I am looking for a PhD student to work on understanding complex information needs.
Web search engines have become remarkably effective in providing appropriate answers to queries that are issued frequently. However, when it comes to complex information needs, often formulated as natural language questions, responses become much less satisfactory (e.g., “Which European universities have active Nobel laureates?”). The goal of this project is to investigate how to improve query understanding and answer retrieval for complex information needs, using massive volumes of unstructured data in combination with knowledge bases. Query understanding entails, among others, determining the type (format) of the answer (single fact, list, answer passage, list of documents, etc.) and identifying the series of processing steps (retrieval, filtering, sorting, aggregation, etc.) required to obtain that answer. If the question is not understood or ambiguous, the system should ask for clarification in an interactive way. This could be done in a conversational manner, similarly to how it is done in commercial personal digital assistants, such as SIRI, Cortana, or Google Now.
The successful applicant would join a team of 2 other PhD students working on the FAETE project.
Details and application instructions can be found here.
Application deadline: April 17, 2016.
Important note: there are multiple projects advertised within the call. You need to indicate that you are applying for this specific project. Feel free to contact me directly for more information.