Kallirroi Georgila

Address

Dr. Kallirroi Georgila
School of Informatics
University of Edinburgh
2 Buccleuch Place
Edinburgh EH8 9LW
United Kingdom

email: kgeorgil@inf.ed.ac.uk
tel: +44 131 650 8286
fax: +44 131 650 4587

Bio

Kallirroi Georgila is a Research Fellow at the Human Communication Research Centre and the Institute for Communicating and Collaborative Systems of the School of Informatics at the University of Edinburgh since March 2004, working on the TALK project. She was born in Greece, and graduated in 1993 from the Department of Electrical and Computer Engineering of the University of Patras. From 1993 to 2003 she worked as a researcher and software engineer for Knowledge S.A. (now SingularLogic), a Greek software company specialising in spoken dialogue systems. In 1996 she joined, as a PhD student and researcher, the Artificial Intelligence Group of the Wire Communications Laboratory in the above department. Her PhD thesis on "Language modelling for spoken dialogue systems" was completed in November 2002. Her research interests include user modelling, dialogue modelling, multimodal dialogue systems, dialogue annotations, speech processing, language modelling, natural language generation, and speech and language corpora. She has worked on several European and commercial projects related to speech, language, and dialogue processing.

Current/Recent Research Projects

MATCH Project: Build a corpus of dialogues collected using a Wizard of Oz environment. The participants are both older and young persons. The experiment has been carefully designed to investigate how spoken dialogue systems can adapt to a wide range of older people's cognitive ability.

TALK Project: Build a multimodal dialogue system in the tourist information (TownInfo) domain that can either follow a fixed dialogue strategy or a dialogue strategy learnt by using Reinforcement Learning and user simulations.

Automatic Annotation of Context and Speech Acts for the COMMUNICATOR Dialogue Corpora

The automatic annotation of the COMMUNICATOR (2000 and 2001) corpora as a sequence of Information States is described in Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations (Georgila K., Lemon O., and Henderson J. - DIALOR 2005). The purposes of this annotation are to generate corpora for reinforcement learning of dialogue policies, for building user simulations, for evaluating different dialogue strategies against a baseline, and for training models for context-sensitive interpretation and context-sensitive speech recognition. The automatic annotation system parses system and user utterances into speech acts and builds up sequences of "Information State Update" (ISU) representations of dialogue context using the DIPPER ISU dialogue manager. The annotated corpora will be made publicly available after the end of the TALK project. An example of a completely annotated dialogue is available here both in XML and text formats. The associated document type definition (DTD) is also available here.

Publications

Georgila K., Lemon O., Henderson J., and Moore J.D. Automatic Annotation of Context and Speech Acts for Dialogue Corpora. Journal of Natural Language Engineering, Cambridge University Press, (to appear).

Wolters M., Georgila K., MacPherson S., and Moore J.D. Being Old Doesn't Mean Acting Old: How Older Users Interact with Spoken Dialogue Systems. ACM Transactions on Accessible Computing, Special Issue on Aging, (to appear).

Wolters M., Georgila K., Moore J.D., Logie R., MacPherson S., and Watson M. Reducing Working Memory Load in Spoken Dialogues: Do We Have to Limit the Number of Options? Interacting with Computers, Elsevier, (to appear).

Henderson J., Lemon O., and Georgila K. Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Datasets. Computational Linguistics, MIT Press, 34(4):487-511, 2008.

Georgila K., Sgarbas K., Tsopanoglou A., Fakotakis N., and Kokkinakis G. A Speech-based Human-Computer Interaction System for Automating Directory Assistance Services. International Journal of Speech Technology, Special Issue on Speech and Human Computer Interaction, Kluwer Academic Publishers, Vol. 6, No. 2, pp. 145-159, April 2003.

Georgila K., Fakotakis N., and Kokkinakis G. Large Vocabulary Search Space Reduction Employing Directed Acyclic Word Graphs and Phonological Rules. International Journal of Speech Technology, Kluwer Academic Publishers, Vol. 5, No. 4, pp. 355-370, November 2002.

Georgila K., Fakotakis N., and Kokkinakis G. Stochastic Language Modelling for Recognition and Generation in Dialogue Systems. TAL (Traitement automatique des langues) journal, Vol. 43(3), pp. 129-154, 2002.

Vipperla R. Wolters M., Georgila K., and Renals S. Speech Input from Older Users in Smart Environments: Challenges and Perspectives. In Proceedings of HCI International, (to appear).

Georgila K., Wolters M., and Moore J.D. Simulating the Behaviour of Older versus Younger Users when Interacting with Spoken Dialogue Systems. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL/HLT), Columbus, Ohio, USA, 2008.

Georgila K., Wolters M., Karaiskos V., Kronenthal M., Logie R., Mayo N., Moore J.D., and Watson M. A Fully Annotated Corpus for Studying the Effect of Cognitive Ageing on Users' Interactions with Spoken Dialogue Systems. In Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco, 2008.

Lemon O., Georgila K., and Henderson J. Evaluating Effectiveness and Portability of Reinforcement Learned Dialogue Strategies with Real Users: The TALK TownInfo Evaluation. In Proceedings of the IEEE/ACL Workshop on Spoken Language Technology, Aruba, 2006.

Georgila K., Henderson J., and Lemon O. User Simulation for Spoken Dialogue Systems: Learning and Evaluation. In Proceedings of the 9th International Conference on Spoken Language Processing (INTERSPEECH - ICSLP), Pittsburgh, USA, 2006.

Georgila K. and Lemon O. Programming by Voice: enhancing adaptivity and robustness of spoken dialogue systems. In Proceedings of the 10th Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL: BRANDIAL), Potsdam, Germany, 2006.

Lemon O., Georgila K., Henderson J., and Stuttle M. An ISU dialogue system exhibiting reinforcement learning of dialogue policies: generic slot-filling in the TALK in-car system. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Trento, Italy, 2006.

Georgila K., Henderson J., and Lemon O. Learning User Simulations for Information State Update Dialogue Systems. In Proceedings of the 9th European Conference on Speech Communication and Technology (INTERSPEECH - EUROSPEECH), Lisbon, Portugal, 2005.

Schatzmann J., Georgila K., and Young S. Quantitative Evaluation of User Simulation Techniques for Spoken Dialogue Systems. In Proceedings of the 6th SIGdial Workshop on Discourse and Dialogue, Lisbon, Portugal, September 2-3, 2005.

Georgila K., Lemon O., and Henderson J. Automatic annotation of COMMUNICATOR dialogue data for learning dialogue strategies and user simulations. In Proceedings of the 9th Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL: DIALOR), Nancy, France, 2005.

Henderson J., Lemon O., and Georgila K. Hybrid reinforcement/supervised learning for dialogue policies from COMMUNICATOR data. In Proceedings of the IJCAI workshop on Knowledge and Reasoning in Practical Dialogue Systems, Edinburgh, UK, 2005.

Henderson J., Lemon O., and Georgila K. Hybrid Reinforcement/Supervised Learning of Dialogue Policies. Poster in the 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, Edinburgh, UK, 2005.

Georgila K. and Lemon O. Adaptive Multimodal Dialogue Management Based on the Information State Update approach. In Online Proceedings of W3C Workshop on Multimodal Interaction, Sophia-Antipolis, France, 2004.

Georgila K., Fakotakis N., and Kokkinakis G. A graphical tool for handling rule grammars in Java Speech Grammar Format. In Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC), Lisbon, Portugal, May 26-28, 2004.

Georgila K., Sgarbas K., Fakotakis N., and Kokkinakis G. A Layered, Transducer-Based Language Model for Speech Recognition. In Proceedings of the 8th International Workshop on Speech and Computers, pp. 93-98, Moscow, Russia, Oct. 27-29, 2003.

Potamitis I., Georgila K., Fakotakis N., and Kokkinakis G. Towards a User-friendly Automated Control of Home Appliances Based on Speech Recognition and Microphone Arrays. In Proceedings of the 8th International Workshop on Speech and Computers, pp. 226-230, Moscow, Russia, Oct. 27-29, 2003.

Potamitis I., Georgila K., Fakotakis N., and Kokkinakis G. An Integrated System for Smart-Home Control of Appliances Based on Remote Speech Interaction. In Proceedings of the 8th European Conference on Speech Communication and Technology (EUROSPEECH), pp. 2197-2200, Geneva, Switzerland, Sept. 1-4, 2003.

Potamitis I., Georgila K., Zervas P., Fakotakis N., and Kokkinakis G. An Electronic Assistant for Automatic Control of Home-Appliances Using Natural Speech and Distant Microphones. In Proceedings of IASTED International Conference on Signal Processing, Pattern Recognition and Applications, pp. 191-195, Rhodes, Greece, June 30-July 02, 2003.

Georgila K., Fakotakis N., and Kokkinakis G. Efficient Stochastic Finite-State Networks for Language Modelling in Spoken Dialogue Systems. In Proceedings of the 7th European Conference on Speech Communication and Technology (EUROSPEECH), Vol. 1, pp. 247- 250, Aalborg, Denmark, Sept. 3-7, 2001.

Georgila K., Tsopanoglou A., Fakotakis N., and Kokkinakis G. Refining the N-best Hypotheses List in Large Vocabulary Recognition by Applying Lexical Rules. In Proceedings of the 6th International Workshop on Speech and Computers, pp. 97- 102, Moscow, Russia, Oct. 29-31, 2001.

Georgila K., Fakotakis N., and Kokkinakis G. Variable History Stochastic Networks for Language Modelling in Dialogue Systems. In Proceedings of the 6th International Workshop on Speech and Computers, pp. 182-187, Moscow, Russia, Oct. 29-31, 2001.

Georgila K., Tsopanoglou A., Fakotakis N., and Kokkinakis G. Improved Large Vocabulary Speech Recognition Using Lexical Rules. In Proceedings of Advances in Human-Computer Interaction (PC-HCI) Conference, pp. 191-196, Patras, Greece, Dec. 7-9, 2001.

Louloudis D., Georgila K., Tsopanoglou A., Fakotakis N., and Kokkinakis G. Efficient Strategy and Language Modeling in Human-Machine Dialogues. In Proceedings of the 5th World Multi-Conference on Systemics, Cybernetics and Informatics (SCI), Vol. XIII, pp. 229- 234, Orlando, Florida, USA, July 22-25, 2001.

Georgila K., Fakotakis N., and Kokkinakis G. Building Stochastic Language Model Networks Based on Simultaneous Word/Phrase Clustering. In Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP), Vol. 1, pp. 122-125, Beijing, China, Oct. 16-20, 2000.

Georgila K., Sgarbas K., Fakotakis N., and Kokkinakis G. Fast Very Large Vocabulary Recognition Based on Compact DAWG-structured Language Models. In Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP), Vol. 2, pp. 987-990, Beijing, China, Oct. 16-20, 2000.

Georgila K., Fakotakis N., and Kokkinakis G. A Graphical Parametric Language- Independent Tool for the Annotation of Speech Corpora. In Proceedings of the 2nd International Conference on Language Resources and Evaluation (LREC), Vol. 3, pp. 1537- 1542, Athens, Greece, May 31-June 2, 2000.

Georgila K., Tsopanoglou A., Fakotakis N., and Kokkinakis G. An Integrated Dialogue System for the Automation of Call Centre Services. In Proceedings of the 5th International Conference on Spoken Language Processing (ICSLP), Vol. 2, pp. 45-48, Sydney, Australia, 1998.

Georgila K., Tsopanoglou A., Fakotakis N., and Kokkinakis G. A Dialogue System for Telephone-based Services Integrating Spoken and Written Language. In Proceedings of the 4th IEEE Workshop on Interactive Voice Technology for Telecommunications Applications (IVTTA), pp. 55-59, Turin, Italy, 1998.

Fakotakis N., Georgila K., and Tsopanoglou A. A Continuous HMM, Text Independent Speaker Recognition System Based on Vowel Spotting. In Proceedings of the 5th European Conference on Speech Communication and Technology (EUROSPEECH), Vol. 5, pp. 2347- 2350, Rhodes, Greece, Sept. 22-25, 1997.