Office : Room E114 Telephone : +44 1707 284266 Fax : +44 1707 284303
e-mail : C.M.Lyon@herts.ac.uk
Postal Address : Science and Technology Research Institute
University of Hertfordshire
Hatfield, Herts.
AL10 9AB, UK
Areas of Research on Natural Language
Early cognitive developments in humans and their analogs in Artificial Intelligence. This work is conducted within the EU Integrated Project ITalk: "Integration and Transfer of Action and Language in Robots" funded by the European Commission under contract number FP7-214668.
The evolution of linguistic communication. This includes investigating the emergence of grammar in human language, using Information Theory techniques to find methods of coding language that make communication more efficient. See an overview of Emergence of Communication and Language
Development of Ferret software system, for detection of similar text in large document collections, and the display of similar passages side by side. For link to executable system go to Plagiarism Detection Group. An Introduction to the Ferret Copy Detector here
Transfer of language processing techniques between English and Chinese, and their extension. This has primarily been undertaken by Dr JunPeng Bao, Royal Society International Fellow at the University of Hertfordshire from Xi'an Jiaotong University from April 2006 to April 2007.
Using the pattern matching powers of neural networks to detect syntactic patterns in language. The prototype ALPINE neural parser will find the subject,and head of the subject, of each sentence.
Lecture capture: displaying the spoken word converted to text in real time,
primarily for hearing impaired students.
Development of real time subtitles for live TV programmes, using speech recognition
technology. Now in use for BBC2
sports programmes.
Publications
Publications include the following, most of which can be downloaded:
Caroline Lyon, Yo Sato, Joe Saunders and Chrystopher Nehaniv "What is Needed for a Robot to Acquire Grammar? Some Underlying Primitive Mechanisms for the Synthesis of Linguistic Ability", IEEE Transactions on Autonomous Mental Development, in press, here
Caroline Lyon and Joe Saunders "Investigating the basis for conversation between human and robot", EpiRob '09 conference, Venice, November 2009 here and poster here
Joe Saunders, Caroline Lyon, Chrystopher Nehaniv, Kerstin Dautenhahn and Frank Forster "A Constructivist Approach to Robot Language Learning via Simulated Babbling and Holophrase Extraction" IEEE ALIFE Conference 2009 here
Caroline Lyon and Chrystopher L. Nehaniv "Developing agents that can speak with humans: pointers from the evolution of language" Technical Report 479, School of Computer Science, University of Hertfordshire, July 2008. here
Caroline Lyon, Chrystopher L. Nehaniv and Angelo Cangelosi, Editors, "Emergence of Communication and Language", published Springer, 2007. Web page here ISBN 1-84628-491-0
Caroline Lyon "The incremental emergence of grammar: early stages in the process" Workshop on Machine Learning and Cognition in Language Acquisition, June 2007. here
JunPeng Bao, Caroline Lyon, Peter Lane, Wei Ji, James Malcolm "Comparing Different Methods to Detect Text Similarity" Technical Report 461, Science and Technology Research Institute, University of Hertfordshire, May 2007.here
JunPeng Bao, Caroline Lyon and Peter Lane. "A Text Annotation Method Based on Semantic Sequences", in Proceedings of the Seventh International Workshop on Computational Semantics, Jan 2007.
JunPeng Bao, Caroline Lyon, Peter Lane "Copy detection in Chinese documents using Ferret" Language Resources and Evaluation, Dec 2006, Vol 40, Numbers 3-4, p357-365. here
JunPeng Bao, Caroline Lyon, Peter Lane, Wei Ji, James Malcolm "Copy detection in Chinese documents using the Ferret: a report on experiments" Technical Report 456, School of Computer Science, University of Hertfordshire, October 2006. here
Caroline Lyon, Ruth Barrett and James Malcolm "Plagiarism is Easy, but Also Easy to Detect" Plagiary Volume 1, March 2006 here
Caroline Lyon, Chrystopher Nehaniv and Bob Dickerson "Entropy Indicators for Investigating Early Language Processes" AISB'05 Conference, April 2005 here
Caroline Lyon, Ruth Barrett and James Malcolm "A theoretical basis to the automated detection of copying between texts, and its practical implementation in the Ferret plagiarism and collusion detector", Plagiarism: Prevention, Practice and Policies Conference, June 2004, here
Ruth Barrett, Anna Cox, James Malcolm and Caroline Lyon "Plagiarism prevention is discipline specific: a view from Computer Science", Plagiarism: Prevention, Practice and Policies Conference, June 2004
Caroline Lyon, Chrystopher Nehaniv, Jean Baillie, Sandra Warren " Evolutionary fitness, homophony and disambiguation through sequential processes", 1st International Workshop on Emergence and Evolution of Linguistic Communication, Kanazawa, May 2004, here
Andrew Lambourne, Jill Hewitt, Caroline Lyon "Speech-Based Real-Time Subtitling Services" International Journal of Speech Technology. Vol 4, p251-349, 2004 here
Caroline Lyon, Bob Dickerson, Chrystopher Nehaniv, "The segmentation of speech and its implications for the emergence of language structure", Evolution of Communication, Vol 4, 2, 2003. here
"Experiments in Electronic Plagiarism Detection", Caroline Lyon, Ruth Barrett and James Malcolm, TR 388, School of Computer Science, University of Hertfordshire, August 2003. here
"Speech Based Subtitles for Live Performance", J Hewitt, C Lyon, R Ahmed, A Lambourne, HCI International Conference 2003.
"Incremental retrieval of documents relevant to a topic" – C Lyon, J Malcolm, R Dickerson, Proceedings of TREC 2002 (Text Retrieval Competition).
Caroline Lyon and James Malcolm "Experience of Plagiarism Detection and Prevention in Higher Education" Proceedings of the World Congress on Networked Learning in a Global Environment: Challenges and Solutions for Virtual Education, Berlin May 2002.
Caroline Lyon "Evolution of Language Structure: Survival of the fittest in a statistical environment" Talk at 4th International Conference on the Evolution of Language, Harvard, March 2002, here
Caroline Lyon, James Malcolm and Bob Dickerson,"Detecting short passages of similar text in large document collections" Proc. of Conference on Empirical Methods in Natural Language Processing,June 2001 here
C Lyon and R Dickerson, "Exploiting statistical characteristics of word sequences for the efficient coding of speech", Proc. of NLPRS'99, Beijing, November 1999 here
C Lyon, "Automated Language Processing with Neural Networks: the ALPINE Partial Parser", Proc. of First Workshop on Natural Language Processing and Neural Networks, NLPRS'99, Beijing, November 1999. here
C Lyon and J Hewitt, "The Value of Minimal Prosodic Information in Spoken Language Corpora", ACL-COLING Conference, Workshop on Partially Automated Techniques for Transcribing Naturally Occurring, Continuous Speech, 1998. here
C Lyon and R Frank, "Using Single Layer Networks for discrete, sequential data: an example from natural language processing", Neural Computing and Applications, 1997, 5 (4). here
C Lyon and R Dickerson Extended version of paper for "Reducing the Complexity of Parsing by a Method of Decomposition" International Workshop on Parsing Technology, Sept. 1997. here
C Lyon and S Brown "Evaluating Parsing Schemes with Entropy Indicators", MOL5, 5th Meeting on the Mathematics of Language, Aug. 1997. here
C Lyon and R Frank, "Neural Network Design for a Natural Language Parser", International Conference on Artificial Neural Networks, ICANN 1995. here.
C Lyon and R Dickerson, "A fast partial parse of natural language sentences using a connectionist method", 7th Conference of the European Chapter of the ACL 1995. here
C Lyon, "The representation of natural language to enable neural networks to detect syntactic structures", PhD thesis, 1994. here