and Language Engineering (1998)

Mark Stevenson, Hamish Cunningham, Yorick Wilks

. Language engineering is a new, practical, branch of NLP and Computational Linguistics. We describe two language engineering systems: GATE (General Architecture for Text Engineering), an...

Word Sense Disambiguation using Optimised Combinations of Knowledge Sources (1998)

Yorick Wilks, Mark Stevenson

Word sense disambiguation algorithms, with few exceptions, have made use of only one lexical knowledge source. We describe a system which performs word sense disambiguation on all content words in...

Information Extraction: Beyond Document Retrieval (1998)

Robert Gaizauskas, Yorick Wilks

In this paper we give a synoptic view of the growth text processing technology of information extraction (IE) whose function is to extract information about a pre-specified set of entities, relations...

Language Processing and the Thesaurus (1998)

Yorick Wilks

The purpose of this paper is to argue that two different features of a classic thesaurus like Roget (an abstract universal classification and the provision of synonym sets) can be relevant to natural...

The Virtual Corpus approach to deriving n-gram statistics from large scale corpora (1998)

Chunyu Kit, Yorick Wilks

This paper reports our implementation of the Virtual Corpus approach to deriving ngram statistics for ngrams of any length from large-scale corpora based on the suffix array data structure. In order...

Sense Tagging: Semantic Tagging with a Lexicon (1997)

Wilks, Yorick, Stevenson, Mark

Sense tagging, the automatic assignment of the appropriate sense from some lexicon to each of the words in a text, is a specialised instance of the general problem of semantic tagging by category or...

Software Infrastructure for Natural Language Processing (1997)

Cunningham, Hamish, Humphreys, Kevin, Gaizauskas, Robert, Wilks, Yorick

We classify and review current approaches to software infrastructure for research, development and delivery of NLP systems. The task is motivated by a discussion of current trends in the field of NLP...

Using a language independent domain model for multilingual information extraction (1997)

Saliha Azzam, Kevin Humphreys, Robert Gaizauskas, Yorick Wilks

The volume of electronic text in different languages, particularly on the World Wide Web, is growing significantly, and the problem of users who are restricted in the number of languages they read...

Sense tagging: Semantic tagging with a lexicon (1997)

Yorick Wilks, Mark Stevenson

Sense tagging, the automatic assignment of the appropriate sense from some lexicon to each of the words in a text, is a specialised instance of the general problem of semantic tagging by category or...

Combining Language Generation and Belief Modelling into a Flexible Hypertext System (1997)

Kalina Bontcheva, Yorick Wilks

this paper we will outline how current dynamic hypertext systems maintain flexibility by assessing the variations in content and linking strategies as supported by the applied nlg techniques and user...

Compacting the Penn Treebank Grammar (1997)

Alexander Krotov, Robert Gaizauskas, Mark Hepple, Yorick Wilks

Treebanks, such as the Penn Treebank (PTB), afford a simple approach to obtaining a broad coverage grammar: simply read the grammar off the parse trees in the treebank. While such a grammar is easy...

Combining Independent Knowledge Sources for Word Sense Disambiguation (1997)

Yorick Wilks, Mark Stevenson

Sense tagging, the automatic assignment of the appropriate sense from some lexicon to each of the words in a text, is a specialised instance of the general problem of word sense disambiguation. We...

Senses and Texts (1997)

Yorick Wilks

This paper addresses the question of whether it is possible to sense-tag systematically, and on a large scale, and how we should assess progress so far. That is to say, how to attach each occurrence...

Senses and Texts (1997)

Yorick Wilks

This paper addresses the question of whether it is possible to sense-tag systematically, and on a large scale, and how we should assess progress so far. That is to say, how to attach each occurrence...

Information Extraction as a core language technology: What is IE? (1997)

Yorick Wilks

this paper, between traditional IR and the newer IE , is not totally clear everywhere but can itself become a question of degree. Suppose parsing systems that produce syntactic and logical...

Software Infrastructure for Natural Language Processing (1997)

Hamish Cunningham, Kevin Humphreys, Robert Gaizauskas, Yorick Wilks

We classify and review current approaches to software infrastructure for research, development and delivery of NLP systems. The task is motivated by a discussion of current trends in the field of NLP...

The Grammar of Sense: Using part-of-speech tags as a first step in semantic disambiguation (1997)

Yorick Wilks, Mark Stevenson

This paper describes two experiments: one exploring the amount of information relevant to sense disambiguation contained in the part-of-speech field of entries in a Machine Readable Dictionary (MRD);...

Extracting Case relations from Corpora (1997)

Roberto Basili, Maria-teresa Pazienza, Paola Velardi, Roberta Catizone, Robin Collier, Mark Stevenson, ...

Description of a system for the automatic acquisition of verbal case frames from corpora. The key target is to acquire domain-specific relations rather than the standard relationships found in...

Compacting the Penn Treebank Grammar (1997)

Alexander Krotov, Er Krotov, Robert Gaizauskas, Yorick Wilks

Treebanks, such as the Penn Treebank (PTB), offer a simple approach to obtaining a broad coverage grammar: one can simply read the grammar off the parse trees in the treebank. While such a grammar is...

Sense Tagging: Semantic Tagging with a Lexicon (1997)

Yorick Wilks, Mark Stevenson

Sense tagging, the automatic assignment of the appropriate sense from some lexicon to each of the words in a text, is a specialised instance of the general problem of semantic tagging by category or...

Sense Tagging: Semantic Tagging with a Lexicon (1997)

Yorick Wilks, Mark Stevenson

Sense tagging, the automatic assignment of the appropriate sense from some lexicon to each of the words in a text, is a specialised instance of the general problem of semantic tagging by category or...

The Grammar of Sense: Is word-sense tagging much more than part-of-speech tagging? (1996)

Wilks, Yorick, Stevenson, Mark

This squib claims that Large-scale Automatic Sense Tagging of text (LAST) can be done at a high-level of accuracy and with far less complexity and computational effort than has been believed until...

New Methods, Current Trends and Software Infrastructure for NLP (1996)

Cunningham, Hamish, Wilks, Yorick, Gaizauskas, Robert J.

The increasing use of `new methods' in NLP, which the NeMLaP conference series exemplifies, occurs in the context of a wider shift in the nature and concerns of the discipline. This paper begins with...

A General Architecture for Language Engineering (GATE) - a new approach to Language Engineering R&D (1996)

Cunningham, Hamish, Gaizauskas, Robert J., Wilks, Yorick

This report argues for the provision of a common software infrastructure for NLP systems. Current trends in Language Engineering research are reviewed as motivation for this infrastructure, and...

TIPSTER-Compatible Projects at Sheffield (1996)

Hamish Cunningham, Kevin Humphreys, Robert Gaizauskas, Yorick Wilks

more appropriately described by the term Language Engineering than the well-established labels of Nat-ural Language Processing or Computational Linguis-tics. This reflects an increased focus on...

GATE: an environment to support research and development in natural language engineering (1996)

Robert Gaizauskas, Hamish Cunningham, Yorick Wilks, Peter Rodgers, Kevin Humphreys

We describe a software environment to support research and development in natural language (NL) engineering. This environment-- GATE (General Architecture for Text Engineering)-- aims to advance...

Evaluation of an Algorithm for the Recognition and Classification of Proper Names (1996)

Takahiro Wakao, Robert Gaizauskas, Yorick Wilks

We describe an information extraction system in which four classes of naming expressions -- organisation, person, location and time names -- are recognised and classified with nearly 92% combined...

Lexicons in the MikroKosmos Project (1996)

Sergei Nirenburg, Stephen Beale, Kavi Mahesh, Boyan Onyshkevych, Victor Raskin, Victor Raskin Yy, ...

Introduction Our approach to the lexicon has been driven by both theoretical and practical concerns. From a theoretical viewpoint, we are interested in capturing the core meanings of texts. We...

New Methods, Current Trends and Software Infrastructure for NLP (1996)

Hamish Cunningham, Yorick Wilks, Robert J. Gaizauskas

. The increasing use of `new methods' in NLP, which this conference series exemplifies, occurs in the context of a wider shift in the nature and concerns of the discipline. This paper begins...

Software Infrastructure for Language Engineering (1996)

Hamish Cunningham, Yorick Wilks, Robert J. Gaizauskas

This paper describes a freely-available system called GATE [Cunningham, Gaizauskas, Wilks 1995] -- a General Architecture for Text Engineering -- which integrates much of this work. GATE is an

GATE: An Environment to Support Research and Development in Natural Language Engineering (1996)

Robert Gaizauskas, Hamish Cunningham, Yorick Wilks, Peter Rodgers, Kevin Humphreys

We describe a software environment to support research and development in natural language (NL) engineering. This environment -- GATE (General Architecture for Text Engineering) -- aims to advance...

GATE - a General Architecture for Text Engineering (1996)

Hamish Cunningham, Yorick Wilks, Robert J. Gaizauskas

Much progress has been made in the provision of reusable data resources for Natural Language Engineering, such as grammars, lexicons, thesauruses. Although a number of projects have addressed the...

Methods for Lexical Items Modification/Creation (1996)

The ECRAN Consortium (ECRAN), Yorick Wilks, Mark Stevenson, Rob Collier, Paola Velardi

Lexicon tuning is the process by which lexical entries in a general purpose lexicon are adapted to a given language domain. Lexicon tuning is performed by increasing-decreasing the expectation of the...

Tipster-Compatible Projects At Sheffield (1996)

Hamish Cunningham, Kevin Humphreys, Robert Gaizauskas, Yorick Wilks

this paper at the April 1996 TIPSTER workshop, and for extensive comments during the preparation of this paper. References

Information Extraction (1996)

Jim Cowie And, Jim Cowie, Yorick Wilks

this article. This quest for some kind of standardization is now extending to specifying the kind of information (patterns basically) which drive IE systems. More formally the idea is to have a...

GATE: An Environment to Support Research and Development in Natural Language Engineering (1996)

Robert Gaizauskas, Hamish Cunningham, Yorick Wilks, Peter Rodgers, Kevin Humphreys

We describe a software environment to support research and development in natural language (NL) engineering. This environment -- GATE (General Architecture for Text Engineering) -- aims to advance...

Evaluation of an algorithm for the recognition and classification of proper names (1996)

Takahiro Wakao, Robert Gaizauskas, Yorick Wilks

We describe an information extraction system in which four classes of naming expressions organisation, person, location and tinm names are recognised and classified with nearly 92 % combined...

Arthur Frederick Parker-Rhodes: a memoir. (1995)

Yorick Wilks

: Parker-Rhodes was an original thinker in information retrieval, quantum mechanics and computational linguistics. The paper describes the basic ideas of his work in the last area for an audience...

Acquiring a Stochastic Context-Free Grammar from the Penn Treebank (1994)

Alexander Krotov, Robert Gaizauskas, Yorick Wilks

In this paper we present preliminary results of investigating the structure of the Penn Treebank and how these results can be used in probabilistic parsing of English. Penn Treebank is a corpus of...

Text Processing Using Multilingual Resources at the Computing Research Laboratory (1994)

COWIE, JIM, DUNNING, TED, GUTHRIE, LOUISE, WILKS, YORICK

The paper surveys five aspects of the work on multilingual text processing at the Computing Research Laboratory, New Mexico State University: a large-scale information extraction (IE) program;...

Your Metaphor or Mine: Belief Ascription and Metaphor Interpretation (1991)

Yorick Wilks, John Barnden, Jin Wang

ViewGen, an algorithm and program for belief ascription, represents the beliefs of agents as explicit, partitioned proposition-sets known as environments. A way of extending View-Gen to the...

Subject-Dependent Co-occurrence and Word Sense Disambiguation (1991)

Joe A. Guthrie, Louise Guthrie, Yorick Wilks, Homa Aidinejad

We describe a method for obtaining subject-dependent word sets relative to some (subjecO domain. Using the subject classifications given in the machine-readable ver-sion of Longman's Dictionary...

Your Metaphor or Mine: Belief Ascription and Metaphor Interpretation (1991)

Yorick Wilks, John Barnden, Jin Wang

ViewGen, an algorithm and program for belief ascription, represents the beliefs of agents as explicit, partitioned proposition-sets known as environments. A way of extending View-Gen to the...

Belief ascription and model generative reasoning: joining two paradigms to a robust parser of messages (1990)

Yorick Wilks, Roger Hartley

This paper discusses the extension of ViewGen, a program for belief ascription, to the area of inten-sional object identification with applications to battle environments, and its combination in a...

Belief ascription and model generative reasoning: joining two paradigms to a robust parser of messages (1990)

Yorick Wilks, Roger Hartley

This paper discusses the extension of ViewGen, a program for belief ascription, to the area of intensional object identification with applications to battle environments, and its combination in a...

Uniform Language Resource Access and Distribution

Hamish Cunningham Wim, Wim Peters, Clare Mccauley, Kalina Bontcheva, Yorick Wilks

The reuseability and accessibility of lexical and linguistic resources often requires substantial programming overhead and detailed knowledge of the structure and nature of resource-specific...

An ascription-based approach to Speech Acts

Mark Lee, Yorick Wilks

: The two principal areas of natural language processing research in pragmatics are belief modelling and speech act processing. Belief modelling is the development of techniques to represent the...

An ascription-based approach to Speech Acts

Mark Lee, Yorick Wilks

: The two principal areas of natural language processing research in pragmatics are belief modelling and speech act processing. Belief modelling is the development of techniques to represent the...