Learning Disentangled Representations of Texts with Application to Biomedical Abstracts.

Learning Disentangled Representations of Texts with Application to Biomedical Abstracts.
复制标题

DOI:
10.18653/v1/d18-1497
复制
发表时间:
2018-10
期刊:
Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing
影响因子:
--
通讯作者:
Wallace BC
Wallace BC
中科院分区:
其他
文献类型:
--
作者:
Jain S;Banner E;van de Meent JW;Marshall IJ;Wallace BC

文献摘要

参考文献

相似文献

我们提出了一种方法,用于学习不同的和互补的方面的代码的文本的解开表示,提供有效的模型转移和可解释性的目的。为了诱导解开嵌入,我们提出了一个对抗性的目标的基础上(dissimilarity)之间的三元组的文件相对于特定的方面。我们的激励应用程序是嵌入生物医学摘要描述临床试验的方式,解开人口,干预措施和结果在一个给定的试验。我们表明,我们的方法学习表示编码这些临床上突出的方面,这些可以有效地用于执行特定方面的检索。我们证明了这种方法的推广超出了我们的激励应用在两个多方面的评论语料库的实验。
We propose a method for learning disentangled representations of texts that code for distinct and complementary aspects, with the aim of affording efficient model transfer and interpretability. To induce disentangled embeddings, we propose an adversarial objective based on the (dis)similarity between triplets of documents with respect to specific aspects. Our motivating application is embedding biomedical abstracts describing clinical trials in a manner that disentangles the populations, interventions, and outcomes in a given trial. We show that our method learns representations that encode these clinically salient aspects, and that these can be effectively used to perform aspect-specific retrieval. We demonstrate that the approach generalizes beyond our motivating application in experiments on two multi-aspect review corpora.
DOI: 10.1162/jmlr.2003.3.4-5.993
发表时间: 2003-05-15
影响因子: 6
作者:
Blei, DM;Ng, AY;Jordan, MI
通讯作者: Jordan, MI