# Direct Fact Retrieval from Knowledge Graphs without Entity Linking

Source: [Direct Fact Retrieval from Knowledge Graphs without Entity Linking](<https://www.sota2.com/research/paper/68fa6f641e209131cea45413>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-24T18:59:26.507Z

Authors: Jinheon Baek, Alham Fikri Aji, Jens Lehmann, Sung Ju Hwang

Published: 2023-05-21T09:46:53.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Single-hop QA on SimpleQuestions](<https://www.sota2.com/research/sota/single-hop-qa-on-simplequestions.md>): Single-hop QA; SimpleQuestions; Accuracy: 0.858.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2305.12416>)

[PDF](<https://arxiv.org/pdf/2305.12416.pdf>)