Building a corpus and developing a question classifier to support messaging-based question answering

We are investigating question classification for restricted domains with the broader goal of supporting mixed-initiative interaction on mobile phones. In this paper, we discuss the development of a new domain-specific corpus of cancer-related questions and our efforts toward training a classifier. This work includes the development of a new taxonomy of expected answer types that we have been evaluating. Our goal is to create software to engage newly diagnosed prostate cancer patients in question-answering dialogs related to their treatment options. We are focusing our work on the interaction environment afforded by text and multimedia (SMS and MMS) messaging using mobile telephones, because of the prevalence of this technology and the growing popularity of text messaging, especially among underserved populations. This work is interesting from a user interface and communication standpoint because, despite this growing popularity, there has been little formal study of this type of interactive communication.

[1]  Dell Zhang,et al.  Question classification using support vector machines , 2003, SIGIR.

[2]  Dan Roth,et al.  Learning question classifiers: the role of semantic information , 2005, Natural Language Engineering.

[3]  Claire Cardie,et al.  Multi-Perspective Question Answering Using the OpQA Corpus , 2005, HLT.

[4]  Klaus Krippendorff,et al.  Computing Krippendorff's Alpha-Reliability , 2011 .

[5]  N. Dubrawsky.  Cancer statistics , 1989, CA: a cancer journal for clinicians.

[6]  A. Jemal,et al.  Cancer Statistics, 2008 , 2008, CA: a cancer journal for clinicians.

[7]  M. Brundage,et al.  The information needed by Canadian early-stage prostate cancer patients for decision-making: stable over a decade. , 2008, Patient education and counseling.

[8]  Fabrizio Sebastiani,et al.  Machine learning in automated text categorization , 2001, CSUR.

[9]  Dan Roth,et al.  Learning Question Classifiers , 2002, COLING.

[10]  P. Gorman,et al.  A taxonomy of generic clinical questions: classification study , 2000, BMJ : British Medical Journal.

[11]  Ellen M. Voorhees,et al.  Overview of the TREC 2004 Novelty Track. , 2005 .

[12]  Holly Blake,et al.  Innovation in practice: mobile phone technology in patient care. , 2008, British journal of community nursing.

[13]  J. Fleiss.  Measuring nominal scale agreement among many raters. , 1971 .

[14]  K W Gish,et al.  Information needs of clinical teams: analysis of questions received by the Clinical Informatics Consult Service. , 2001, Bulletin of the Medical Library Association.

[15]  Hakan Sundblad.  A Re-examination of Question Classification , 2007, NODALIDA.

[16]  Steven E. Stemler.  Practical Assessment, Research, and Evaluation Practical Assessment, Research, and Evaluation A Comparison of Consensus, Consistency, and Measurement A Comparison of Consensus, Consistency, and Measurement Approaches to Estimating Interrater Reliability Approaches to Estimating Interrater Reliabilit , 2022 .