Summary of the paper
| Title | WITcHCRafT: A Workbench for Intelligent exploraTion of Human ComputeR conversaTions |
|---|---|
| Authors | Alexander Schmitt, Gregor Bertrand, Tobias Heinroth, Wolfgang Minker and Jackson Liscombe |
| Abstract | We present Witchcraft, an open-source framework for the evaluation ofprediction models for spoken dialogue systems based on interaction logs andaudio recordings. The use of Witchcraft is two fold: first, it provides anadaptable user interface to easily manage and browse thousands of loggeddialogues (e.g. calls). Second, with help of the underlying models and theconnected machine learning framework RapidMiner the workbench is able todisplay at each dialogue turn the probability of the task being completed basedon the dialogue history. It estimates the emotional state, gender and age ofthe user. While browsing through a logged conversation, the user can directlyobserve the prediction result of the models at each dialogue step. By that,Witchcraft allows for spotting problematic dialogue situations and demonstrateswhere the current system and the prediction models have design flaws.Witchcraft will be made publically available to the community and will bedeployed as open-source project. |
| Language | Statistical and machine learning methods |
| Topics | Emotion Recognition/Generation, Tools, systems, applications, Statistical and machine learning methods |
Full paper  |
WITcHCRafT: A Workbench for Intelligent exploraTion of Human ComputeR conversaTions |
| Bibtex | @InProceedings{SCHMITT10.123, author = {Alexander Schmitt, Gregor Bertrand, Tobias Heinroth, Wolfgang Minker and Jackson Liscombe}, title = {WITcHCRafT: A Workbench for Intelligent exploraTion of Human ComputeR conversaTions}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |