Summary of the paper

Title Classifying Action Items for Semantic Email
Authors Simon Scerri, Gerhard Gossen, Brian Davis and Siegfried Handschuh
Abstract Email can be considered as a virtual working environment in which users areconstantly struggling to manage the vast amount of exchanged data. Althoughmost of this data belongs to well-defined workflows, these are implicit andlargely unsupported by existing email clients. Semanta provides this support byenabling Semantic Email ― email enhanced with machine-processable metadataabout specific types of email Action Items (e.g. Task Assignment, MeetingProposal). In the larger picture, these items form part of ad-hoc workflows(e.g. Task Delegation, Meeting Scheduling). Semanta is faced with aknowledge-acquisition bottleneck, as users cannot be expected to annotate eachaction item, and their automatic recognition proves difficult. This paperfocuses on applying computationally treatable aspects of speech act theory forthe classification of email action items. A rule-based classification model isemployed, based on the presence or form of a number of linguistic features. Thetechnology’s evaluation suggests that whereas full automation is notfeasible, the results are good enough to be presented as suggestions for theuser to review. In addition the rule-based system will bootstrap a machinelearning system that is currently in development, to generate the initialtraining sets which are then improved through the user’s reviewing.
Language Semantic Web
Topics Discourse annotation, representation and processing, Information Extraction, Information Retrieval, Semantic Web
Full paper Classifying Action Items for Semantic Email
Bibtex @InProceedings{SCERRI10.39,
  author = {Simon Scerri, Gerhard Gossen, Brian Davis and Siegfried Handschuh},
  title = {Classifying Action Items for Semantic Email},
  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}
 }
Powered by ELDA © 2010 ELDA/ELRA