[Corpora-List] Post-doctoral position in Natural Language Modelling in Singapore (NTU)

Francis Bond bond at ieee.org
Fri Apr 25 11:25:32 CEST 2014


we are looking for a post-doc interested in combining lexical and structural semantics (wordnet meets HPSG)! Read below for details:

University or Organization: Nanyang Technological University Department: Linguistics and Multilingual Studies

Computational Linguistics Lab Job Location: Singapore Web Address: http://compling.hss.ntu.edu.sg/

Job Rank: Post Doc

Specialty Areas: Computational Linguistics; Natural Language Understanding; Machine Translation


Post Doc Researcher Natural Language Modeling


The Division of Linguistics and Multilingual Studies (LMS) at NTU seeks a post-doctoral fellow for research on semantic representation as part of the project “That’s what you meant: An Integrated Semantic Framework for Representing Meaning” (abstract below). The postdoctoral fellow will work with Francis Bond <http://www3.ntu.edu.sg/home/fcbond/>.

Duties and Responsibilities:

(1) Responsible for coordinating the project a. Test the design for an Integrated Semantic Framework b. Help instantiate grammars for Chinese, English and Japanese c. Evaluate with disambiguation models for these three grammars d. Compile transfer grammars for Japanese and Chinese to English machine translation

(2) Postdoctoral fellows may be required to assist in teaching, up to the equivalent of one semester-based course per academic year.

Requirements and Profile:

(1) PhD in Computational Linguistics, Linguistics, Computer Science, Cognitive Science, or a related discipline.

(2) Experience with both symbolic and statistical NLP, e.g.:

* Language modeling, especially semantic modeling

* parsing with Head-driven Phrase Structure Grammar (HPSG)

* machine translation

(3) Knowledge of Chinese and Japanese highly desirable.


The duration of the position is 2.5 years. Initial appointment is for a period of one year, renewable for 1.5 more years, subject to satisfactory performance. Competitive salary based on experience. Review of applications will begin in May 2014 and will continue until the position is filled.

Applications should include:

* a detailed CV

* names and contact details of 3 referees

* a brief research proposal

* a sample of your research output (a paper or dissertation)

Send applications (by email) to:

Linguistics and Multilingual Studies Nanyang Technological University HSS building, HSS-05-17 14 Nanyang Drive, Singapore 637332 Fax: +65 6794 9577 Email: ntunlpgroup at gmail.com

Any inquiries about this position should be sent to: Francis Bond <bond at ieee.org>

For more information about the research group, please see: http://compling.hss.ntu.edu.sg/

Brief Abstract of the Project:

There are two main approaches to the study of meaning in text. One looks at the relations between words when they are used (structural semantics). For example, in the sentence /The head fired the driver/, there is an act of firing, where the boss is the one who fires the driver. A typical (simplified) representation of this would be [fire (head, driver)]. Another approach is to consider the meaning of each word in relation to our knowledge of other words (lexical semantics): in this sentence /head/ means something similar to "boss" rather than being a "body part"; /fire/ means to "terminate employment" not to "discharge a projectile"; and /driver/ is a "person who drives a vehicle", not a "golf club" or "piece of software". A typical (simplified) representation of this would be [The head_3 fired_2 the driver_1], where the subscripts refer to a definition of the meaning in some external knowledge source. Our goal is to unite these two approaches (structural and lexical) in an integrated semantic framework in order to be able to study the interactions between the two kinds of information and to better model language computationally. In our integrated representation, the final representation will be something like: [fire_2 (head_3, driver_1)]. More technically, we are integrating minimal recursion semantic representations with wordnet senses extending both as necessary. We will look at three languages: Chinese, English and Japanese, using and extending existing resources.

-- Francis Bond <http://www3.ntu.edu.sg/home/fcbond/> Division of Linguistics and Multilingual Studies Nanyang Technological University -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 5164 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20140425/67120a69/attachment.txt>

More information about the Corpora mailing list