Flexible, corpus-based modelling of Human
Plausibility Judgments
S. Padó, U. Padó, and K. Erk. Proceedings of EMNLP/CoNLL 2007, page 400--409. Prague, Czech Republic, (2007)
Abstract
In this paper, we consider the computational modelling of human plausibility judgements for verb-relation-argument triples, a task equivalent to the computation of selectional preferences. Such models have applications both in psycholinguistics and in computational linguistics.
By extending a recent model, we obtain a completely corpus-driven model for this task which achieves significant correlations with human judgements. It rivals or exceeds deeper, resource-driven models while exhibiting higher coverage. Moreover, we show that our model can be combined with deeper models to obtain better predictions than from either model alone.
%0 Conference Paper
%1 pado07:_flexib_human_plaus_judgm
%A Padó, Sebastian
%A Padó, Ulrike
%A Erk, Katrin
%B Proceedings of EMNLP/CoNLL 2007
%C Prague, Czech Republic
%D 2007
%K conference myown
%P 400--409
%T Flexible, corpus-based modelling of Human
Plausibility Judgments
%U http://www.aclweb.org/anthology/D/D07/D07-1042.pdf
%X In this paper, we consider the computational modelling of human plausibility judgements for verb-relation-argument triples, a task equivalent to the computation of selectional preferences. Such models have applications both in psycholinguistics and in computational linguistics.
By extending a recent model, we obtain a completely corpus-driven model for this task which achieves significant correlations with human judgements. It rivals or exceeds deeper, resource-driven models while exhibiting higher coverage. Moreover, we show that our model can be combined with deeper models to obtain better predictions than from either model alone.
@inproceedings{pado07:_flexib_human_plaus_judgm,
abstract = {In this paper, we consider the computational modelling of human plausibility judgements for verb-relation-argument triples, a task equivalent to the computation of selectional preferences. Such models have applications both in psycholinguistics and in computational linguistics.
By extending a recent model, we obtain a completely corpus-driven model for this task which achieves significant correlations with human judgements. It rivals or exceeds deeper, resource-driven models while exhibiting higher coverage. Moreover, we show that our model can be combined with deeper models to obtain better predictions than from either model alone.},
added-at = {2017-04-03T19:28:28.000+0200},
address = {Prague, Czech Republic},
author = {Padó, Sebastian and Padó, Ulrike and Erk, Katrin},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/219390728d8ebbbf351dc1276699d74fd/sp},
booktitle = {Proceedings of EMNLP/CoNLL 2007},
interhash = {c9a70c1552fa89b7b37d25c3da338333},
intrahash = {19390728d8ebbbf351dc1276699d74fd},
keywords = {conference myown},
pages = {400--409},
timestamp = {2024-02-22T12:36:15.000+0100},
title = {Flexible, corpus-based modelling of Human
Plausibility Judgments},
url = {http://www.aclweb.org/anthology/D/D07/D07-1042.pdf},
year = 2007
}