arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.09663cs.CLcs.LGstat.ML
收藏

上下文移动者的距离和重心:构建表征的上下文最优传输

Context Mover's Distance & Barycenters: Optimal Transport of Contexts for Building Representations

EPFL(洛桑联邦理工学院);École Polytechnique(巴黎综合理工学院)

Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi

摘要:

我们提出了一个框架,用于构建实体及其组合的无监督表示,其中每个实体被视为概率分布,而不是向量嵌入。特别是,这种分布是支持的上下文,共同出现的实体,并嵌入在一个合适的低维空间。这使我们能够从最优运输的角度考虑表示学习,并利用其工具,如Wasserstein距离和重心。我们详细阐述了如何将该方法应用于获得文本的无监督表示,并说明了在测量句子相似性,词蕴涵和相似性等任务上的性能(定量和定性),其中我们根据经验观察到显着的收益(例如,相对于Sent2vec,GenSen的4.1%相对改善)。所提出的方法的主要优点包括:(a)通过将实体建模为分布来捕获不确定性和多义,(b)利用特定任务的底层几何结构(具有地面成本),(c)同时提供上下文之间的最佳传输概念的可解释性,以及(d)在现有点嵌入方法之上的简单适用性。该代码以及预构建的直方图可在https://github.com/context-mover/上获得。

英文摘要:

We present a framework for building unsupervised representations of entities and their compositions, where each entity is viewed as a probability distribution rather than a vector embedding. In particular, this distribution is supported over the contexts which co-occur with the entity and are embedded in a suitable low-dimensional space. This enables us to consider representation learning from the perspective of Optimal Transport and take advantage of its tools such as Wasserstein distance and barycenters. We elaborate how the method can be applied for obtaining unsupervised representations of text and illustrate the performance (quantitatively as well as qualitatively) on tasks such as measuring sentence similarity, word entailment and similarity, where we empirically observe significant gains (e.g., 4.1% relative improvement over Sent2vec, GenSen). The key benefits of the proposed approach include: (a) capturing uncertainty and polysemy via modeling the entities as distributions, (b) utilizing the underlying geometry of the particular task (with the ground cost), (c) simultaneously providing interpretability with the notion of optimal transport between contexts and (d) easy applicability on top of existing point embedding methods. The code, as well as prebuilt histograms, are available under https://github.com/context-mover/.

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。

↑