Main research areas

We conduct research on adaptive, autonomous and socio-culturally grounded cognitive systems that are able to learn and use language. We apply and develop computational methods, models and frameworks for adaptive machine translation and socio-cognitive multiagent systems.

Emergence of Linguistic and Cognitive Features and Structures

The research on emergent linguistic and cognitive representations enables computers to deal with semantics: to process data having certain access to its meaning within multimodal contexts. We deal with the analysis and generation of conceptual structures and complex meanings.

The emergence of representations can be considered to consist of the following interrelated tasks: the discovery of (1) elements of representation (e.g. words, morphemes, phonemes), (2) their meaning relations (syntax and semantics), and (3) structures or ``rules'' of their use in natural utterances (syntax and pragmatics).

Links

• Computational Cognitive Systems research group
• Adaptive Natural Language Processing group
• Home page of Krista Lagus
• Home page of Timo Honkela
• Home page of Mathias Creutz

Learning Social Interactions

One important feature of an intelligent agent is its ability to make rational decisions based on its current knowledge of the environment. If the environment of the agent is not static, i.e., there are other active entities, e.g., other agents or humans in the environment, it is crucial to model these entities for making rational decisions.

Our earlier research in this areas has been directed at learning social interactions between agents based on, for example, Markov games. The reinforcement learning approach based on Markov games provides a complete model of interactions between learning agents.

Publications

• Könönen, V.J., 2004. Asymmetric multiagent reinforcement learning. Web Intelligence and Agent Systems: An International Journal (WIAS) 2, number 2, pages 105-121.
• Könönen, V.J., 2004. Hybrid model for multiagent reinforcement learning. Proceedings of the International Joint Conference on Neural Networks (IJCNN-2004). Budapest, Hungary, 25-29 July 2004, pages 1793-1798.
• Könönen, V.J., 2004. Policy gradient method for team Markov games. Proceedings of the Fifth International Conference on Intelligent Data Engineering and Automated Learning (IDEAL-2004). Exeter, UK, 25-27 August 2004. Heidelberg, Springer-Verlag. Lecture Notes in Computer Science 3177, pages 733-739.
• Könönen, V.J. and Oja, E., 2004. Asymmetric multiagent reinforcement learning in pricing applications. Proceedings of the International Joint Conference on Neural Networks (IJCNN-2004). Budapest, Hungary, 25-29 July 2004, pages 1097-1102.
• Skripal, P. and Honkela, T. Framework for Modeling Emotions in Communities of Agents. In: H. Hyötyniemi, P. Ala-Siuru and J. Seppänen (eds.), Life, Cognition and Systems Sciences, Symposium Proceedings of the 11th Finnish Artificial Intelligence Conference, Finnish Science Center Heureka Vantaa, 1-3 September 2004, pp. 163-172.
• Honkela, T., Hynna, K. I. and Knuuttila, T. Framework for Modeling Partial Conceptual Autonomy of Adaptive and Communicating Agents. Proceedings of CogSci2003, 25th Annual Meeting of Cognitive Science Society, Boston, Massachusetts, July 31-August 2, 2003.
• Honkela, T. and Winter, J. Simulating Language Learning in Community of Agents Using Self-Organizing Maps, Report A71, Helsinki University of Technology, Laboratory of Computer and Information Science, December, 2003.

Links

• Computational Cognitive Systems research group

Learning to Translate

Reaching good quality machine translation (MT) is difficult and the development of a traditional MT system requires a lot of human effort. However, the availability of large corpora makes it possible to use various probabilistic and statistical methods to let the system generate the necessary resources automatically.

Within-language translation

In addition to the traditional translation from one language to another, we develop methods that enable translations or interpretations within one language.

The underpinning idea is the fact that contextual, experiential and/or disciplinary diversity impede interpersonal communication and understanding. Therefore, even speakers of one language may need translation tools that facilitate efficient communication, for example, between representatives of different professional domains.

Methodology

Our approach is extensively based on unsupervised statistical machine learning techniques, including independent component analysis, self-organizing map, clustering, expectation maximization algorithm, compression and Bayesian methods. We also want to take carefully into account the underlying cognitive, linguistic and philosophical issues in order to avoid local minima in the technology development.

Activities

In 2006, we organized a Finnish-Swedish Machine Translation Challenge with our collaborators from the University of Helsinki. During autumn 2005 and early 2006 we organized a seminar on statistical machine translation.

Publications

• Marcus Dobrinkat, Tero Tapiovaara, Jaakko Väyrynen, and Kimmo Kettunen. Evaluating machine translations using mNCD. In Proceedings of the ACL 2010 Conference Short Papers, pages 80-85. Association for Computational Linguistics, 2010.
• Marcus Dobrinkat, Tero Tapiovaara, Jaakko Väyrynen, and Kimmo Kettunen. Normalized compression distance based measures for MetricsMATR 2010. In Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, pages 343-348. Association for Computational Linguistics, 2010.
• Sami Virpioja, André Mansikkaniemi, Jaakko Väyrynen, and Mikko Kurimo. Applying morphological decompositions to statistical machine translation. In Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, pages 201-206. Association for Computational Linguistics, 2010.
• Jaakko J. Väyrynen, Tero Tapiovaara, Kimmo Kettunen, and Marcus Dobrinkat. Normalized compression distance as an automatic MT evaluation metric. In Proceedings of MT 25 years on, 21-22 Nov 2009 Cranfield, UK, 2009. To appear.
• Timo Honkela, Sami Virpioja, and Jaakko Väyrynen. Adaptive translation: Finding interlingual mappings using self-organizing maps. In Vera Kurkova, Roman Neruda, and Jan Koutnik, editors, Proceedings of ICANN'08, volume 5163 of Lecture Notes in Computer Science, pages 603-612. Springer, 2008.
• Marcus Dobrinkat. Domain adaptation in statistical machine translation systems via user feedback. Master's thesis, Helsinki University of Technology, Department of Information and Computer Science, Espoo, Finland, December 2008.
• David Ellis, Mathias Creutz, Timo Honkela, and Mikko Kurimo. Speech to speech machine translation: Biblical chatter from Finnish to English. In Proceedings of the IJCNLP-08 Workshop on NLP for Less Privileged Languages, pages 123-130, Hyderabad, India, January 2008. Asian Federation of Natural Language Processing.
• Sami Virpioja, Jaakko J. Väyrynen, Mathias Creutz, and Markus Sadeniemi. Morphology-aware statistical machine translation based on morphs induced in an unsupervised manner. In Proceedings of the Machine Translation Summit XI, pages 491-498, September 2007.
• Kettunen, K., Sadeniemi, M. Lindh-Knuutila, T. and Honkela, T. Analysis of EU Languages Through Text Compression. Proceedings of FinTAL 2006, pp. 99-109.
• Lindh-Knuutila, T., Honkela, T. and Lagus, K. Simulating Meaning Negotiation using Observational Language Games. Proceedings of the Third International Symposium on the Emergence and Evolution of Linguistic Communication. Rome, Italy, September, 2006, pp. 168-179.

Please, see also the full list of publications.

Links

• Computational Cognitive Systems research group

Knowledge translation and innovation

Knowledge translation can be defined as the process of supporting the uptake of research in a manner that improves the practices in the society and in industries through improved understanding, processes, services, products or systems.