Embedding learning transforms discrete data entities into continuous
numerical representations, encoding features/properties of the entities.
Despite the outstanding performance reported from different embedding learning
algorithms, few efforts were devoted to structurally interpreting how features
are encoded in the learned embedding space. This work proposes EmbeddingTree, a
hierarchical embedding exploration algorithm that relates the semantics of
entity features with the less-interpretable embedding vectors. An interactive
visualization tool is also developed based on EmbeddingTree to explore
high-dimensional embeddings. The tool helps users discover nuance features of
data entities, perform feature denoising/injecting in embedding training, and
generate embeddings for unseen entities. We demonstrate the efficacy of
EmbeddingTree and our visualization tool through embeddings generated for
industry-scale merchant data and the public 30Music listening/playlists
dataset.

提出了一种层次嵌入探索算法 EmbeddingTree，通过关联语义和嵌入向量，解释了特征是如何在学习到的嵌入空间中被编码的。同时还开发了交互式可视化工具，帮助用户探索高维嵌入，并演示了在工业规模的商家数据和公开的音乐播放列表数据集上生成的嵌入的有效性。