EsdRank: Connecting Query and Documents through External Semi-Structured Data

By Chenyan Xiong, Jamie Callan. 2015

97 citations recorded by the source corpus.

This paper presents EsdRank, a new technique for improving ranking using external semi-structured data such as controlled vocabularies and knowledge bases. EsdRank treats vocabularies, terms and entities from external data, as objects connecting query and documents. Evidence used to link query to objects, and to rank documents are incorporated as features between query-object and object-document correspondingly. A latent listwise learning to rank algorithm, Latent-ListMLE, models the objects as latent space between query and documents, and learns how to handle all evidence in a unified procedure from document relevance judgments. EsdRank is tested in two scenarios: Using a knowledge base for web search, and using a controlled vocabulary for medical search. Experiments on TREC Web Track and OHSUMED data show significant improvements over state-of-the-art baselines.

Subfields: Artificial Intelligence, Information Systems, Molecular Biology, 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

In Information Systems

In Molecular Biology

In Information Retrieval & Search

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].”
Modeling Relational Data with Graph Convolutional Networks (2017, background): “Knowledge bases organize and store factual knowledge, enabling a wide variety of applications including question answering [48, 1, 37, 17, 2, 10] and information retrieval [22, 7, 46, 45].”
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.”
An Empirical Study of Learning to Rank for Entity Search (2016, background): “Publicly available knowledge bases such as DBpedia, Freebase, and Wikipedia are beginning to be used for tasks such as document ranking, card retrieval, and question answering [3, 4, 5].”
Utilizing Knowledge Graphs in Text-centric Information Retrieval (2017, methodology): “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].”
Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding (2017, methodology): “EsdRank uses entities from entity linking and entity search to build additional connections between query and documents [25].”
Document Retrieval Using Entity-Based Language Models (2016, background): “Most of these methods expand the query with terms or entities related to those appearing (or marked) in it [46, 35, 39, 7, 13, 31, 45, 29]; other methods project queries and documents onto a latent or explicit entity space [14, 33, 44].”
Bag-of-Entities Representation for Ranking (2016, methodology): “TagMe is an entity linking system [2] widely used in prior research [4, 7].”
Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval (2018, background): “, 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.”
Constrained Semi-supervised Learning in the Presence of Unanticipated Classes (2016, methodology): “In information retrieval, several recent approaches to query expansion make use of glosses [34, 129, 143] to improve the performance of ad-hoc infor-”
On the Representation and Embedding of Knowledge Bases beyond Binary Relations (2016, background): “…has inspired intense research interest in this area, from completing and improving knowledge bases (e.g., [Baader et al. , 2007; Angeli and Manning, 2013]) to developing applications that retrieve information from the knowledge data (e.g., [Marin et al. , 2014; Xiong and Callan, 2015a; 2015b]).”