COMBO: A Complete Benchmark for Open KG Canonicalization

TL;DR

COMBO introduces a comprehensive benchmark dataset for open knowledge graph canonicalization, including relation and entity canonicalization, with new metrics and baseline evaluations, advancing research in standardizing KG triples.

Contribution

It provides the first dataset with relation and ontology-level canonicalization, new evaluation metrics, and baseline results using pretrained language models.

Findings

Pretrained language models improve relation canonicalization.

Ontology-level canonicalization benefits from phrase encoding.

Baseline methods set a standard for future research.

Abstract

Open knowledge graph (KG) consists of (subject, relation, object) triples extracted from millions of raw text. The subject and object noun phrases and the relation in open KG have severe redundancy and ambiguity and need to be canonicalized. Existing datasets for open KG canonicalization only provide gold entity-level canonicalization for noun phrases. In this paper, we present COMBO, a Complete Benchmark for Open KG canonicalization. Compared with existing datasets, we additionally provide gold canonicalization for relation phrases, gold ontology-level canonicalization for noun phrases, as well as source sentences from which triples are extracted. We also propose metrics for evaluating each type of canonicalization. On the COMBO dataset, we empirically compare previously proposed canonicalization methods as well as a few simple baseline methods based on pretrained language models. We find that properly encoding the phrases in a triple using pretrained language models results in better relation canonicalization and ontology-level canonicalization of the noun phrase. We release our dataset, baselines, and evaluation scripts at https://github.com/jeffchy/COMBO/tree/main.