Direct Fact Retrieval from Knowledge Graphs without Entity Linking

TL;DR

This paper introduces DiFaR, a direct knowledge graph fact retrieval method that embeds facts into a dense space and retrieves them based on similarity, avoiding complex entity linking steps.

Contribution

The paper presents a novel direct retrieval framework for KGs that simplifies the process by embedding facts and using similarity search, outperforming traditional multi-step methods.

Findings

DiFaR significantly outperforms baseline methods in fact retrieval tasks.

Embedding facts in a dense space enables efficient and accurate retrieval.

Refinement with a reranker improves the relevance of retrieved facts.

Abstract

There has been a surge of interest in utilizing Knowledge Graphs (KGs) for various natural language processing/understanding tasks. The conventional mechanism to retrieve facts in KGs usually involves three steps: entity span detection, entity disambiguation, and relation classification. However, this approach requires additional labels for training each of the three subcomponents in addition to pairs of input texts and facts, and also may accumulate errors propagated from failures in previous steps. To tackle these limitations, we propose a simple knowledge retrieval framework, which directly retrieves facts from the KGs given the input text based on their representational similarities, which we refer to as Direct Fact Retrieval (DiFaR). Specifically, we first embed all facts in KGs onto a dense embedding space by using a language model trained by only pairs of input texts and facts, and then provide the nearest facts in response to the input text. Since the fact, consisting of only two entities and one relation, has little context to encode, we propose to further refine ranks of top-k retrieved facts with a reranker that contextualizes the input text and the fact jointly. We validate our DiFaR framework on multiple fact retrieval tasks, showing that it significantly outperforms relevant baselines that use the three-step approach.