Overview

The 1st Workshop on Representation Learning for NLP (RepL4NLP) will be held on August 11, 2016 and hosted by the 54rd Annual Meeting of the Association for Computational Linguistics (ACL) in Berlin, Germany. The workshop is being organised by Phil Blunsom, Kyunghyun Cho, Shay Cohen, Edward Grefenstette, Karl Moritz Hermann, Laura Rimell, Jason Weston, and Scott Wen-tau Yih, and will be sponsored by Google DeepMind, Facebook AI Research, and Microsoft Research.

Representation Learning for NLP aims to continue the spirit of previously successful workshops at ACL/NAACL/EACL, namely VSM at NAACL’15 and CVSC at ACL’13/EACL’14/ACL’15, which focussed on vector space models of meaning, compositionality, and the application of deep neural networks and spectral methods to NLP. It will provide a forum for discussing recent advances on these topics, as well as future research directions in linguistically motivated vector-based models in NLP.

Key Dates
  • Deadline for paper submission: 15 May 2016 (extended)
  • Notification of acceptance: 5 June 2016
  • Camera ready submission due: 22 June 2016
  • Early registration deadline (ACL'16)To be announced.
  • Workshop: 11 August 2016
Keynote Speakers
Topics
  • Analysis of language using eigenvalue, singular value and tensor decompositions
  • Distributional compositional semantics
  • Integration of distributional representations with other models
  • Knowledge base embedding
  • Language modeling for automatic speech recognition, statistical machine translation, and information retrieval
  • Language modeling for logical and natural reasoning
  • Latent-variable and representation learning for language
  • Multi-modal learning for distributional representations
  • Neural networks and deep learning in NLP
  • The role of syntax in compositional models
  • Spectral learning and the method of moments in NLP
  • Word embeddings and their applications
Related Workshops
Prospective attendees of RepL4NLP may be interested in the following companion workshop, also collocated with ACL: the 1st Workshop on Evaluating Vector-Space Representations for NLP, organised by Omer Levy, Felix Hill, Roi Reichart, Kyunghyun Cho, Anna Korhonen, Yoav Goldberg, and Antoine Bordes. We expect the topics covered by both workshops to complement one another well, and encourage ACL attendees to consider attending both.