KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
This addresses the integration of knowledge and language for NLP researchers, offering a novel approach that is not purely incremental but combines existing ideas in a unified framework.
The paper tackles the problem that pre-trained language models (PLMs) poorly capture factual knowledge, while knowledge embedding (KE) methods underutilize textual information, by proposing KEPLER, a unified model that integrates factual knowledge into PLMs and enhances KE with text. It achieves state-of-the-art results on various NLP tasks and excels as an inductive KE model on knowledge graph link prediction, with the creation of Wikidata5M as a new benchmark dataset.
Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. In contrast, knowledge embedding (KE) methods can effectively represent the relational facts in knowledge graphs (KGs) with informative entity embeddings, but conventional KE models cannot take full advantage of the abundant textual information. In this paper, we propose a unified model for Knowledge Embedding and Pre-trained LanguagE Representation (KEPLER), which can not only better integrate factual knowledge into PLMs but also produce effective text-enhanced KE with the strong PLMs. In KEPLER, we encode textual entity descriptions with a PLM as their embeddings, and then jointly optimize the KE and language modeling objectives. Experimental results show that KEPLER achieves state-of-the-art performances on various NLP tasks, and also works remarkably well as an inductive KE model on KG link prediction. Furthermore, for pre-training and evaluating KEPLER, we construct Wikidata5M, a large-scale KG dataset with aligned entity descriptions, and benchmark state-of-the-art KE methods on it. It shall serve as a new KE benchmark and facilitate the research on large KG, inductive KE, and KG with text. The source code can be obtained from https://github.com/THU-KEG/KEPLER.