Learning Distributed Representations of Texts and Entities from Knowledge Base
This addresses the challenge of integrating textual and structured knowledge for various NLP applications, representing an incremental improvement over existing methods.
The authors tackled the problem of learning joint distributed representations for texts and knowledge base entities by training a neural network model to predict relevant entities from text, achieving state-of-the-art results on sentence textual similarity, entity linking, and factoid question answering tasks.
We describe a neural network model that jointly learns distributed representations of texts and knowledge base (KB) entities. Given a text in the KB, we train our proposed model to predict entities that are relevant to the text. Our model is designed to be generic with the ability to address various NLP tasks with ease. We train the model using a large corpus of texts and their entity annotations extracted from Wikipedia. We evaluated the model on three important NLP tasks (i.e., sentence textual similarity, entity linking, and factoid question answering) involving both unsupervised and supervised settings. As a result, we achieved state-of-the-art results on all three of these tasks. Our code and trained models are publicly available for further academic research.