Entity Search Based on the Representation Learning Model With Different Embedding Strategies

Abstract

We focus on the problem of learning distributed representations for entity search queries, named entities, and their short descriptions. With our representation learning models, the entity search query, named entity, and description can be represented as low-dimensional vectors with minimal human preprocessing. Our goal is to develop a simple but effective model that can make the distributed representations of query-related entities similar to the query representation in the vector space. Hence, we propose three kinds of learning strategies, and the difference between them mainly lies in how to deal with the relationship between an entity and its description. We analyze the strengths and weaknesses of each learning strategy and validate our methods on public data sets, which contain various query types and different languages (i.e., English and Chinese). The experimental results indicate that our proposed methods can adapt to different types of entity search queries, and outperform the current state-of-the-art methods no matter the entity collection is homogeneous or heterogeneous. Besides, the proposed methods can be trained fast and can be easily extended to other similar tasks.

Keywords

• Entity search
• entity embedding
• language model
• representation learning