Tell Me Why Is It So? Explaining Knowledge Graph Relationships by Finding Descriptive Support Passages
This addresses the need for transparency in high-risk domains like healthcare and intelligence, where users require explanations for decision-making, especially with opaque machine-learned fact extractors.
The paper tackles the problem of explaining facts in knowledge graphs by finding descriptive passages from a source corpus, using Wikidata and Wikipedia to test their approach and reporting user study results.
We address the problem of finding descriptive explanations of facts stored in a knowledge graph. This is important in high-risk domains such as healthcare, intelligence, etc. where users need additional information for decision making and is especially crucial for applications that rely on automatically constructed knowledge bases where machine learned systems extract facts from an input corpus and working of the extractors is opaque to the end-user. We follow an approach inspired from information retrieval and propose a simple and efficient, yet effective solution that takes into account passage level as well as document level properties to produce a ranked list of passages describing a given input relation. We test our approach using Wikidata as the knowledge base and Wikipedia as the source corpus and report results of user studies conducted to study the effectiveness of our proposed model.