Full Seminar Details

Trung Huynh

 Trung Huynh
Learning word representations with deep learning
This event took place on Wednesday 04 October 2017 at 11:30


Learning word representations from unsupervised methods has been recently extensively explored. However the studied methods have been limited to methods based on co-occurrence statistics or windowed bag-of-word shallow neural networks. These methods are usually so computationally efficient that they can be trained with huge corpora that may contain billions of tokens. These bag-of-word models however do not utilise the structural nature of languages for their inferences. We hypothesise that by using structural architectures, specifically recurrent neural networks, derived word representations contain properties learned from the preserved sequential nature of the inputs.

Watch the webcast replay >>

Jobs

Senior Research Fellow x 2

Knowledge Media Institute (KMi)
50,618 - 56,950 (Grade AC4)
Based in Milton Keynes
Permanent Position

WE ACCEPT APPLICATIONS FROM CITIZENS GLOBALLY The Knowledge Media Institute (KMi) is one of the top research centres in the world in the area of knowledge and media technologies, and we offer a creative and flexible working environment. The...

Research Assistant / Associate

Knowledge Media Institute (KMi)
29.799 - 38,833 (Grade AC1 / AC2)
Based in Milton Keynes
Temporary contract until 30th November 2018

WE ACCEPT APPLICATIONS FROM CITIZENS GLOBALLY The Knowledge Media Institute (KMi) is a distinct research unit within the Faculty of Science, Technology, Engineering and Mathematics (STEM) at the Open University. KMi is looking for a Research...

Research Assistant / Associate

Knowledge Media Institute (KMi)
29,799 - 38,833 (Grade AC1 / AC2)
Based in Milton Keynes
Temporary contract until 31st December 2018

WE ACCEPT APPLICATIONS FROM CITIZENS GLOBALLY The Knowledge Media Institute (KMi) is a distinct research unit within the Faculty of Science, Technology, Engineering and Mathematics (STEM) at the Open University. KMi is looking for a Research...

CONTACT US

Knowledge Media Institute
The Open University
Walton Hall
Milton Keynes
MK7 6AA
United Kingdom

Tel: +44 (0)1908 653800

Fax: +44 (0)1908 653169

Email: KMi Support

COMMENT

If you have any comments, suggestions or general feedback regarding our website, please email us at the address below.

Email: KMi Development Team