Clustering Algorithms for Query Expansion Based Information Retrieval

Khennak, Ilyes; Drias, Habiba; Kechid, Amine; Moulai, Hadjer

doi:10.1007/978-3-030-28374-2_23

Cited by 3 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our second proposed clustering strategy is KMedoids [18]. The KMedoids algorithm returns the medoid of each cluster -the medoid is the most centrally located embedding of the input document embeddings.…”

Section: Colbert-prf Variantsmentioning

confidence: 99%

“…For the Approximate Scoring experiments, let 𝑘 1 denote the number of passages retrieved in the Stage 1 ANN, and 𝑘 4 denote the number of passages retrieved in the Stage 4 ANN. Then, for (i) the ColBERT-PRF Ranker model, we apply with rank cutoff of 𝑘 1 = 300 and 𝑘 4 = 1000 18 , and for (ii) the ReRanker model, we apply with rank cutoff 𝑘 1 = 1000 in the first stage only, to ensure sufficient recall of relevant passages to be upranked after applying PRF. We later vary 𝑘 1 and 𝑘 4 to demonstrate their impact upon efficiency and effectiveness.…”

Section: Research Question and Experimental Setupmentioning

confidence: 99%

See 1 more Smart Citation

ColBERT-PRF: Semantic Pseudo-Relevance Feedback for Dense Passage and Document Retrieval

et al. 2023

View full text Add to dashboard Cite

Pseudo-relevance feedback mechanisms, from Rocchio to the relevance models, have shown the usefulness of expanding and reweighting the users’ initial queries using information occurring in an initial set of retrieved documents, known as the pseudo-relevant set. Recently, dense retrieval – through the use of neural contextual language models such as BERT for analysing the documents’ and queries’ contents and computing their relevance scores – has shown a promising performance on several information retrieval tasks still relying on the traditional inverted index for identifying documents relevant to a query. Two different dense retrieval families have emerged: the use of single embedded representations for each passage and query, e.g., using BERT’s [CLS] token, or via multiple representations, e.g., using an embedding for each token of the query and document (exemplified by ColBERT). In this work, we conduct the first study into the potential for multiple representation dense retrieval to be enhanced using pseudo-relevance feedback and present our proposed approach ColBERT-PRF. In particular, based on the pseudo-relevant set of documents identified using a first-pass dense retrieval, ColBERT-PRF extracts the representative feedback embeddings from the document embeddings of the pseudo-relevant set. Among the representative feedback embeddings, the embeddings that most highly discriminate among documents are employed as the expansion embeddings, which are then added to the original query representation. We show that these additional expansion embeddings both enhance the effectiveness of a reranking of the initial query results as well as an additional dense retrieval operation. Indeed, experiments on the MSMARCO passage ranking dataset show that MAP can be improved by upto 26% on the TREC 2019 query set and 10% on the TREC 2020 query set by the application of our proposed ColBERT-PRF method on a ColBERT dense retrieval approach. We further validate the effectiveness of our proposed pseudo-relevance feedback technique for a dense retrieval model on MSMARCO document ranking and TREC Robust04 document ranking tasks. For instance, ColBERT-PRF exhibits upto 21% and 14% improvement in MAP over the ColBERT E2E model on the MSMARCO document ranking TREC 2019 and TREC 2020 query sets, respectively. Additionally, we study the effectiveness of variants of the ColBERT-PRF model with different weighting methods. Finally, we show that ColBERT-PRF can be made more efficient, attaining upto 4.54x speedup over the default ColBERT-PRF model, and with little impact on effectiveness, through the application of approximate scoring and different clustering methods.

show abstract

Section: Colbert-prf Variantsmentioning

confidence: 99%

Section: Research Question and Experimental Setupmentioning

confidence: 99%

ColBERT-PRF: Semantic Pseudo-Relevance Feedback for Dense Passage and Document Retrieval

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The terms to be added for the initial query are, commonly, the discriminative terms generated and selected from the collection itself via global [38], [44] or local dependent-corpus knowledge approach [49] either with the making use of local context analysis (LCA) [50] which uses the highly ranked documents qualified as relevant by the search system with adopting of pseudo relevance feedback [51] or interactively employing user judgment through relevance feedback information [52] injected by the user himself. For avoiding performance degradation especially when relying on pseudo-relevance feedback, automatic documents clustering may be extensively useful such as in [53]. Employing independent-corpus knowledge approach or external knowledge resources, such as other documents set [54], thesaurus [55], DBpedia [56], Freebase [57], ConceptNet [58], Wikipedia [59], or WordNet [35], [59], [60], is another adopted alternative for generating query expansion terms.…”

Section: Automatic Query Expansionmentioning

confidence: 99%

Query Refinement into Information Retrieval Systems

Mosbah

2023

JIOS

View full text Add to dashboard Cite

Query, expressing the user need and requirement, has an important role, in aninformation retrieval system, for reaching a high accuracy search. In this paper, wepresent an overview of the different refinement operations that the query may undergo,in the sake to enhance performance of an information retrieval system, such as:automatic query formulation through words prevision, query reformulation, queryexpansion, and query optimization.

show abstract

“…Sendo assim, propõe-se extrair grupos de mesmo tema ou assunto sem necessidade de interferência do usuário, uma vez que geralmente o agrupamentoé feito de maneira não supervisionada. Vale ressaltar que além da aplicação direta do agrupamento de textos para organização e gerenciamento de coleções de textos em grupos temáticos, o agrupamento de textosé utilizado para diversas outras finalidades e aplicações como a organização de resultados de busca [Khennak et al 2019], seleção de exemplos para o aprendizado ativo [Ienco et al 2013], e aprendizado baseado em umaúnica classe [Golo and Rossi 2019].…”

Section: Introductionunclassified

Aprendizado de Máquina não Supervisionado Baseado em Redes Heterogêneas para Agrupamento de Textos

Santos¹,

Rossi²

2020

Anais Do Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2020)

View full text Add to dashboard Cite

As representações em redes permitem modelar diferentes tipos de relações entre textos, são capazes de capturar padrões dificilmente capturados pelo modelo espaço vetorial, e algoritmos de agrupamento em redes, como a propagação de rótulos, possuem complexidade linear. Porém, o agrupamento em redes não tem sido explorado (i) especificamente no agrupamento de textos; e (ii) com as diferentes possibilidades de representar textos em redes. Com isso, o objetivo deste artigo é a exploração e análise de técnicas de agrupamento aplicadas a diferentes tipos de representações em redes. Foram realizados experimentos utilizando 30 coleções de diferentes domínios, representadas em formato bag-of-words, redes de similaridade do tipo k-Nearest Neighbors e redes bipartidas. A abordagem de propagação de rótulos em redes de similaridade obteve os melhores resultados para a maioria das medidas de avaliação e para a maioria das coleções de textos. O algoritmo de propagação de rótulos demonstrou-se promissor, principalmente quando aplicado a redes de similaridade.

show abstract

Clustering Algorithms for Query Expansion Based Information Retrieval

Cited by 3 publications

References 18 publications

ColBERT-PRF: Semantic Pseudo-Relevance Feedback for Dense Passage and Document Retrieval

ColBERT-PRF: Semantic Pseudo-Relevance Feedback for Dense Passage and Document Retrieval

Query Refinement into Information Retrieval Systems

Aprendizado de Máquina não Supervisionado Baseado em Redes Heterogêneas para Agrupamento de Textos

Contact Info

Product

Resources

About