Lately, the paradigm for Pattern Recognition (PR) systems design is shifting from the concept of full-automation to systems where the decision process is conditioned by human feedback. This shift is motivated by the fact that full automation often proves elusive, or unnatural in many applications where technology is expected to assist rather than replace the human agents.
This chapter examines the challenges and research opportunities entailed by placing PR within the human-interaction framework; namely: (a) taking direct advantage of the feedback information provided by the user in each interaction step to improve raw performance; (b) acknowledging the inherent multimodality of interaction to improve overall system behavior and usability and (c) using the feedback-derived data to tune the system to the user behavior and the specific task considered, by means of adaptive learning techniques.
One of the most influential factors for the rapid development of PR technology in the last few decades is the nowadays commonly adopted assessment paradigm based on labeled training and testing corpora. This chapter includes a discussion about simple but realistic “user models” or interaction protocols and assessment criteria which allow the successful labeled corpus-based assessment paradigm to be applied also in the interactive scenario.
This chapter also provides an introduction to general approaches available to solve the underlying interactive search problems on the basis of existing methods to solve the corresponding non-interactive counterparts and an overview of modern machine learning approaches which can be useful in the interactive framework.
KeywordsMachine Translation Confidence Measure Interaction Protocol Active Learning Strategy Interaction Step
- 2.Berger, A. L., Pietra, S. A. D., & Pietra, V. J. D. (1996). A maximum entropy approach to natural language processing. Computational Linguistics, 22, 39–71. Google Scholar
- 6.Casacuberta, F., & Higuera, C. D. L. (2000). Computational complexity of problems on probabilistic grammars and transducers. In ICGI’00: Proceedings of the 5th international colloquium on grammatical inference (pp. 15–24), London, UK. Berlin: Springer. Google Scholar
- 7.Chapelle, O., Schölkopf, B., & Zien, A. (2006). Semi-supervised learning. Cambridge: MIT Press. Google Scholar
- 9.Cohn, D., Atlas, L., & Ladner, R. (1994). Improving generalization with active learning. Machine Learning, 15(2), 201–221. Google Scholar
- 11.Dasgupta, S. (2005). Coarse sample complexity bounds for active learning. In Neural information processing systems. Google Scholar
- 13.Dasgupta, S., Hsu, D., & Monteleoni, C. (2008). A general agnostic active learning algorithm. In J. C. Platt, D. Koller, Y. Singer & S. Roweis (Eds.), Advances in neural information processing systems (Vol. 20, pp. 353–360). Cambridge: MIT Press. Google Scholar
- 19.Freund, Y., Seung, H. S., Shamir, E., & Tishby, N. (1995). Selective sampling using the query by committee algorithm. In Machine learning (pp. 133–168). Google Scholar
- 21.Geman, S., & Geman, D. (1987). Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. In Readings in computer vision: issues, problems, principles, and paradigms (pp. 564–584). San Mateo: Morgan Kaufmann. Google Scholar
- 22.González-Rubio, J., Ortiz-Martínez, D., & Casacuberta, F. (2010). Balancing user effort and translation error in interactive machine translation via confidence measures. In Proceedings of the 48th annual meeting of the association for computational linguistics (ACL10) (pp. 173–177). Google Scholar
- 24.Hanneke, S. (2009). Theoretical foundations of active learning. Machine Learning Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, USA. Advisors: Blum, A., Dasgupta, S., Wasserman, L., & Xing, E. P. Google Scholar
- 25.Hazan, E., & Seshadhri, C. (2009). Efficient learning algorithms for changing environments. In Proceedings of the 26th annual international conference on machine learning. Google Scholar
- 28.Jaimes, A., & Sebe, N. (2006). Multimodal human–computer interaction: A survey. Computer Vision and Image Understanding, 108(1–2), 116–134. Special Issue on Vision for Human-Computer Interaction. Google Scholar
- 30.Jelinek, F. (1998). Statistical methods for speech recognition. Cambridge: MIT Press. Google Scholar
- 37.Och, F. J., & Ney, H. (2002). Discriminative training and maximum entropy models for statistical machine translation. In Proc. of ACL (pp. 295–302). Google Scholar
- 39.Pearl, J. (1984). Heuristics: intelligent search strategies for computer problem solving. Reading: Addison-Wesley. Google Scholar
- 40.Pearl, J. (1988). Probabilistic reasoning in intelligent systems: networks of plausible inference. San Mateo: Morgan Kaufmann. Google Scholar
- 46.Serrano, N., Sanchis, A., & Juan, A. (2010). Balancing error and supervision effort in interactive-predictive handwriting recognition. In Proceedings of the international conference on intelligent user interfaces (IUI 2010) (pp. 373–376). Google Scholar
- 47.Shalev-shwartz, S., & Tewari, A. (2008). Efficient bandit algorithms for online multiclass prediction sham m. kakade. In Proc. of the 25th international conference on machine learning. Google Scholar
- 48.Toselli, A. H., Pastor, M., & Vidal, E. (2007). On-line handwriting recognition system for Tamil handwritten characters. In Lecture notes in computer science: Vol. 4477. 3rd Iberian conference on pattern recognition and image analysis (pp. 370–377), Girona (Spain). Berlin: Springer. CrossRefGoogle Scholar
- 52.Zaphiris, P., & Ang, C. S. (2008). Cross-disciplinary advances in human computer interaction: user modeling, social computing, and adaptive interfaces. Advances in technology and human interaction book series. Information Science Reference. Google Scholar