Paper Info
Title
Unsupervised PCFG induction for grounded language learning with highly ambiguous supervision
Abstract
"Grounded" language learning employs training data in the form of sentences paired with relevant but ambiguous perceptual contexts. Börschinger et al. (2011) introduced an approach to grounded language learning based on unsupervised PCFG induction. Their approach works well when each sentence potentially refers to one of a small set of possible meanings, such as in the sportscasting task. However, it does not scale to problems with a large set of potential meanings for each sentence, such as the navigation instruction following task studied by Chen and Mooney (2011). This paper presents an enhancement of the PCFG approach that scales to such problems with highly-ambiguous supervision. Experimental results on the navigation task demonstrates the effectiveness of our approach.
Year
Venue
Keywords
2012
EMNLP-CoNLL
language learning,pcfg approach,unsupervised pcfg induction,ambiguous perceptual context,large set,small set,ambiguous supervision,navigation instruction,sportscasting task,navigation task
Field
DocType
Volume
Training set,Chen,Computer science,Speech recognition,Language acquisition,Artificial intelligence,Natural language processing,Sentence,Perception,Small set,Machine learning
Conference
D12-1
Citations 
PageRank 
References 
25
0.89
22
Authors
2
Name
Order
Citations
PageRank
Joohyun Kim129222.75
Raymond J. Mooney210408961.10