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:
影响因子:
--
通讯作者:
Wallace BC
中科院分区:
文献类型:
--
作者:
Jain S;Banner E;van de Meent JW;Marshall IJ;Wallace BC
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.
影响因子:
6
作者:
Blei, DM;Ng, AY;Jordan, MI
通讯作者:
Jordan, MI