Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval

05/19/2018
by   Zhenghao Liu, et al.
0

This paper presents the Entity-Duet Neural Ranking Model (EDRM), which introduces knowledge graphs to neural search systems. EDRM represents queries and documents by their words and entity annotations. The semantics from knowledge graphs are integrated in the distributed representations of their entities, while the ranking is conducted by interaction-based neural ranking networks. The two components are learned end-to-end, making EDRM a natural combination of entity-oriented search and neural information retrieval. Our experiments on a commercial search log demonstrate the effectiveness of EDRM. Our analyses reveal that knowledge graph semantics significantly improve the generalization ability of neural ranking models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/03/2018

Towards Better Text Understanding and Retrieval through Kernel Entity Salience Modeling

This paper presents a Kernel Entity Salience Model (KESM) that improves ...
research
05/09/2022

Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective

Knowledge graph completion (KGC) aims to infer missing knowledge triples...
research
05/06/2020

Graph-Embedding Empowered Entity Retrieval

In this research, we improve upon the current state of the art in entity...
research
06/20/2017

Word-Entity Duet Representations for Document Ranking

This paper presents a word-entity duet framework for utilizing knowledge...
research
11/08/2022

Query-Specific Knowledge Graphs for Complex Finance Topics

Across the financial domain, researchers answer complex questions by ext...
research
05/04/2020

Hierarchical Knowledge Graphs: A Novel Information Representation for Exploratory Search Tasks

In exploratory search tasks, alongside information retrieval, informatio...
research
09/01/2021

Hypergraph-of-Entity: A General Model for Entity-Oriented Search

The hypergraph-of-entity was conceptually proposed as a general model fo...

Please sign up or login with your details

Forgot password? Click here to reset