Knowledge Base Completion for Long-Tail Entities

TL;DR

This paper introduces a new LM-based method for filling knowledge gaps about long-tail entities in KBs, using a two-stage approach with a novel dataset, MALT, showing significant improvements in recall.

Contribution

It presents a novel two-stage LM-based approach specifically designed for long-tail entities and introduces the MALT dataset for evaluation.

Findings

Outperforms baselines in F1 score

Achieves major gains in recall

Effective for long-tail entity facts

Abstract

Despite their impressive scale, knowledge bases (KBs), such as Wikidata, still contain significant gaps. Language models (LMs) have been proposed as a source for filling these gaps. However, prior works have focused on prominent entities with rich coverage by LMs, neglecting the crucial case of long-tail entities. In this paper, we present a novel method for LM-based-KB completion that is specifically geared for facts about long-tail entities. The method leverages two different LMs in two stages: for candidate retrieval and for candidate verification and disambiguation. To evaluate our method and various baselines, we introduce a novel dataset, called MALT, rooted in Wikidata. Our method outperforms all baselines in F1, with major gains especially in recall.