Latent entity space: a novel retrieval approach for entity-bearing queries

By Xitong Liu, Hui Fang. 2015

75 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Information Retrieval & Search

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

1. Chenyan Xiong
2. Jamie Callan
3. Zhiyuan Liu
4. Maosong Sun
5. Zhenghao Liu
6. Tie-Yan Liu
7. Zhuyun Dai
8. Jimmy J. Lin

In Information Systems

1. Jamie Callan
2. Chenyan Xiong
3. Tie-Yan Liu
4. Zhenghao Liu
5. Zhiyuan Liu
6. Maosong Sun
7. Zhuyun Dai
8. Edgar Meij

In Information Retrieval & Search

1. Chenyan Xiong
2. Jamie Callan
3. Zhenghao Liu
4. Tie-Yan Liu
5. Zhiyuan Liu
6. Maosong Sun
7. Zhuyun Dai
8. Oren Kurland

Citations in the corpus

• Word-Entity Duet Representations for Document Ranking (2017, methodology): “Document representation can be enriched by adding the annotated entities into the document’s vector space model [17, 21, 23]. ranking model can also be improved by utilizing the entities and their attributes to build additional connections between query and documents [14, 19].”
• Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (2019, neutral): “web-search query logs has revealed that there is a large portion of entity seeking queries (Liu and Fang, 2015).”
• Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding (2017, background): “Latent Entity Space (LES) uses query entities and closely related document entities as the latent space between query and documents, and the latent entities’ descriptions are used to connect query and documents in an unsupervised model [16].”
• Bag-of-Entities Representation for Ranking (2016, methodology): “The choice of knowledge base in this paper is Freebase, one of the largest public knowledge bases frequently used in recent IR research [1, 5, 7, 8].”
• Utilizing Knowledge Graphs in Text-centric Information Retrieval (2017, background): “Such approaches match information in KGs with information in text and obtain state-of-the-art performance for ad hoc document retrieval [3, 9, 12, 17].”
• Document Retrieval Using Entity-Based Language Models (2016, methodology): “Inspired by approaches in the vector-space model [42], and in work on using a latent entity space [33], we consider a method that fuses document retrieval scores produced by utilizing, independently , term-only ( θ termx ) and entity-only ( θ entx ) language models induced from text x .”
• A Survey on Application of Knowledge Graph (2020, background): “Liu et al. [34] map both queries and documents to a high-dimensional latent entity space, in which each dimension corresponds to one entity, and then estimate the relevance between query and document based on their projections to each dimension in the latent space.”
• Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval (2018, methodology): “, 2014), entity-based connections between query and documents (Liu and Fang, 2015; Xiong and Callan, 2015), and soft-match query and documents through knowledge graph relations or embeddings (Xiong et al.”