Résultats de recherche pour « Query expansion techniques »

In this work several semantic approaches to concept-based query expansion and reranking schemes are studied and compared with different ontology-based expansion methods in web document search and retrieval. In particular, we focus on concept-based query expansion schemes, where, in order to effectively increase the precision of web document retrieval and to decrease the users browsing time, the main goal is to quickly provide users with the most suitable query expansion. Two key tasks for query expansion in web document retrieval are to find the expansion candidates, as the closest concepts in web document domain, and to rank the expanded queries properly. The approach we propose aims at improving the expansion phase for better web document retrieval and precision. The basic idea is to measure the distance between candidate concepts using the PMING distance, a collaborative semantic proximity measure, i.e. a measure which can be computed by using statistical results from web search engine. Experiments show that the proposed technique can provide users with more satisfying expansion results and improve the quality of web document retrieval.

Abstract In Information Retrieval, query expansion refers to the procedure ofreformulating a user's search query by adding further search terms to theoriginal query to improve retrieval quality. Short queries, specifically, oftensuffer from ambiguity, i.e., they refer to multiple possible senses. Theobjective of query expansion, then, is to augment with terms that best match theuser's information need. In this work, we propose and analyse a system forsemantic query expansion that leverages contextual information extracted fromuser profiles to generate queries capable of disambiguating multi-sense searchqueries. We generate synthetic profiles from a knowledge graph of Wikipediaarticles, on which we train individual word2vec embeddings. Using a k-nearestneighbour search, we determine semantically close keywords to append to a givenquery. We evaluate this user-centric approach across corpora of varying sizes,assessing the extent to which sentinel articles are retrieved. Our findingssuggest that tailoring the expansion to the user's context results in animprovement of median rank by 2 levels, and an increase in category retrievalamong the top three results of 6% on average.

Query recommendation systems are ubiquitous in modern search engines, assisting users in producing effective queries to meet their information needs. However, these systems require a large amount of data to produce good recommendations, such as a large collection of documents to index and query logs. In particular, query logs and user data are not available in cold start scenarios. Query logs are expensive to collect and maintain and require complex and time-consuming cascading pipelines for creating, combining, and ranking recommendations. To address these issues, we frame the query recommendation problem as a generative task, proposing a novel approach called Generative Query Recommendation (GQR). GQR uses an LLM as its foundation and does not require to be trained or fine-tuned to tackle the query recommendation problem. We design a prompt that enables the LLM to understand the specific recommendation task, even using a single example. We then improved our system by proposing a version that exploits query logs called Retriever-Augmented GQR (RA-GQR). RA-GQr dynamically composes its prompt by retrieving similar queries from query logs. GQR approaches reuses a pre-existing neural architecture resulting in a simpler and more ready-to-market approach, even in a cold start scenario. Our proposed GQR obtains state-of-the-art performance in terms of NDCG@10 and clarity score against two commercial search engines and the previous state-of-the-art approach on the Robust04 and ClueWeb09B collections, improving on average the NDCG@10 performance up to ~4% on Robust04 and ClueWeb09B w.r.t the previous best competitor. RA-GQR further improve the NDCG@10 obtaining an increase of ~11%, ~6\% on Robust04 and ClueWeb09B w.r.t the best competitor. Furthermore, our system obtained ~59% of user preferences in a blind user study, proving that our method produces the most engaging queries.

The problem of Natural Language Query Formalization (NLQF) is to translate a given user query in natural language (NL) into a formal language so that the semantic interpretation has equivalence with the NL interpretation. Formalization of NL queries enables logic based reasoning during information retrieval, database query, question-answering, etc. Formalization also helps in Web query normalization and indexing, query intent analysis, etc. In this paper we are proposing a Description Logics based formal methodology for wh-query intent (also called desire) identification and corresponding formal translation. We evaluated the scalability of our proposed formalism using Microsoft Encarta 98 query dataset and OWL-S TC v.4.0 dataset.

We consider social peer-to-peer data management systems (PDMS), where each peer maintains both semantic mappings between its schema and some acquaintances, and social links with peer friends. In this context, reformulating a query from a peer's schema into other peer's schemas is a hard problem, as it may generate as many rewritings as the set of mappings from that peer to the outside and transitively on, by eventually traversing the entire network. However, not all the obtained rewritings are relevant to a given query. In this paper, we address this problem by inspecting semantic mappings and social links to find only relevant rewritings. We propose a new notion of 'relevance' of a query with respect to a mapping, and, based on this notion, a new semantic query reformulation approach for social PDMS, which achieves great accuracy and flexibility. To find rapidly the most interesting mappings, we combine several techniques: (i) social links are expressed as FOAF (Friend of a Friend) links to characterize peer's friendship and compact mapping summaries are used to obtain mapping descriptions; (ii) local semantic views are special views that contain information about external mappings; and (iii) gossiping techniques improve the search of relevant mappings. Our experimental evaluation, based on a prototype on top of PeerSim and a simulated network demonstrate that our solution yields greater recall, compared to traditional query translation approaches proposed in the literature.

The self-supervised training method can fully leverage the structural characteristics of unlabeled datasets, enhancing the technical prowess of natural language processing. We explore the application of self-supervision’s advantages to query expansion. To achieve this, we amassed a substantial query corpus and trained it using a generative model. Simultaneously, we introduced the SG-BERT/GPT2 extension method, leveraging two generators, BERT and GPT2. We also conducted an analysis of the impact on code search before and after generative model training, as well as the influence of the original query length on the expanded model. Experimental results consistently demonstrate the superiority of the trained model over the untrained one. Additionally, in deep learning-based code search methods, query expansion proves most effective for datasets with relatively short original query lengths, while longer expansions yield the opposite effect. Finally, when compared to various established query expansion methods, the SG-BERT/GPT2 expansion method, rooted in the self-supervised generative model, consistently outperforms them across multiple language test datasets. With ongoing self-supervised generation and continuous optimization of the query corpus, further enhancements in effectiveness can be achieved.

The enormous growth of research publications has made it challenging for academic search engines to bring the most relevant papers against the given search query. Numerous solutions have been proposed over the years to improve the effectiveness of academic search, including exploiting query expansion and citation analysis. Query expansion techniques mitigate the mismatch between the language used in a query and indexed documents. However, these techniques can suffer from introducing non-relevant information while expanding the original query. Recently, contextualized model BERT to document retrieval has been quite successful in query expansion. Motivated by such issues and inspired by the success of BERT, this paper proposes a novel approach called QeBERT. QeBERT exploits BERT-based embedding and Citation Network Analysis (CNA) in query expansion for improving scholarly search. Specifically, we use the context-aware BERT-embedding and CNA for query expansion in Pseudo-Relevance Feedback (PRF) fash-ion. Initial experimental results on the ACL dataset show that BERT-embedding can provide a valuable augmentation to query expansion and improve search relevance when combined with CNA.