Schedule

April 14: Preliminaries
Speaker: Alexander Koller - slides

Meeting 1: Friday, June 4

10:15-11:45 Ungrounded models of meaning
Speaker: Michaela Regneri

• Chambers & Jurafsky (2008), "Unsupervised learning of narrative event chains". Proceedings of ACL.
• Chambers & Jurafsky (2009), "Unsupervised learning of narrative schemas and their participants". Proceedings of ACL.

12:45-14:15 Language-learning robots
Speaker: Geert-Jan Kruijff

• Kruijff et al. (2007), "Situated dialogue and spatial organization: What, where ... and why?". International Journal of Advanced Robotic Systems.
• Gold & Scassellati (2007), "A robot that uses existing vocabulary to infer non-visual word meaning from observation". Proceedings of AAAI.

14:30-16:00 Learning grounded models from visual data
Speaker: Boris Fersing

• Feldman et al. (1996). "L0: The First Five Years". Artificial Intelligence Review.
• Marszalek et al. (2009). "Actions in context". Proceedings of CVPR.

Meeting 2: Sunday, June 13

9:30-11:00 Acquiring grounded language from games
Speaker: Jingwen Hu

• Ahn & Dabbish (2004), "Labeling images with a computer game". Proceedings of SIGCHI.
• Orkin & Roy (2007), "The restaurant game: Learning social behavior and language from thousands of players online". Journal of Game Development.
• Fleischman & Roy (2005), "Intentional context in situated language learning". Proceedings of CoNLL.

11:15-12:45 Sports reporting
Speaker: Charles LaRosse

• Chen et al. (2010), "Training a multilingual sportscaster: Using perceptual context to learn language". Journal of AI Research.
• Snyder & Barzilay (2007), "Database-Text alignment via structured multilabel classification". Proceedings of IJCAI.

13:30-15:00 Windows GUI actions
Speaker: Prashanth Nagabhushanarao

• Branavan et al. (2009), "Reinforcement learning for mapping instructions to actions". Proceedings of ACL.
• Branavan et al. (2010), "Reading between the lines: Learning to map high-level instructions to commands". Proceedings of ACL.

15:15-16:45 Situated communication in virtual environments
Speaker: Andrew Gargett

• Koller et al. (2010), "The First GIVE Challenge". In Krahmer & Theune, "Empirical Methods in Natural Language Generation", Springer.
• Dionne et al. (2009), "GUIDE". System description, GIVE-1 Challenge.
• Garoufi & Koller (2010), "Automated planning for situated natural language generation". Proceedings of ACL.
• MacMahon & Kuipers (2006), "Walk the talk: Connecting language, knowledge, and action in route instructions". Proceedings of AAAI.
• Zukerman et al. (2009), "Towards the interpretation of utterance sequences in a dialogue system". Proceedings of SIGDial.

Meeting 3: Friday, June 25

10:15-11:45 Grounded language learning in humans
Speaker: Judith Köhne

• (literature will follow)

12:45-14:15 Grounded models of language evolution
Speaker: Fai Greeve

• Kirby (2002), "Learning, bottlenecks, and the evolution of recursive syntax". In T. Briscoe (ed.), "Linguistic Evolution through Language Acquisition: Formal and Computational Models", Cambridge University Press.
• Steels & Loetzsch (2008), "Perspective alignment in spatial language". In Coventry et al. (eds.), "Spatial Language and Dialogue". Oxford University Press.

14:30-16:00 Grounding in parsing and generation
Speaker: Alexander Koller

• Schuler (2001), "Computational properties of environment-based disambiguation". Proceedings of ACL.
• Gorniak & Roy (2005), "Probabilistic grounding of situated speech using plan recognition and reference resolution". Proceedings of ICMI.
• Reiter et al. (2005), "Choosing words in computer-generated weather forecasts". AI Journal.
• Kelleher & van Genabith (2004), "Visual salience and reference resolution in simulated 3-D environments". Artificial Intelligence Review.