Web Query Expansion by WordNet

This paper presents a framework which combines data and text retrieval techniques to exercise and evaluate ontology based query expansions. We prepare by using linguistic techniques to identify query and document concepts, locating them in a ontologically defined semantic space. Expansions originate from the identified query concepts, with success determined by matching in the relevant document set. We identify three orthogonal dimensions that can affect query expansion success; relationship source, success measure technique, and query expansion technique. Expansion technique is further divided into six different categories: simple pruning, complex probability, voting, directional, semantic propagation, and multiple source concept. We describe each technique and show examples where they would be useful. The system architecture used facilitates plugging in of various expansion and evaluation routines, and flowing results from one method to the next. The system is useful for microanalysis of query expansion, discovering which components of ontological derived knowledge most influence query expansion success. In this work, we apply our framework to the medical domain.

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.

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.

Proksch has proved the changed terms of source code negatively affect code search quality. However, current query expansion (QE) methods always ignore it. In this paper we propose a novel QE method based on the semantics of change sequences (QESC). It not only captures which changes occurred by ext racting change sequences from Github commits, but also understands why changes occurred by learning sequence semantics with Deep Belief Network (DBN). Thus it could extract relevant terms to expand or irrelevant terms to exclude from the changes semantically similar to a query. Our experimental results show QESC outperforms the existing QE methods by 15–23% in terms of precision on inspecting the first query result.

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 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.

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.

Information retrieval systems utilize user feedback for generating optimal queries with respect to a particular information need. However, the methods that have been developed in IR for generating these queries do not memorize information gathered from previous search processes, and hence cannot use such information in new search processes. Thus, a new search process cannot profit from the results of the previous processes. Web Information Retrieval systems should be able to maintain results from previous search processes, thus learning from previous queries and improving overall retrieval quality. In this chapter, we are using the similarity of a new query to previously learned queries. We then expand the new query by extracting terms from documents, which have been judged as relevant to these previously learned queries. Thus, the new method uses global feedback information for query expansion in contrast to local feedback information, which has been widely used in previous work in query expansion methods. Experimentally, we compared a new query expansion method with two conventional information retrieval methods in local and global query expansion to enhance the traditional information system. From the results gathered it can be concluded that although the traditional IR system performance is high, but we notice that PRF method increases the average recall and decreases the fallout measure.

In this paper we propose the schema of 3-layer domain ontology. The entity relation, entity-attribute pair and textual description are distributed in layers respectively. Based on the 3-layer ontology we proposed 4 query expansion methods: top-down expansion, synonyms expansion, bottom-up expansion and backtracking expansion. A set of experiment1 is carried out to prove the expansion methods. Different result shows the expansion methods is effective as a whole, and we analysis the shortage of our methods.

Manifold ranking has been successfully applied in query-oriented multi-document summarization. It not only makes use of the relationships among the sentences, but also the relationships between the given query and the sentences. However, the information of original query is often insufficient. So we present a query expansion method, which is combined in the manifold ranking to resolve this problem. Our method not only utilizes the information of the query term itself and the knowledge base WordNet to expand it by synonyms, but also uses the information of the document set itself to expand the query in various ways (mean expansion, variance expansion and TextRank expansion). Compared with the previous query expansion methods, our method combines multiple query expansion methods to better represent query information, and at the same time, it makes a useful attempt on manifold ranking. In addition, we use the degree of word overlap and the proximity between words to calculate the similarity between sentences. We performed experiments on the datasets of DUC 2006 and DUC2007, and the evaluation results show that the proposed query expansion method can significantly improve the system performance and make our system comparable to the state-of-the-art systems.

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.

We present a method for automatic query expansion for cross-lingual information retrieval in the medical domain. The method employs machine translation of source-language queries into a document language and linear regression to predict the retrieval performance for each translated query when expanded with a candidate term. Candidate terms (in the document language) come from multiple sources: query translation hypotheses obtained from the machine translation system, Wikipedia articles and PubMed abstracts. Query expansion is applied only when the model predicts a score for a candidate term that exceeds a tuned threshold which allows to expand queries with strongly related terms only. Our experiments are conducted using the CLEF eHealth 2013–2015 test collection and show significant improvements in both cross-lingual and monolingual settings.

Entity-based ranking is a popular research area in document ranking as knowledge graphs can introduce additional evidence for ranking systems. In most entity-based ranking framework, the original query is transformed into a set of entities and candidate documents are ranked according to their relevance to the entity set. However, mistakes can easily occur during the transformation process, which introduce noise to the ranking system. This paper represents an expansion-based ranking framework, which expand the original query with high-quality candidate entities to mitigate the impact of transformation mistakes and enrich the semantics of the query in the meanwhile. Compared with existing query expansion methods, our expansion method is lightweight as it reduces much computational burden and requests little extra information. However, the core concerns of the users might be covered up after query expansion. To alleviate this dilemma, a core concern capturing method is pro-posed, wherein the attention weight of each inter-entity relation is measured to capture the core entity pairs in the expanded query. Experiments on the S2-CS dataset demonstrate the effectiveness of our lightweight query expansion method and the superiority of our core concern capturing method. Compared with a classical retrieval model, our method provides 11% improvements in terms of NDCG@15.

An evaluation of query expansion by the addition of clustered terms for a document retrieval system

A search query, being a very concise grounding of user intent, could potentially have many possible interpretations. Search engines hedge their bets by diversifying top results to cover multiple such possibilities so that the user is likely to be satisfied, whatever be her intended interpretation. Diversified Query Expansion is the problem of diversifying query expansion suggestions, so that the user can specialize the query to better suit her intent, even before perusing search results. We propose a method, Select-Link-Rank, that exploits semantic information from Wikipedia to generate diversified query expansions. SLR does collective processing of terms and Wikipedia entities in an integrated framework, simultaneously diversifying query expansions and entity recommendations. SLR starts with selecting informative terms from search results of the initial query, links them to Wikipedia entities, performs a diversity-conscious entity scoring and transfers such scoring to the term space to arrive at query expansion suggestions. Through an extensive empirical analysis and user study, we show that our method outperforms the state-of-the-art diversified query expansion and diversified entity recommendation techniques.