A Survey of Automatic Query Expansion in Information Retrieval

Abstract

The relative ineffectiveness of information retrieval systems is largely caused by the inaccuracy with which a query formed by a few keywords models the actual user information need. One well known method to overcome this limitation is automatic query expansion (AQE), whereby the user's original query is augmented by new features with a similar meaning. AQE has a long history in the information retrieval community but it is only in the last years that it has reached a level of scientific and experimental maturity, especially in laboratory settings such as TREC. This survey presents a unified view of a large number of recent approaches to AQE that leverage various data sources and employ very different principles and techniques. The following questions are addressed: Why is query expansion so important to improve search effectiveness? What are the main steps involved in the design and implementation of an AQE component? What approaches to AQE are available and how do they compare? Which issues must still be resolved before AQE becomes a standard component of large operational information retrieval systems (e.g., search engines)?

Query Refinement Using Conversational Context: A Method and an Evaluation Resource

“…Several methods for the refinement of explicit queries asked by users have been proposed in the field of information retrieval, and are often classified into query expansion techniques and relevance feedback ones [11]. Query expansion generates one or more hypotheses for query refinement by recognizing possible interpretations of a query, based on knowledge coming either directly from the corpus [2,29,24,10,3] or from Web data or personal profiles in the case of Web search [30,13,12,21].…”

“…Query expansion generates one or more hypotheses for query refinement by recognizing possible interpretations of a query, based on knowledge coming either directly from the corpus [2,29,24,10,3] or from Web data or personal profiles in the case of Web search [30,13,12,21]. Query expansion techniques select suggestions for query refinement either interactively or automatically [11]. For instance, relevance feedback gathers judgments obtained from the users on sample results obtained from an initial query [25,26,19].…”

“…However, in order to apply this method to a retrieval system for which the local context is a conversation, the keyword lists must avoid considering irrelevant topics from ASR errors. Moreover, unlike written documents which follow generally a planned and focused structured, in a conversation users often turn from one topic to another, and adding such a variety of keywords to a query might deteriorate the retrieval results [4,11].…”

“…Since there is no variation in these values for the last three values, we set fragment size to 400 words. We have also limited the weighting to the first 10 keywords extracted from each fragment, following several previous studies [11], thus speeding up the query processing.…”

Caching and Prefetching Strategies for SPARQL Queries

“…Linked Data sources offer a wealth of information about a multitude of topics, including geo-location facts 1 , government data 2 , or cross-domain information 3 . The SPARQL Protocol and RDF Query Language (Sparql) has become the de facto query language to retrieve this information from publicly available endpoints.…”