arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.07226cs.CL
收藏

基于事件知识的内隐论元预测

Implicit Argument Prediction with Event Knowledge

The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Pengxiang Cheng, Katrin Erk

摘要:

隐式参数在语法上与其谓词没有联系,因此很难提取。以前的工作使用具有大量特征的模型,在非常小的数据集上进行评估。我们提出训练模型的隐式论点预测一个简单的完形填空任务,数据可以自动生成的规模。这使我们能够使用神经模型,该模型利用叙事连贯性和实体显著性进行预测。我们表明,我们的模型在合成和自然数据上都具有优越的性能。

英文摘要:

Implicit arguments are not syntactically connected to their predicates, and are therefore hard to extract. Previous work has used models with large numbers of features, evaluated on very small datasets. We propose to train models for implicit argument prediction on a simple cloze task, for which data can be generated automatically at scale. This allows us to use a neural model, which draws on narrative coherence and entity salience for predictions. We show that our model has superior performance on both synthetic and natural data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑