Semantic Entity Retrieval Toolkit
This toolkit addresses the need for accessible and flexible tools in natural language processing for researchers and practitioners working with entity representations, but it is incremental as it builds on existing models.
The authors introduced the Semantic Entity Retrieval Toolkit (SERT), which implements their previously published models for learning semantic representations of words and entities, providing a unified interface, GPU support, and customization options for tasks like entity ranking and downstream applications.
Unsupervised learning of low-dimensional, semantic representations of words and entities has recently gained attention. In this paper we describe the Semantic Entity Retrieval Toolkit (SERT) that provides implementations of our previously published entity representation models. The toolkit provides a unified interface to different representation learning algorithms, fine-grained parsing configuration and can be used transparently with GPUs. In addition, users can easily modify existing models or implement their own models in the framework. After model training, SERT can be used to rank entities according to a textual query and extract the learned entity/word representation for use in downstream algorithms, such as clustering or recommendation.