Towards Understanding Situated Natural Language

Antoine Bordes, Nicolas Usunier, Ronan Collobert, Jason Weston
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9:65-72, 2010.

Abstract

We present a general framework and learning algorithm for the task of concept labeling: each word in a given sentence has to be tagged with the unique physical entity (e.g. person, object or location) or abstract concept it refers to. Our method allows both world knowledge and linguistic information to be used during learning and prediction. We show experimentally that we can learn to use world knowledge to resolve ambiguities in language, such as word senses or reference resolution, without the use of handcrafted rules or features.

Cite this Paper


BibTeX
@InProceedings{pmlr-v9-bordes10a, title = {Towards Understanding Situated Natural Language}, author = {Bordes, Antoine and Usunier, Nicolas and Collobert, Ronan and Weston, Jason}, booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics}, pages = {65--72}, year = {2010}, editor = {Teh, Yee Whye and Titterington, Mike}, volume = {9}, series = {Proceedings of Machine Learning Research}, address = {Chia Laguna Resort, Sardinia, Italy}, month = {13--15 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v9/bordes10a/bordes10a.pdf}, url = { http://proceedings.mlr.press/v9/bordes10a.html }, abstract = {We present a general framework and learning algorithm for the task of concept labeling: each word in a given sentence has to be tagged with the unique physical entity (e.g. person, object or location) or abstract concept it refers to. Our method allows both world knowledge and linguistic information to be used during learning and prediction. We show experimentally that we can learn to use world knowledge to resolve ambiguities in language, such as word senses or reference resolution, without the use of handcrafted rules or features.} }
Endnote
%0 Conference Paper %T Towards Understanding Situated Natural Language %A Antoine Bordes %A Nicolas Usunier %A Ronan Collobert %A Jason Weston %B Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2010 %E Yee Whye Teh %E Mike Titterington %F pmlr-v9-bordes10a %I PMLR %P 65--72 %U http://proceedings.mlr.press/v9/bordes10a.html %V 9 %X We present a general framework and learning algorithm for the task of concept labeling: each word in a given sentence has to be tagged with the unique physical entity (e.g. person, object or location) or abstract concept it refers to. Our method allows both world knowledge and linguistic information to be used during learning and prediction. We show experimentally that we can learn to use world knowledge to resolve ambiguities in language, such as word senses or reference resolution, without the use of handcrafted rules or features.
RIS
TY - CPAPER TI - Towards Understanding Situated Natural Language AU - Antoine Bordes AU - Nicolas Usunier AU - Ronan Collobert AU - Jason Weston BT - Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics DA - 2010/03/31 ED - Yee Whye Teh ED - Mike Titterington ID - pmlr-v9-bordes10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 9 SP - 65 EP - 72 L1 - http://proceedings.mlr.press/v9/bordes10a/bordes10a.pdf UR - http://proceedings.mlr.press/v9/bordes10a.html AB - We present a general framework and learning algorithm for the task of concept labeling: each word in a given sentence has to be tagged with the unique physical entity (e.g. person, object or location) or abstract concept it refers to. Our method allows both world knowledge and linguistic information to be used during learning and prediction. We show experimentally that we can learn to use world knowledge to resolve ambiguities in language, such as word senses or reference resolution, without the use of handcrafted rules or features. ER -
APA
Bordes, A., Usunier, N., Collobert, R. & Weston, J.. (2010). Towards Understanding Situated Natural Language. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 9:65-72 Available from http://proceedings.mlr.press/v9/bordes10a.html .

Related Material