Modeling Semantic Expectation: Using Script Knowledge for Referent Prediction
Modeling Semantic Expectation: Using Script Knowledge for Referent Prediction
复制标题
建模语义期望:使用脚本知识进行指示预测
DOI:
10.1162/tacl_a_00044
复制
发表时间:
2017
影响因子:
10.9
通讯作者:
M. Pinkal
中科院分区:
文献类型:
--
作者:
A. Modi;I. Titov;V. Demberg;A. Sayeed;M. Pinkal
Recent research in psycholinguistics has provided increasing evidence that humans predict upcoming content. Prediction also affects perception and might be a key to robustness in human language processing. In this paper, we investigate the factors that affect human prediction by building a computational model that can predict upcoming discourse referents based on linguistic knowledge alone vs. linguistic knowledge jointly with common-sense knowledge in the form of scripts. We find that script knowledge significantly improves model estimates of human predictions. In a second study, we test the highly controversial hypothesis that predictability influences referring expression type but do not find evidence for such an effect.
登录
查看更多内容
DOI:
--
发表时间:
2014-05
期刊:
--
影响因子:
--
作者:
Jan A. Botha;Phil Blunsom
通讯作者:
Jan A. Botha;Phil Blunsom
影响因子:
3.8
作者:
Alessandra Zarcone;Marten van Schijndel;J. Vogels;Vera Demberg
通讯作者:
Vera Demberg
DOI:
--
发表时间:
1994
期刊:
影响因子:
--
作者:
R. Stevenson;R. Crawley;D. Kleinman
通讯作者:
D. Kleinman
DOI:
--
发表时间:
2009
期刊:
影响因子:
--
作者:
Harry J. Tily;S. Piantadosi
通讯作者:
S. Piantadosi
DOI:
--
发表时间:
2016
期刊:
RepEval@ACL
影响因子:
--
作者:
A. Sayeed;Clayton Greenberg;Vera Demberg
通讯作者:
Vera Demberg