Relationship Queries on Extended Knowledge Graphs

Abstract

Entity search over text corpora is not geared for relationship queries where answers are tuples of related entities and where a query often requires joining cues from multiple documents. With large knowledge graphs, structured querying on their relational facts is an alternative, but often suffers from poor recall because of mismatches between user queries and the knowledge graph or because of weakly populated relations.This paper presents the TriniT search engine for querying and ranking on extended knowledge graphs that combine relational facts with textual web contents. Our query language is designed on the paradigm of SPO triple patterns, but is more expressive, supporting textual phrases for each of the SPO arguments. We present a model for automatic query relaxation to compensate for mismatches between the data and a user's query. Query answers -tuples of entities -are ranked by a statistical language model. We present experiments with different benchmarks, including complex relationship queries, over a combination of the Yago knowledge graph and the entity-annotated ClueWeb'09 corpus.

Exploratory querying of extended knowledge graphs

“…We have performed extensive experiments to evaluate our framework [14]. On a challenging set of 70 entity-relationship queries, we achieve an average NDCG at rank 5 of 0.775, with the next best state-of-the-art system achieving 0.419.…”

“…, where args(p) is the set of subject-object pairs connected by p in the XKG [14]. Additionally, relaxation rules can be specified manually, or automatically obtained using rule mining on the KG (e.g.…”

“…We adapt and extend this approach for our triple-pattern setting [14]. A triple pattern is viewed as a document that emits triples with certain probabilities.…”

“…To address these usability pain points, we have developed TriniT: a system that allows users to extend the KG to make up for missing knowledge, massages a user's query to better align it with the extended data, and can make suggestions regarding future queries [14]. TriniT supports query relaxation rules that are invoked to allow for relevant answers which are not found otherwise.…”

RELink

“…In recent years, we have seen increased interest in using online information sources to find concise and precise information about specific issues, events, and entities [11]. For example, in response Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page.…”