arXiv 1805.040442018-05-10cs.CL

用于自动分类归纳的端到端强化学习

End-to-End Reinforcement Learning for Automatic Taxonomy Induction

University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Southern California（南加州大学）；Department of Computer Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系）

Yuning Mao, Xiang Ren, Jiaming Shen, Xiaotao Gu, Jiawei Han

备注：: 11 Pages. ACL 2018 Camera Ready

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

我们提出了一种新的端到端的强化学习方法，从一组术语自动分类归纳。虽然现有方法将问题视为两阶段任务（即，检测上位对，然后将这些对组织成树结构的层次结构），我们认为这种两阶段方法可能会遭受错误传播，并且不能有效地优化捕获分类法的整体结构的度量。在我们的方法中，使用多个信息源学习术语对的表示，并用于确定要选择的\textit{which}术语和通过策略网络将其放置在分类上的\textit{where}。所有组件都以端到端的方式进行训练，并通过训练分类上的整体树度量进行累积奖励。在两个不同领域的公共数据集上的实验表明，该方法在祖先F1上的分类归纳性能优于现有的最先进的分类归纳方法高达19.6%.

英文摘要：

We present a novel end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms. While prior methods treat the problem as a two-phase task (i.e., detecting hypernymy pairs followed by organizing these pairs into a tree-structured hierarchy), we argue that such two-phase methods may suffer from error propagation, and cannot effectively optimize metrics that capture the holistic structure of a taxonomy. In our approach, the representations of term pairs are learned using multiple sources of information and used to determine \textit{which} term to select and \textit{where} to place it on the taxonomy via a policy network. All components are trained in an end-to-end manner with cumulative rewards, measured by a holistic tree metric over the training taxonomies. Experiments on two public datasets of different domains show that our approach outperforms prior state-of-the-art taxonomy induction methods up to 19.6\% on ancestor F1.

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。

摘要：

英文摘要：

相关论文