<div dir="ltr"><span style="font-size:13px">PhD</span><span style="font-size:13px"> position at University Paris Saclay, Orsay (near Paris), France</span><br><div class="gmail_quote"><div dir="ltr"><br style="font-size:13px"><span style="font-size:13px">Title: Hybrid Question Answering over Heterogeneous Data</span><br style="font-size:13px"><span style="font-size:13px">Laboratories:</span><br style="font-size:13px"><span style="font-size:13px"> LRI, CNRS UMR 8623, Université Paris Sud, France</span><br style="font-size:13px"><span style="font-size:13px"> LIMSI, CNRS, Université Paris-Saclay, France</span><br style="font-size:13px"><span style="font-size:13px">Supervisors: </span><span style="font-size:13px">Brigitte</span><span style="font-size:13px"> </span><span style="font-size:13px">Grau</span><span style="font-size:13px"> (LIMSI); Yue Ma (LRI)</span><br style="font-size:13px"><span style="font-size:13px">Project context: GoASQ (ANR international project with TU Dresden, Germany)</span><br style="font-size:13px"><span style="font-size:13px">Financial support: ANR</span><br style="font-size:13px"><span style="font-size:13px">Start Date: as soon as possible (latest </span><span style="font-size:13px"><span>December 1, 2016</span></span><span style="font-size:13px">)</span><br style="font-size:13px"><span style="font-size:13px">Duration: three years</span><br style="font-size:13px"><span style="font-size:13px">Application Deadline: </span>open until filled (1st round of interview will be by the end of June, 2016)<div><br><span style="font-size:13px">***Motivations***</span><br style="font-size:13px"><span style="font-size:13px">More and more information on individuals (e.g., persons, events, biological objects) are available electronically in a structured or semi-structured form. However, selecting individuals satisfying certain complex constraints manually is a complex, error-prone, and time and personnel-consuming effort. To this end, tools that can (semi-)automatically answer questions based on heterogeneous data need to be developed, as exampled by IBM Watson system. This Ph.D project is to deal with instance extraction problem for applications that involve rich background domain knowledge, such as searching electronic patient records for eligible patients satisfying non-trivial combinations of certain properties, e.g., eligibility criteria for clinical trials. We name this task complex question answering.</span></div><div><br style="font-size:13px"><span style="font-size:13px">While simple questions can directly be expressed and answered using keywords in natural language, complex questions that can refer to type and relational information will increase the precision of retrieved results, and thus reduce the effort for posterior manual verification of the results. </span><span style="font-size:13px">Formal queries are powerful in this context, in representing complex questions and exploring background knowledge; however they are often difficult to master, which makes such an advanced answering system impractical if without a user adapted interface. To resolve the problem, this </span><span style="font-size:13px">PhD</span><span style="font-size:13px"> project is to provide a user with the possibility to formulate her need with natural language questions that can be complex pieces of texts. Apart from this easier interface, natural language will enable us to formulate constraints that </span><span style="font-size:13px">cannot be represented formally due to the expressiveness limits of formal languages, but that can be directly verified using textual data.</span><br style="font-size:13px"><br style="font-size:13px"><span style="font-size:13px">***Ph.D Work***</span><br style="font-size:13px"><span style="font-size:13px">To achieve the complex question answering, this </span><span style="font-size:13px">PhD</span><span style="font-size:13px"> project is to develop a novel answering question paradigm that integrates both formal database-like query answering and texts based question answering by information extraction methods. This is because these are two important approaches for complex question answering, but of each own advantages. To benefit from both methods, a key contribution of this </span><span style="font-size:13px">PhD</span><span style="font-size:13px"> work will be the approaches for combining answers to a formal query with answers found based on information retrieval techniques, which has been identified as a challenge in question answering systems.</span><br style="font-size:13px"><span style="font-size:13px">It is to study the hybrid complex question answering systems by taking into account the limits of both ontological reasoning and text processing approaches alone. In particular, the following approaches </span><span style="font-size:13px">need to be developed:</span><br style="font-size:13px"><span style="font-size:13px"> - Text-for-ontology search: selecting relevant cases by text-based retrieval for defining a subset of individuals to reduce the calculation complexity of formal queries.</span><br style="font-size:13px"><span style="font-size:13px"> - Ontology driven search: querying the populated ontology for selecting potential relevant individuals and related texts, and reranking these individuals by verifying remaining unstructured information on them.</span><br style="font-size:13px"><span style="font-size:13px"> - Hybrid answer production: producing final answers to a question by comparing and then combining the results from ontology based reasoning method and text based processing method.</span><br style="font-size:13px"><br style="font-size:13px"><span style="font-size:13px">***Required profile***</span><br style="font-size:13px"><span style="font-size:13px">Master in Computer Science or related domain</span><br style="font-size:13px"><span style="font-size:13px">Knowledge in Semantic Web, Information Extraction, and/or Artificial Intelligence is required. Background in Natural Language Processing, Automatic Reasoning or Information Retrieval is desired.</span><br style="font-size:13px"><span style="font-size:13px">Programming: Java, python</span><br style="font-size:13px"><span style="font-size:13px">Language: good English level, French is not required</span><br style="font-size:13px"><span style="font-size:13px">Ability to work in team, motivation on multidiscipline studies</span><br style="font-size:13px"><br style="font-size:13px"><span style="font-size:13px">***Documents required for application***</span><br style="font-size:13px"><span style="font-size:13px">CV, motivation letter, and recommendation letters</span><br style="font-size:13px"><span style="font-size:13px">Transcripts for Master and undergraduate courses</span><br style="font-size:13px"><br style="font-size:13px"><span style="font-size:13px">Please send your applications to </span><a href="http://brigitte.grau_at_limsi.fr/" rel="noreferrer" style="font-size:13px" target="_blank"><span>brigitte</span>.grau_at_limsi.fr</a><span style="font-size:13px"> and </span><a href="http://yue.ma_at_lri.fr/" rel="noreferrer" style="font-size:13px" target="_blank">yue.ma_at_lri.fr</a><span style="font-size:13px"> as soon as possible.</span><span class="HOEnZb"><font color="#888888"><div style="margin:2px 0px 0px;font-size:13px"></div></font></span></div><span class="HOEnZb"><font color="#888888"><br clear="all"><div><br></div>-- <br><div data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><span style="font-size:13.3333339691162px">Maître de Conférences</span><div><a href="http://www.lri.fr/" style="font-size:13.3333339691162px" target="_blank">Laboratoire de Recherche en Informatique (LRI - CNRS)</a><div><a href="http://www.u-psud.fr/" style="font-size:13.3333339691162px" target="_blank">Université Paris-Sud</a></div><div>91405 Orsay Cedex</div><div><span style="font-size:small">Tel : 01 69 15 57 54 </span><br></div><div><font size="2">Bureau : 175/PCRI-S</font></div></div></div></div></div></div></font></span></div>
</div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><span style="font-size:13.3333339691162px">Maître de Conférences</span><div><a href="http://www.lri.fr/" style="font-size:13.3333339691162px" target="_blank">Laboratoire de Recherche en Informatique (LRI - CNRS)</a><div><a href="http://www.u-psud.fr/" style="font-size:13.3333339691162px" target="_blank">Université Paris-Sud</a></div><div>91405 Orsay Cedex</div><div><span style="font-size:small">Tel : 01 69 15 66 80</span><br></div><div><font size="2">Bureau : 175/PCRI-S</font></div></div></div></div></div></div>
</div>