2016 · 114 citations · 20 references
ComputingComputer ScienceComputational LinguisticsNatural Language ProcessingPragmaticsDialogue SystemsLanguage ModelingLanguage ModelsNatural Language GenerationPragmatic InferencePragmatic SemanticsCaptioning TechnologyConversational InferenceLanguage GenerationListener BehaviorPragmatic UnderstandingPragmatics Of DialogueReferring Expression UnderstandingSpoken Language Generation
We present a model for contrastively describing scenes, in which context-specific behavior results from a combination of inferencedriven pragmatics and learned semantics. Like previous learned approaches to language generation, our model uses a simple featuredriven architecture (here a pair of neural "listener" and "speaker" models) to ground language in the world. Like inference-driven approaches to pragmatics, our model actively reasons about listener behavior when selecting utterances. For training, our approach requires only ordinary captions, annotated without demonstration of the pragmatic behavior the model ultimately exhibits. In human evaluations on a referring expression game, our approach succeeds 81% of the time, compared to 69% using existing techniques.
20
Explaining and Harnessing Adversarial Examples
Ian Goodfellow, Jonathon Shlens, Christian Szegedy · arXiv (Cornell University) · 2014 · 8.2K citations · Full text
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Kelvin Xu, Jimmy Ba, Ryan Kiros et al. · arXiv (Cornell University) · 2015 · 7.5K citations · Full text
Long-term recurrent convolutional networks for visual recognition and description
Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama et al. · 2015 · 5.3K citations
Generation and Comprehension of Unambiguous Object Descriptions
Junhua Mao, Jonathan Huang, Alexander Toshev et al. · 2016 · 1.2K citations