A Systematic Investigation of KB-Text Embedding Alignment at Scale
arXiv:2106.01586
Abstract
Knowledge bases (KBs) and text often contain complementary knowledge: KBs store structured knowledge that can support long range reasoning, while text stores more comprehensive and timely knowledge in an unstructured way. Separately embedding the individual knowledge sources into vector spaces has demonstrated tremendous successes in encoding the respective knowledge, but how to jointly embed and reason with both knowledge sources to fully leverage the complementary information is still largely an open problem. We conduct a large-scale, systematic investigation of aligning KB and text embeddings for joint reasoning. We set up a novel evaluation framework with two evaluation tasks, few-shot link prediction and analogical reasoning, and evaluate an array of KB-text embedding alignment methods. We also demonstrate how such alignment can infuse textual information into KB embeddings for more accurate link prediction on emerging entities and events, using COVID-19 as a case study.
arXiv commentAccepted to ACL-IJCNLP 2021. 11 pages, 2 figures
References in corpus (7)
- Distributed Representations of Words and Phrases and their Compositionality
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Exploiting Similarities among Languages for Machine Translation
- HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
- A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- Type-Constrained Representation Learning in Knowledge Graphs