Analysis of Statistical Question Classification for Fact-Based Questions

Question classification systems play an important role in question answering systems and can be used in a wide range of other domains. The goal of question classification is to accurately assign labels to questions based on expected answer type. Most approaches in the past have relied on matching questions against hand-crafted rules. However, rules require laborious effort to create and often suffer from being too specific. Statistical question classification methods overcome these issues by employing machine learning techniques. We empirically show that a statistical approach is robust and achieves good performance on three diverse data sets with little or no hand tuning. Furthermore, we examine the role different syntactic and semantic features have on performance. We find that semantic features tend to increase performance more than purely syntactic features. Finally, we analyze common causes of misclassification error and provide insight into ways they may be overcome.     

Educational concerns of Arabic speaking migrants from Sudan and Iraq to Melbourne: Expectations on migrant parents in Australia

Families immigrating to Australia face many challenges integrating into the educational system, including language barriers and interrupted schooling. We have qualitatively evaluated the educational concerns of Arabic migrants from Sudan and Iraq to Melbourne, Victoria, Australia, a city that receives a high percentage of Australia's immigrants. Using an interactive paradigm incorporating focus group discussions for thematic analysis, we concluded that the parents’ frame of reference for education was a more didactic style of learning. Parents viewed education as an essential part of the way forward for their children in Australia. However, it was stressful for them to try to cope with a new host nation's expectation of their involvement in their children's education while at the same time dealing with a language barrier. Professionals should look to empower parents with structural information about the key elements of the educational curriculum with minimal reliance on written technical language and match their expectations of parental involvement to the situation of the parents.