(aside image)

Cognitive Systems Blog


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).


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.



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.

Translation example

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.


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.


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.


Please, see also the full list of publications.


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.

Valid HTML 4.01 Transitional