Learning Semantic Correspondences with Less Supervision
P. Liang, M. Jordan, и D. Klein. Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, стр. 91--99. Suntec, Singapore, Association for Computational Linguistics, (августа 2009)
Аннотация
A central problem in grounded language acquisition
is learning the correspondences between a
rich world state and a stream of text which references
that world state. To deal with the high degree
of ambiguity present in this setting, we present
a generative model that simultaneously segments
the text into utterances and maps each utterance
to a meaning representation grounded in the world
state. We show that our model generalizes across
three domains of increasing difficulty—Robocup
sportscasting, weather forecasts (a new domain),
and NFL recaps.
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP
%0 Conference Paper
%1 citeulike:5971394
%A Liang, Percy
%A Jordan, Michael
%A Klein, Dan
%B Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP
%C Suntec, Singapore
%D 2009
%I Association for Computational Linguistics
%K related semantics nlp2rdf_relevant
%P 91--99
%T Learning Semantic Correspondences with Less Supervision
%U http://www.aclweb.org/anthology/P/P09/P09-1011.pdf
%X A central problem in grounded language acquisition
is learning the correspondences between a
rich world state and a stream of text which references
that world state. To deal with the high degree
of ambiguity present in this setting, we present
a generative model that simultaneously segments
the text into utterances and maps each utterance
to a meaning representation grounded in the world
state. We show that our model generalizes across
three domains of increasing difficulty—Robocup
sportscasting, weather forecasts (a new domain),
and NFL recaps.
@inproceedings{citeulike:5971394,
abstract = {A central problem in grounded language acquisition
is learning the correspondences between a
rich world state and a stream of text which references
that world state. To deal with the high degree
of ambiguity present in this setting, we present
a generative model that simultaneously segments
the text into utterances and maps each utterance
to a meaning representation grounded in the world
state. We show that our model generalizes across
three domains of increasing difficulty—Robocup
sportscasting, weather forecasts (a new domain),
and NFL recaps.},
added-at = {2010-01-13T11:03:03.000+0100},
address = {Suntec, Singapore},
author = {Liang, Percy and Jordan, Michael and Klein, Dan},
biburl = {https://www.bibsonomy.org/bibtex/277469b23022ac7e380a53969bc7d7674/sebastian},
booktitle = {Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP},
citeulike-article-id = {5971394},
citeulike-linkout-0 = {http://www.aclweb.org/anthology-new/P/P09/P09-1011.bib},
citeulike-linkout-1 = {http://www.aclweb.org/anthology-new/P/P09/P09-1011.pdf},
interhash = {e5a42da26c90925e5b86ff3c90bc6e54},
intrahash = {77469b23022ac7e380a53969bc7d7674},
keywords = {related semantics nlp2rdf_relevant},
month = {August},
pages = {91--99},
posted-at = {2009-10-19 15:27:16},
priority = {2},
publisher = {Association for Computational Linguistics},
timestamp = {2013-07-07T16:28:17.000+0200},
title = {Learning Semantic Correspondences with Less Supervision},
url = {http://www.aclweb.org/anthology/P/P09/P09-1011.pdf},
year = 2009
}