<div dir="ltr">G'day,<br><br>we are looking for a post-doc interested in combining lexical and structural semantics (wordnet meets HPSG)! Read below for details:<br><br>University or Organization: Nanyang Technological University<br>
Department: Linguistics and Multilingual Studies<br> Computational Linguistics Lab<br>Job Location: Singapore<br>Web Address: <a href="http://compling.hss.ntu.edu.sg/">http://compling.hss.ntu.edu.sg/</a><br><br>
Job Rank: Post Doc<br><br>Specialty Areas: Computational Linguistics; Natural Language<br>Understanding; Machine Translation<br><br>Description:<br><br>Post Doc Researcher Natural Language Modeling<br><br>Context<br><br>
The Division of Linguistics and Multilingual Studies (LMS) at NTU<br>
seeks a post-doctoral fellow for research on semantic representation<br>as part of the project “That’s what you meant: An Integrated Semantic<br>Framework for Representing Meaning” (abstract below). The<br>postdoctoral fellow will work with Francis Bond<br>
<<a href="http://www3.ntu.edu.sg/home/fcbond/">http://www3.ntu.edu.sg/home/fcbond/</a>>.<br><br>Duties and Responsibilities:<br><br>(1) Responsible for coordinating the project<br>a. Test the design for an Integrated Semantic Framework<br>
b. Help instantiate grammars for Chinese, English and Japanese<br>c. Evaluate with disambiguation models for these three grammars<br>d. Compile transfer grammars for Japanese and Chinese to English machine translation<br>
<br>(2) Postdoctoral fellows may be required to assist in teaching, up to the<br>equivalent of one semester-based course per academic year.<br><br><br>Requirements and Profile:<br><br>(1) PhD in Computational Linguistics, Linguistics, Computer Science,<br>
Cognitive Science, or a related discipline. <br><br>(2) Experience with both symbolic and statistical NLP, e.g.:<br> * Language modeling, especially semantic modeling<br> * parsing with Head-driven Phrase Structure Grammar (HPSG)<br>
* machine translation<br><br>(3) Knowledge of Chinese and Japanese highly desirable. <br><br>Appointment:<br><br>The duration of the position is 2.5 years. Initial appointment is for<br>a period of one year, renewable for 1.5 more years, subject to<br>
satisfactory performance. Competitive salary based on experience.<br>Review of applications will begin in May 2014 and will continue<br>until the position is filled.<br><br><br>Applications should include: <br><br> * a detailed CV<br>
* names and contact details of 3 referees<br> * a brief research proposal<br> * a sample of your research output (a paper or dissertation)<br><br><br>Send applications (by email) to:<br><br>Linguistics and Multilingual Studies<br>
Nanyang Technological University<br>HSS building, HSS-05-17<br>14 Nanyang Drive, Singapore 637332<br>Fax: +65 6794 9577<br>Email: <a href="mailto:ntunlpgroup@gmail.com">ntunlpgroup@gmail.com</a> <br><br>Any inquiries about this position should be sent to:<br>
Francis Bond <<a href="mailto:bond@ieee.org">bond@ieee.org</a>><br><br>For more information about the research group, please see:<br><a href="http://compling.hss.ntu.edu.sg/">http://compling.hss.ntu.edu.sg/</a><br>
<br>
<br>Brief Abstract of the Project: <br><br>There are two main approaches to the study of meaning in text. One<br>looks at the relations between words when they are used (structural<br>semantics). For example, in the sentence /The head fired the driver/,<br>
there is an act of firing, where the boss is the one who fires the<br>driver. A typical (simplified) representation of this would be [fire<br>(head, driver)]. Another approach is to consider the meaning of each<br>word in relation to our knowledge of other words (lexical semantics):<br>
in this sentence /head/ means something similar to "boss" rather than<br>being a "body part"; /fire/ means to "terminate employment" not to<br>"discharge a projectile"; and /driver/ is a "person who drives a<br>
vehicle", not a "golf club" or "piece of software". A typical<br>(simplified) representation of this would be [The head_3 fired_2 the<br>driver_1], where the subscripts refer to a definition of the meaning<br>
in some external knowledge source. Our goal is to unite these two<br>approaches (structural and lexical) in an integrated semantic<br>framework in order to be able to study the interactions between the<br>two kinds of information and to better model language<br>
computationally. In our integrated representation, the final<br>representation will be something like: [fire_2 (head_3, driver_1)].<br>More technically, we are integrating minimal recursion semantic<br>representations with wordnet senses extending both as necessary. We<br>
will look at three languages: Chinese, English and Japanese, using and<br>extending existing resources.<br><br clear="all"><div><br><br><br>-- <br>Francis Bond <<a href="http://www3.ntu.edu.sg/home/fcbond/">http://www3.ntu.edu.sg/home/fcbond/</a>><br>
Division of Linguistics and Multilingual Studies<br>Nanyang Technological University
</div></div>