David Grangier and Antoine Bordes from Facebook AI Research, together with Léon Bottou and Chris Burges from Microsoft Research and Cédric Archambeau from Amazon are organizing the 2nd Workshop on Learning Semantics at the NIPS conference in December in Montreal (http://nips.cc).
Understanding the semantic structure of unstructured data — text, dialogs, images — is a critical challenge given their central role in many applications, including question answering, dialog systems, information retrieval… In recent years, there has been much interest in designing models and algorithms to automatically extract and manipulate semantic representations from raw data.
This workshop aims at gathering experts from the different fields of semantics to favor cross-fertilization, discussions and constructive debates on topics such as:
Word similarities and sense disambiguation
- Information and relation extraction
- Lexical and compositional semantics
- Learning semantic frames and semantic role labeling
- Grounded language learning
- Semantic representation for dialog understanding
- Visual scene understanding
- Multi-modal semantic representation and reasoning
The workshop will include the following invited speakers:
- Stephen Clarke (University of Cambridge)
- Pedros Domingos (University of Washington)
- Alyosha Efros (UC Berkeley)
- Tomas Mikolov (Facebook AI Research)
- Savas Parastaditis (Microsoft Cortana)
- Sebastien Riedel (University College London)
- Jeffrey Siskind (Purdue University)
- Ivan Titov (University of Amsterdam)
- Luke Zettlemoyer (University of Washington)
- Larry Zitnick (Microsoft Research)
A call for contributions will be out shortly to invite submissions of abstracts to be presented during the workshop.
More information at https://sites.google.com/site/learningsemantics2014/