Enhancing Attentive Task Search with Information Gain Trees and Failure Detection Strategies

Kristin Stamm, Andreas Dengel

2013

Abstract

Enterprises today are challenged by managing requests arriving through all communication channels. To support service employees in better and faster understanding incoming documents, we developed the approach of process-driven document analysis (DA). We introduced the structure Attentive Task (AT) to formalize information expectations toward an incoming document. To map the documents to the corresponding AT, we previously developed a novel search approach that uses DA results as evidences for prioritizing all AT. With this approach, we consider numerous task instances including their context instead of a few process classes. The application of AT search in enterprises raises two challenges: (1) Complex domains require a structured selection of well performing evidence types, (2) a failure detection method is needed for handling a substantial part of incoming documents that cannot be related to any AT. Here, we apply methods from machine learning to meet these requirements. We learn and apply information gain trees for structuring and optimizing evidence selection. We propose five strategies for detecting documents without ATs. We evaluate the suggested methods with two processes of a financial institution.

References

  1. Bellotti, V. et al. (2005). Quality vs. quantity: Email-centric task-management and its relationship with overload. Human-Computer Interaction, 20:1-2.
  2. Cohen, W., Carvalho, V., and Mitchell, T. (2004). Learning to classify email into ”speech acts”. In Proceedings of EMNLP.
  3. Dengel, A. and Hinkelmann, K. (1996). The specialist board - a technology workbench for document analysis and understanding. In IDPT.
  4. Dredze, M., Lau, T., and Kushmerick, N. (2006). Automatically classifying emails into activities. In Proceedings of IUI.
  5. Faulring, A. et al. (2010). Agent-assisted task management that reduces email overload. In Proceedings of IUI.
  6. Granitzer, M. et al. (2009). Machine learning based work task classification. Journal of Digital Information Management.
  7. Katz, A. and Berman, I. (2011). Designing an e-mail prototype to enhance effective communication and task management: A case study. Serdica Journal of Computing, 5.
  8. Krämer, J. (2010). Pim-mail: consolidating task and email management. In Proceedings of CHI.
  9. Kullback, S. and Leibler, R. (1951). On information and sufficiency. The Annals of Mathematical Statistics, 22.
  10. Kushmerick, N. and Lau, T. A. (2005). Automated email activity management: an unsupervised learning approach. Proceedings of IUI.
  11. Scerri, S., Gossen, G., Davis, B., and Handschuh, S. (2010). Classifying action items for semantic email. In Proceedings of LREC.
  12. Shafer, G. (1976). A Mathematical Theory of Evidence, volume 1. Princeton university press Princeton.
  13. Stamm, K. and Dengel, A. (2012a). Attentive tasks: Process-driven document analysis for multichannel documents. Proceedings of DAS.
  14. Stamm, K. and Dengel, A. (2012b). Searching attentive tasks with document analysis evidences and dempstershafer theory. Proceedings of ICPR.
Download


Paper Citation


in Harvard Style

Stamm K. and Dengel A. (2013). Enhancing Attentive Task Search with Information Gain Trees and Failure Detection Strategies . In Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-8565-39-6, pages 81-90. DOI: 10.5220/0004227300810090


in Bibtex Style

@conference{icaart13,
author={Kristin Stamm and Andreas Dengel},
title={Enhancing Attentive Task Search with Information Gain Trees and Failure Detection Strategies},
booktitle={Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2013},
pages={81-90},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004227300810090},
isbn={978-989-8565-39-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Enhancing Attentive Task Search with Information Gain Trees and Failure Detection Strategies
SN - 978-989-8565-39-6
AU - Stamm K.
AU - Dengel A.
PY - 2013
SP - 81
EP - 90
DO - 10.5220/0004227300810090