arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.04601cs.CL
收藏

MUSE:模块化无监督意义嵌入

MUSE: Modularizing Unsupervised Sense Embeddings

National Taiwan University(台湾大学);Massachusetts Institute of Technology(麻省理工学院)

Guang-He Lee, Yun-Nung Chen

摘要:

本文提出了一种无监督的方式来解决词义歧义问题,其中词义表示是沿着给定上下文的词义选择机制来学习的。以前的工作集中在设计一个单一的模型来提供这两种机制,因此遭受粗粒度的表示学习或低效的意义选择。建议的模块化方法,MUSE,实现灵活的模块,以优化不同的机制,实现第一个纯意义级的表示学习系统与线性时间的意义选择。我们利用强化学习来实现对所提出的模块的联合训练,并在意义选择上引入各种探索技术以提高鲁棒性。在基准数据上的实验表明,该方法在同义词选择和上下文词相似度方面达到了MaxSimC的最佳性能。

英文摘要:

This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts. Prior work focused on designing a single model to deliver both mechanisms, and thus suffered from either coarse-grained representation learning or inefficient sense selection. The proposed modular approach, MUSE, implements flexible modules to optimize distinct mechanisms, achieving the first purely sense-level representation learning system with linear-time sense selection. We leverage reinforcement learning to enable joint training on the proposed modules, and introduce various exploration techniques on sense selection for better robustness. The experiments on benchmark data show that the proposed approach achieves the state-of-the-art performance on synonym selection as well as on contextual word similarities in terms of MaxSimC.

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。

↑