Sciweavers

Share
ACL
2010

Phrase-Based Statistical Language Generation Using Graphical Models and Active Learning

8 years 8 months ago
Phrase-Based Statistical Language Generation Using Graphical Models and Active Learning
Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to inform the generation decision process. Both approaches rely on the existence of a handcrafted generator, which limits their scalability to new domains. This paper presents BAGEL, a statistical language generator which uses dynamic Bayesian networks to learn from semantically-aligned data produced by 42 untrained annotators. A human evaluation shows that BAGEL can generate natural and informative utterances from unseen inputs in the information presentation domain. Additionally, generation performance on sparse datasets is improved significantly by using certainty-based active learning, yielding ratings close to the human gold standard with a fraction of the data.
François Mairesse, Milica Gasic, Filip Jurc
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where ACL
Authors François Mairesse, Milica Gasic, Filip Jurcícek, Simon Keizer, Blaise Thomson, Kai Yu, Steve Young
Comments (0)
books