Opportunistic Active Learning for Grounding Natural Language Descriptions

Jesse Thomason, Aishwarya Padmakumar, Jivko Sinapov, Justin Hart, Peter Stone, Raymond J. Mooney
Proceedings of the 1st Annual Conference on Robot Learning, PMLR 78:67-76, 2017.

Abstract

Active learning identifies data points from a pool of unlabeled examples whose labels, if made available, are most likely to improve the predictions of a supervised model. Most research on active learning assumes that an agent has access to the entire pool of unlabeled data and can ask for labels of any data points during an initial training phase. However, when incorporated in a larger task, an agent may only be able to query some subset of the unlabeled pool. An agent can also opportunistically query for labels that may be useful in the future, even if they are not immediately relevant. In this paper, we demonstrate that this type of opportunistic active learning can improve performance in grounding natural language descriptions of everyday objects—an important skill for home and office robots. We find, with a real robot in an object identification setting, that inquisitive behavior—asking users important questions about the meanings of words that may be off-topic for the current dialog—leads to identifying the correct object more often over time.

Cite this Paper

BibTeX
@InProceedings{pmlr-v78-thomason17a, title = {Opportunistic Active Learning for Grounding Natural Language Descriptions}, author = {Thomason, Jesse and Padmakumar, Aishwarya and Sinapov, Jivko and Hart, Justin and Stone, Peter and Mooney, Raymond J.}, booktitle = {Proceedings of the 1st Annual Conference on Robot Learning}, pages = {67--76}, year = {2017}, editor = {Levine, Sergey and Vanhoucke, Vincent and Goldberg, Ken}, volume = {78}, series = {Proceedings of Machine Learning Research}, month = {13--15 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v78/thomason17a/thomason17a.pdf}, url = {https://proceedings.mlr.press/v78/thomason17a.html}, abstract = {Active learning identifies data points from a pool of unlabeled examples whose labels, if made available, are most likely to improve the predictions of a supervised model. Most research on active learning assumes that an agent has access to the entire pool of unlabeled data and can ask for labels of any data points during an initial training phase. However, when incorporated in a larger task, an agent may only be able to query some subset of the unlabeled pool. An agent can also opportunistically query for labels that may be useful in the future, even if they are not immediately relevant. In this paper, we demonstrate that this type of opportunistic active learning can improve performance in grounding natural language descriptions of everyday objects—an important skill for home and office robots. We find, with a real robot in an object identification setting, that inquisitive behavior—asking users important questions about the meanings of words that may be off-topic for the current dialog—leads to identifying the correct object more often over time.} }
Endnote
%0 Conference Paper %T Opportunistic Active Learning for Grounding Natural Language Descriptions %A Jesse Thomason %A Aishwarya Padmakumar %A Jivko Sinapov %A Justin Hart %A Peter Stone %A Raymond J. Mooney %B Proceedings of the 1st Annual Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2017 %E Sergey Levine %E Vincent Vanhoucke %E Ken Goldberg %F pmlr-v78-thomason17a %I PMLR %P 67--76 %U https://proceedings.mlr.press/v78/thomason17a.html %V 78 %X Active learning identifies data points from a pool of unlabeled examples whose labels, if made available, are most likely to improve the predictions of a supervised model. Most research on active learning assumes that an agent has access to the entire pool of unlabeled data and can ask for labels of any data points during an initial training phase. However, when incorporated in a larger task, an agent may only be able to query some subset of the unlabeled pool. An agent can also opportunistically query for labels that may be useful in the future, even if they are not immediately relevant. In this paper, we demonstrate that this type of opportunistic active learning can improve performance in grounding natural language descriptions of everyday objects—an important skill for home and office robots. We find, with a real robot in an object identification setting, that inquisitive behavior—asking users important questions about the meanings of words that may be off-topic for the current dialog—leads to identifying the correct object more often over time.
APA
Thomason, J., Padmakumar, A., Sinapov, J., Hart, J., Stone, P. & Mooney, R.J.. (2017). Opportunistic Active Learning for Grounding Natural Language Descriptions. Proceedings of the 1st Annual Conference on Robot Learning, in Proceedings of Machine Learning Research 78:67-76 Available from https://proceedings.mlr.press/v78/thomason17a.html.

Related Material