Ranking related entities for web search queries

Kang, Changsung; Vadrevu, Srinivas; Zhang, Ruiqiang; Zwol, Roelof van; Pueyo, Lluís Garcia; Torzec, Nicolas; He, Jianzhang; Chang, Yi

doi:10.1145/1963192.1963227

Cited by 10 publications

(7 citation statements)

References 3 publications

(1 reference statement)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the semantic gap between the words in user query and the descriptions of entities in the entitygraph can be significant [18]. Entity ranking, or ad-hoc object retrieval is aimed at finding the most relevant entity related to the user's query, and it has been the focus of many recent studies [2,14,20,19,26]. Pound et al provide a query classification of entity-related search queries and define evaluation metrics for the entity retrieval task [20].…”

Section: Related Workmentioning

confidence: 99%

“…This task has also been the focus of evaluations in TREC [1] and other venues such as the SemSearch challenges [3]. A variant of the ad-hoc object retrieval task is the recommendation of related entities, where the focus is on ranking the relationships between a query entity and other entities in the graph, see Kang et al [14] and van Zwol et al [26]. More recently, Blanco et al [2] present their work on the Spark system, which is a continuation of the work of Kang et al…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Timely Semantics: A Study of a Stream-Based Ranking System for Entity Relationships

Fischer

Blanco

Mika

et al. 2015

The Semantic Web - ISWC 2015

View full text Add to dashboard Cite

In recent years, search engines have started presenting se-mantically relevant entity information together with document search results. Entity ranking systems are used to compute recommendations for related entities that a user might also be interested to explore. Typically, this is done by ranking relationships between entities in a semantic knowledge graph using signals found in a data source as well as type annotations on the nodes and links of the graph. However, the process of producing these rankings can take a substantial amount of time. As a result, entity ranking systems typically lag behind real-world events and present relevant entities with outdated relationships to the search term or even outdated entities that should be replaced with more recent relations or entities. This paper presents a study using a real-world stream-processing based implementation of an entity ranking system, to understand the effect of data timeliness on entity rankings. We describe the system and the data it processes in detail. Using a longitudinal case-study, we demonstrate (i) that low-latency, large-scale entity relationship ranking is feasible using moderate resources and (ii) that stream-based entity ranking improves the freshness of related entities while maintaining relevance. Abstract. In recent years, search engines have started presenting semantically relevant entity information together with document search results. Entity ranking systems are used to compute recommendations for related entities that a user might also be interested to explore. Typically, this is done by ranking relationships between entities in a semantic knowledge graph using signals found in a data source as well as type annotations on the nodes and links of the graph. However, the process of producing these rankings can take a substantial amount of time. As a result, entity ranking systems typically lag behind real-world events and present relevant entities with outdated relationships to the search term or even outdated entities that should be replaced with more recent relations or entities. This paper presents a study using a real-world stream-processing based implementation of an entity ranking system, to understand the effect of data timeliness on entity rankings. We describe the system and the data it processes in detail. Using a longitudinal case-study, we demonstrate (i) that low-latency, large-scale entity relationship ranking is feasible using moderate resources and (ii) that stream-based entity ranking improves the freshness of related entities while maintaining relevance.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Timely Semantics: A Study of a Stream-Based Ranking System for Entity Relationships

Fischer

Blanco

Mika

et al. 2015

The Semantic Web - ISWC 2015

View full text Add to dashboard Cite

show abstract

“…Although recommendations similar to ours appear on the result pages of Google Search and Bing Search, details of these systems have not been published. Previous versions of our system have been described in [11,6]. These papers have focused largely on ranking and provided limited descriptions of the overall process of generating entity recommendations.…”

Section: Related Workmentioning

confidence: 99%

“…These papers have focused largely on ranking and provided limited descriptions of the overall process of generating entity recommendations. Our system has evolved considerably since the publication of these papers, including the ranking model, which does not rely any more on a click-based objective as described in [6].…”

Section: Related Workmentioning

confidence: 99%

Entity Recommendations in Web Search

Blanco

Cambazoğlu

Mika

et al. 2013

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. While some web search users know exactly what they are looking for, others are willing to explore other topics related to an initial interest. Often, the user's initial interest can be uniquely linked to an entity in a knowledge base, and in this case it is natural to recommend the explicitly linked entities for further exploration. In real world knowledge bases, however, the number of linked entities may be very large and not all related entities may be equally relevant. Thus there is a need for ranking related entities. In this paper, we describe Spark, a recommendation engine that links a users' initial query to an entity within a knowledge base and provides a ranking of the related entities. Spark extracts several signals from a variety of data sources, including user sessions, Twitter and Flickr, using a large cluster of computers running Hadoop. These signals are combined with a machine learned ranking model in order to produce a final recommendation of entities to user queries, which is currently powering Yahoo! Search results pages.

show abstract

“…The authors show that the proposed method and its variations are able to boost long tail queries, and personalized query suggestion. Kang et al retrieve entities from several sources (query logs, Flickr, Wikipedia) and use a gradient boosting algorithm to obtain a function which predicts the relative relevance between two entities based on their concurrence [18].…”

Section: Related Workmentioning

confidence: 99%

When entities meet query recommender systems

Ceccarelli

Gordea

Lucchese

et al. 2013

Proceedings of the 28th Annual ACM Symposium on Applied Computing

View full text Add to dashboard Cite

The Web of Data is growing in popularity and dimension, and entities are gaining importance in many research fields. In this paper, we explore the use of entities that can be extracted from a query log to enhance query recommendation. In particular, we use a large query log recorded by the Europeana portal, a central access point to the descriptions of more than 20 million cultural heritage objects, and we extend a state-of-the-art query recommendation algorithm to take into account the semantic information associated with the submitted queries. Our novel method generates highly related and diversified suggestions. We assess it by means of a new evaluation technique. The manually annotated dataset used for performance comparisons has been made available to the research community to favor the repeatability of the experiments.

show abstract

Ranking related entities for web search queries

Cited by 10 publications

References 3 publications

Timely Semantics: A Study of a Stream-Based Ranking System for Entity Relationships

Timely Semantics: A Study of a Stream-Based Ranking System for Entity Relationships

Entity Recommendations in Web Search

When entities meet query recommender systems

Contact Info

Product

Resources

About