Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification
arXiv:2010.16068
Abstract
Relation classification aims to extract semantic relations between entity pairs from the sentences. However, most existing methods can only identify seen relation classes that occurred during training. To recognize unseen relations at test time, we explore the problem of zero-shot relation classification. Previous work regards the problem as reading comprehension or textual entailment, which have to rely on artificial descriptive information to improve the understandability of relation types. Thus, rich semantic knowledge of the relation labels is ignored. In this paper, we propose a novel logic-guided semantic representation learning model for zero-shot relation classification. Our approach builds connections between seen and unseen relations via implicit and explicit semantic representations with knowledge graph embeddings and logic rules. Extensive experimental results demonstrate that our method can generalize to unseen relation types and achieve promising improvements.
Accepted for COLING 2020
References in corpus (12)
- Label-Embedding for Image Classification
- Zero-Shot Learning by Convex Combination of Semantic Embeddings
- Zero Shot Recognition with Unreliable Attributes
- Modeling Relation Paths for Representation Learning of Knowledge Bases
- Train Once, Test Anywhere: Zero-Shot Learning for Text Classification
- DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
- RDF2Rules: Learning Rules from RDF Knowledge Bases by Mining Frequent Predicate Cycles
- Finding Influential Instances for Distantly Supervised Relation Extraction
- Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction
- The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis
- Zero-Shot Transfer Learning for Event Extraction
- On Robustness and Bias Analysis of BERT-based Relation Extraction