Difference between revisions of "NL Grounding Reading Group"
From PublicWiki
(→Grounding in Graphics / Vision) |
(→Grounded Robot Commands) |
||
Line 107: | Line 107: | ||
* [http://www.umiacs.umd.edu/~cteo/public-shared/ICRA2012_ActionObjects_preprint.pdf Towards a Watson That Sees: Language-Guided Action Recognition for Robots]. Ching L. Teo, Yezhou Yang, Hal Daume III, Cornelia Ferm ´ uller and Yiannis Aloimonos. | * [http://www.umiacs.umd.edu/~cteo/public-shared/ICRA2012_ActionObjects_preprint.pdf Towards a Watson That Sees: Language-Guided Action Recognition for Robots]. Ching L. Teo, Yezhou Yang, Hal Daume III, Cornelia Ferm ´ uller and Yiannis Aloimonos. | ||
* [http://people.csail.mit.edu/stefie10/publications/tellex11.pdf Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation]. Stefanie Tellex*, Thomas Kollar*, Steven Dickerson*, Matthew R. Walter, Ashis Gopal Banerjee, Seth Teller, Nicholas Roy. | * [http://people.csail.mit.edu/stefie10/publications/tellex11.pdf Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation]. Stefanie Tellex*, Thomas Kollar*, Steven Dickerson*, Matthew R. Walter, Ashis Gopal Banerjee, Seth Teller, Nicholas Roy. | ||
+ | * [http://homes.cs.washington.edu/~cynthia/Pubs/MatuszekISER2012.pdf Learning to Parse Natural Language Commands to a Robot Control System]. Cynthia Matuszek, Evan Herbst, Luke Zettlemoyer, Dieter Fox. | ||
+ | * [http://hrilab.cs.tufts.edu/publications/cantrelletal12hri.pdf Tell me when and why to do it!: run-time planner model updates via natural language instruction]. Rehj Cantrell, Kartik Talamadupula, Paul Schermerhorn, J. Benton, Subbarao Kambhampati, Matthias Scheutz | ||
====Grounding in Graphics / Vision==== | ====Grounding in Graphics / Vision==== |
Revision as of 22:00, 10 October 2012
This is the wiki page for topics to be discussed in the NL grounding reading group.
When: Wednesdays, 3:30pm
Where: CSE 203
We also have a mailing list (https://mailman.cs.washington.edu/mailman/listinfo/grounding).
Contact: cynthia@cs
Contents
Schedule: Autumn 2012
Date | Paper | Authors | Venue | Leader | Info |
---|---|---|---|---|---|
Oct 3 | Learning to Connect Language and Perception | Raymond J. Mooney | AAAI 2008 | Cynthia | |
Oct 10 | Approaching the Symbol Grounding Problem with Probabilistic Graphical Models | S. Tellex, T. Kollar, S. Dickerson, M. R. Walter, A. G. Banerjee, S. Teller, N. Roy | AI Magazine. 32(4) | Nicholas | |
Oct 17 | |||||
Oct 24 | WordsEye: An Automatic Text-to-Scene Conversion System | Bob Coyne and Daniel Bauer and Owen Rambow. | Gabe | ||
Oct 31 | |||||
Nov 7 | |||||
Nov 14 | Yuyin | ||||
Nov 21 | |||||
Nov 28 | |||||
Dec 5 | |||||
Dec 12 |
Potential Papers
Consider these as mere suggestions! Please check papers before assigning them.
Language Games/Language Evolution
- Lingodroids: Studies in spatial cognition and language. Ruth Schulz, Arren Glover, Michael J. Milford, Gordon Wyeth, Janet Wiles.
- Lingodroids: Learning terms for time. Heath, S., Schulz, R. ; Ball, D. ; Wiles, J.
- Grounding Language through Evolutionary Language Games Luc Steels.
- The Physical Symbol Grounding Problem Paul Vogt.
- Mutual Online Concept Learning for Multiple Agents. Jun Wang, Les Gasser.
Grounded Robot Commands
- Towards a Watson That Sees: Language-Guided Action Recognition for Robots. Ching L. Teo, Yezhou Yang, Hal Daume III, Cornelia Ferm ´ uller and Yiannis Aloimonos.
- Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation. Stefanie Tellex*, Thomas Kollar*, Steven Dickerson*, Matthew R. Walter, Ashis Gopal Banerjee, Seth Teller, Nicholas Roy.
- Learning to Parse Natural Language Commands to a Robot Control System. Cynthia Matuszek, Evan Herbst, Luke Zettlemoyer, Dieter Fox.
- Tell me when and why to do it!: run-time planner model updates via natural language instruction. Rehj Cantrell, Kartik Talamadupula, Paul Schermerhorn, J. Benton, Subbarao Kambhampati, Matthias Scheutz
Grounding in Graphics / Vision
- VigNet: Grounding Language in Graphics using Frame Semantics. Bob Coyne and Daniel Bauer and Owen Rambow.
- WordsEye: An Automatic Text-to-Scene Conversion System. Bob Coyne, Richard Sproat.
- A Database for Fine Grained Activity Detection of Cooking Activities. Marcus Rohrbach, Sikandar Amin, Mykhaylo Andriluka, Bernt Schiele. CVPR 2012.