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

By Zhenghao Liu, Chenyan Xiong, Maosong Sun, Zhiyuan Liu. 2018

136 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (2019, neutral): “There has been a lot of work which leverages knowledge graphs (KGs) to learn better entity representations (Xiong and Callan, 2015; Xiong et al., 2017; Liu et al., 2018) and for better query reformulation (Cao et al.”
A Survey on Application of Knowledge Graph (2020, background): “The research work [36] introduces KGs to neural search systems.”
Selective Weak Supervision for Neural Information Retrieval (2020, methodology): “Conv-KNRM, which captures soft matches between query-document n-grams using kernels [5], significantly outperforms feature-based methods in the Chinese Sogou-T search log [23, 53, 54], the Bing click log [5], and MS MARCO which includes millions of expert relevance label [17, 37].”
A Deep Look into Neural Ranking Models for Information Retrieval (2019, background): “[133] proposed EDRM that incorporates entities in interaction-focused neural ranking models.”
CPM-2: Large-scale Cost-effective Pre-trained Language Models (2021, methodology): “We think this is because the LCQMC dataset is relatively easier than the other two datasets and vanilla fine-tuning can perform well enough without a better prompt.”
Knowledge Graphs: Opportunities and Challenges (2023, background): “Liu et al. (2018) proposed the Entity-Duet Neural Ranking Model (EDRM).”
Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications (2022, unknown): “tion [32], recommendation systems [33], and real-time ranking [34], [35], [36].”
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks (2020, background): “…representations of real-world facts (or events), inasmuch as it supports countless knowledge-driven tasks in areas such as information retrieval (Liu et al. 2018), natural language understanding (Chen, Chen, and Yu 2019; He et al. 2017), recommender systems (Koren, Bell, and Volinsky 2009) and…”
A Survey of Model Architectures in Information Retrieval (2025, unknown): “…2013; Pennington et al., 2014) provide semantic-based term representations to enable neural ranking models to focus on learning relevance matching patterns, improving training convergence and retrieval performance on both representation-based and interaction-based models (Levy et al., 2015).”