Contextualized query expansion via unsupervised chunk selection for text retrieval

Query Expansion (QE) is widely applied to improve the retrieval performance of ad-hoc search, using different techniques and several data sources to find expansion terms. In Information Retrieval literature, selecting expansion terms remains a challenging task that relies on the extraction of term relationships. In this paper, we propose a new learning to rank-based query expansion model. The main idea behind is that, given a query and the set of its related ARs, our model ranks these ARs according to their relevance score regarding to this query and then selects the most suitable ones to be used in the QE process. Experiments are conducted on three test collections, namely: CLEF2003, TREC-Robust and TREC-Microblog, including long, hard and short queries. Results showed that the retrieval performance can be significantly improved when the ARs ranking method is used compared to other state of the art expansion models, especially for hard and long queries.

We propose a novel Frequently Asked Question (FAQ) retrieval technique with a neural query expansion model. With the growth in Question Answering systems and mobile communications, FAQ retrieval systems have become widely used in site searches and call center support. However, FAQ retrieval often has lexical gaps between queries and answer documents. To bridge these gaps, we design a query expansion model on the basis of an Encoder-Decoder model as a type of deep neural network. The model learns the words that appear in answers for questions using Q&A pair documents and generates the expanded queries from inputted queries to retrieve answer documents. We evaluate our proposed technique in a multi-domain FAQ retrieval task. Experimental results show that our technique retrieves FAQs more accurately than the previous methods.

The effects of query structures and query expansion (QE) on retrieval performance were tested with a best match retrieval system (InQuery^1). Query structure means the use of operators to express the relations between search keys. Six different structures were tested, representing strong structures (e.g., queries with facets or concepts identified) and weak structures (no concepts identified, a query is ‘a bag of search keys’). QE was based on concepts, which were first selected from a searching thesaurus, and then expanded by semantic relationships given in the thesaurus. The expansion levels were (a) no expansion, (b) a synonym expansion, (c) a narrower concept expansion, (d) an associative concept expansion, and (e) a cumulative expansion of all other expansions. With weak structures and Boolean structured queries, QE was not very effective. The best performance was achieved with a combination of a facet structure, where search keys within a facet were treated as instances of one search key (the SYN operator), and the largest expansion.

Query Expansion is commonly used in Information Retrieval to overcome vocabulary mismatch issues, such as synonymy between the original query terms and a relevant document. In general, query expansion experiments exhibit mixed results. Overall TREC Genomics Track results are also mixed; however, results from the top performing systems provide strong evidence supporting the need for expansion. In this paper, we examine the conditions necessary for optimal query expansion performance with respect to two system design issues: IR framework and knowledge source used for expansion. We present a query expansion framework that improves Okapi baseline passage MAP performance by 185%. Using this framework, we compare and contrast the effectiveness of a variety of biomedical knowledge sources used by TREC 2006 Genomics Track participants for expansion. Based on the outcome of these experiments, we discuss the success factors required for effective query expansion with respect to various sources of term expansion, such as corpus-based cooccurrence statistics, pseudo-relevance feedback methods, and domain-specific and domain-independent ontologies and databases. Our results show that choice of document ranking algorithm is the most important factor affecting retrieval performance on this dataset. In addition, when an appropriate ranking algorithm is used, we find that query expansion with domain-specific knowledge sources provides an equally substantive gain in performance over a baseline system.

The application of lexical simplification techniques in this study aims to reduce vocabulary mismatch between user queries and document collections. Two distinct strategies —complex word substitution (Stg1) and query expansion with simplified alternative (Stg2)— are systematically evaluated across six benchmark datasets (FiQA, ArguAna, NFCorpus, SCIDOCS, SciFact, and TREC-COVID) using nDCG@10 and MAP utilizing dense and sparse neural retrieval models. Our experiments reveal that Stg1 consistently degrades retrieval performance, with nDCG@10 and MAP declines often exceeding 0.10 and 0.03, respectively. In contrast, Stg2 preserves nearly all baseline effectiveness, nDCG@10 drops by fewer than 0.02 points, MAP by fewer than 0.01, and in some instances even surpasses the baseline. Risk-sensitive evaluation further confirms that Stg2 incurs minimal or no per-query risk and exhibits promising results, whereas Stg1 uniformly harms effectiveness. These findings indicate that appending simplified term variants alongside original query terms offers a fair and robust means of addressing vocabulary mismatch without sacrificing precision or recall. It is recommended that future IR pipelines incorporate carefully tailored query simplification models to balance user query intent and high retrieval quality.

This paper study about a review of the literature on Query Expansion (QE) methods. The main aspects of the review study are the methods, limitations of the QE methods, and datasets used in QE. As the results of this study, we can conclude several methods used on QE i.e., Ontology, Association Rules, Wordnet, Methathesaurus, Synonym mapping, Concept-based, Local Co-occurrence, and Latent Semantic Indexing (LSI). Each of the methods still has limitations. For datasets used in QE, many researchers use public datasets.

This paper describes and evaluates the use of Geographical Knowledge Re-Ranking, Linguistic Processing, and Query Expansion techniques to improve Geographical Information Retrieval effectiveness. Geographical Knowledge Re-Ranking is performed with Geographical Gazetteers and conservative Toponym Disambiguation techniques that boost the ranking of the geographically relevant documents retrieved by standard state-of-the-art Information Retrieval algorithms. Linguistic Processing is performed in two ways: 1) Part-of-Speech tagging and Named Entity Recognition and Classification are applied to analyze the text collections and topics to detect toponyms, 2) Stemming (Porter’s algorithm) and Lemmatization are also applied in combination with default stopwords filtering. The Query Expansion methods tested are the Bose-Einstein (Bo1) and Kullback-Leibler term weighting models. The experiments have been performed with the English Monolingual test collections of the GeoCLEF evaluations (from years 2005, 2006, 2007, and 2008) using the TF-IDF, BM25, and InL2 Information Retrieval algorithms over unprocessed texts as baselines. The experiments have been performed with each GeoCLEF test collection (25 topics per evaluation) separately and with the fusion of all these collections (100 topics). The results of evaluating separately Geographical Knowledge Re-Ranking, Linguistic Processing (lemmatization, stemming, and the combination of both), and Query Expansion with the fusion of all the topics show that all these processes improve the Mean Average Precision (MAP) and RPrecision effectiveness measures in all the experiments and show statistical significance over the baselines in most of them. The best results in MAP and RPrecision are obtained with the InL2 algorithm using the following techniques: Geographical Knowledge Re-Ranking, Lemmatization with Stemming, and Kullback-Leibler Query Expansion. Some configurations with Geographical Knowledge Re-Ranking, Linguistic Processing and Query Expansion have improved the MAP of the best official results at GeoCLEF evaluations of 2005, 2006, and 2007.KeywordsInformation retrievalGeographical gazetteersNatural language processingToponym disambiguationQuery expansionEfectiveness measures

The existing query expansion (QE) methods cannot find the most users-requested source code version at times due to the over-expansion resulting from noises. To solve this problem, we propose a QE method based on evolving contexts (EC) that are added/deleted terms and their dependent terms during code evolution. On expanding a query, we appended the added terms as relevant terms, and excluded the deleted terms as noisy terms. We also developed a QE-integrating framework based on the Support Vector Machine (SVM) Ranking, called QESR, to simultaneously integrate multiple QE methods. Our experiment shows that QESR outperforms the state-of-the-art QE methods CodeHow and Query Expansion based on Crowd Knowledge (QECK) by 13%–16% in terms of precision when the first query result is inspected.

One of the major challenges in Web search pertains to the correct interpretation of users' intent. Query Expansion is one of the well-known approaches for determining the intent of the user by addressing the vocabulary mismatch problem. A limitation of the current query expansion approaches is that the relations between the query words and the expanded words is limited. In this thesis, we capture users' intent through query expansion. We build on earlier work in the area by adopting a pseudo-relevance feedback approach; however, we advance the state of the art by proposing an approach for feature learning within the process of query expansion. In our work, we specifically consider the Wikipedia corpus as the feedback collection space and identify the best features within this context for term selection in two supervised and unsupervised models. We compare our work with state of the art query expansion techniques, the results of which show promising robustness and improved precision.

Queries to search engines on the Web are usually short. They do not provide sufficient information for an effective selection of relevant documents. Previous research has proposed the utilization of query expansion to deal with this problem. However, expansion terms are usually determined on term co-occurrences within documents. In this study, we propose a new method for query expansion based on user interactions recorded in user logs. The central idea is to extract correlations between query terms and document terms by analyzing user logs. These correlations are then used to select high-quality expansion terms for new queries. Compared to previous query expansion methods, ours takes advantage of the user judgments implied in user logs. The experimental results show that the log-based query expansion method can produce much better results than both the classical search method and the other query expansion methods.

To evaluate the effectiveness of generative query expansion for biomedical literature retrieval. We thoroughly examined eight generative query expansion methods using three large language models across five datasets for biomedical literature retrieval. We further performed a quantitative analysis, including performance comparisons, rank transition analysis, and article-type effect analysis. We also conducted a qualitative examination of representative cases, from which we derived an error taxonomy. On BioASQ-Y/N, GPT-4o-based query expansion shifts Recall@10 to 0.417-0.512 and nDCG@10 to 0.358-0.479, relative to a baseline of 0.491 and 0.456. For PubMedQA, Precision@1 ranges from 0.764 to 0.876 and nDCG@10 from 0.847 to 0.931, compared with baseline values of 0.893 and 0.935. For 2019-Trec-PM, query expansion yields Recall@100 of 0.217-0.256 and nDCG@100 of 0.272-0.312, versus a baseline of 0.227 and 0.274. Similarly, for 2018-TREC-PM, Recall@100 spans 0.169-0.227 and nDCG@100 spans 0.195-0.250, relative to baseline scores of 0.164 and 0.191. For 2017-TREC-PM, Recall@100 and nDCG@100 fall within 0.111-0.139 and 0.154-0.191 under query expansion, compared with baseline metrics of 0.102 and 0.147. Both general-purpose and domain-specific Llama-based models demonstrate similar performance to GPT-4o. The impact of query expansion varies significantly by the expansion methods and type of evidence, but is relatively agnostic to backbone model choice. Notably, query expansion primarily affects article ranking but has a limited impact on the screening stage. Our findings underscore the unique challenges of biomedical literature retrieval and highlight the need to develop domain-specific information retrieval techniques.

With the development of the web 2.0 communities, information retrieval has been widely applied based on the collaborative tagging system. However, a user issues a query that is often a brief query with only one or two keywords, which leads to a series of problems like inaccurate query words, information overload and information disorientation. The query expansion addresses this issue by reformulating each search query with additional words. By analyzing the limitation of existing query expansion methods in folksonomy, this paper proposes a novel query expansion method, based on user profile and topic model, for search in folksonomy. In detail, topic model is constructed by variational antoencoder with Word2Vec firstly. Then, query expansion is conducted by user profile and topic model. Finally, the proposed method is evaluated by a real dataset. Evaluation results show that the proposed method outperforms the baseline methods.

Accepted: 24.11.2015 In this paper, a hybrid approach is developed for geospatial information retrieval which combines query expansion (QE) and latent semantic indexing (LSI) methods. The hybrid method uses the advantages of Query Expansion and Semantic indexing methods for improving search results. LSI establishes relations depending on the similarities between queries and the documents where QE helps by adding extra similar terms to the queries. The dataset is populated using data extracted from Wikipedia and USGS (The United States Geological Survey). Automation is programmed to get all the information from the web and to extract the meaningful words. The significant terms are the name of the places, directions, and nearby locations. The dataset includes mountains and places with their latitudes, longitudes, locations and directions. The extracted data is also taken into Protege for semantically querying. The approach is applied to geographical data (popular search items on search engines), and by querying the data with the combination of LSI and QE more related results are handled than the results of methods when they are applied alone. Many queries are run, and the results are listed and compared. At the end of the study it is understood that the hybrid method considerably improves the search results.

This paper proposes a multi-agent query refinement approach to realize personalized query expansion effective for academic paper retrieval in a Big Data environment. First, we use Hadoop as a platform to develop a formalized model to represent different types of large caches of data in order to analyze and process Big Data efficiently. Second, we use a client agent to verify user identities and monitor whether a device is ready to run a query-expanded task. We then use a query expansion agent to determine the domain that the initial query belongs to by applying a knowledgebased query expansion strategy and comprehensively considering users’ interests according to the intelligent devices they use by implementing a user-device-based query expansion strategy and a weighted query expansion strategy in order to obtain the optimized query expansion set. We compare our method with the conceptual retrieval method as well as other two lexical methods for query expansion, and we prove that our method has better average recall and average precision ratios.

We propose a new method for query expansion called "term similarity tree model" (TSTM). Term similarity tree is built to represent and estimate similarities between terms. Based on TSTM, we use similarity restriction and overlay restriction to implement query expansion. This method can cluster terms automatically, make the process of query expansion more flexible and controllable, and control noise effectively. In addition, the parameters of TSTM can be adjusted easily to meet the requirements of different types of queries. TREC data is used to test the method. The experiments show that TSTM method outperforms the existing methods in query expansion, such as WordNet-based method, local cooccurrence method and latent semantic indexing (LSI-based) method.