arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.02710cs.CLcs.AI
收藏

混合匹配:基于高斯混合嵌入的可扩展对话响应检索

Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings

IBM Research(IBM研究院)

Gaurav Pandey, Danish Contractor, Sachindra Joshi

摘要:

基于嵌入的对话响应检索方法将上下文响应对嵌入为嵌入空间中的点。这些方法是可扩展的,但无法解释上下文响应对之间存在的复杂的多对多关系。另一方面,有一些方法通过多层神经网络联合提供上下文-响应对。这些方法可以模拟上下文-响应对之间的复杂关系,但当响应集适度大(>100)时无法扩展。在本文中,我们通过提出一个可扩展的模型,可以学习上下文响应对之间的复杂关系,结合了这两个世界的最佳。具体而言,该模型将上下文以及响应映射到嵌入空间上的概率分布。我们通过优化由训练数据中的上下文响应对引起的分布之间的Kullback-Leibler散度来训练模型。我们表明,所得到的模型实现了更好的性能相比,其他基于嵌入的方法公开可用的会话数据。

英文摘要:

Embedding-based approaches for dialog response retrieval embed the context-response pairs as points in the embedding space. These approaches are scalable, but fail to account for the complex, many-to-many relationships that exist between context-response pairs. On the other end of the spectrum, there are approaches that feed the context-response pairs jointly through multiple layers of neural networks. These approaches can model the complex relationships between context-response pairs, but fail to scale when the set of responses is moderately large (>100). In this paper, we combine the best of both worlds by proposing a scalable model that can learn complex relationships between context-response pairs. Specifically, the model maps the contexts as well as responses to probability distributions over the embedding space. We train the models by optimizing the Kullback-Leibler divergence between the distributions induced by context-response pairs in the training data. We show that the resultant model achieves better performance as compared to other embedding-based approaches on publicly available conversation data.

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。

↑