Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 45 for “"bm25"”.
-
BB25HLegalSum : a method for legal document summarization that leverages BM25 and BERT-based clustering
… a method that combines BERT clusters with the BM25 algorithm to summarize legal documents and present them to users with highlighted important information. The process involves selecting unique sentences from the original document, clustering them to find sentences about a similar subject, …
-
Vector Space Proximity Based Document Retrieval For Document Embeddings Built By Transformers
… Our first approach is based on the classic BM25 information retrieval approach and assumes that relevant articles will share common key- words with the current article. Our second approach is based on novel document embedding repre- sentations and uses various proximity measures to retrieve …
-
Rewarding the Location of Terms in Sentences to Enhance Probabilistic Information Retrieval
… model is derived in combination with the BM25 model to enhance probabilistic information retrieval. Experiments on five TREC datasets of varied size and content indicates that the proposed model significantly outperforms the optimized BM25 and DirichletLM in MAP over all datasets with all …
-
Relevance Analysis for Document Retrieval
… main goal of this study is to enhance the Okapi BM25 document retrieval model. In doing so, this research hypothesizes that the structure of text inside documents and queries hold valuable semantic information that can be incorporated into the Okapi BM25 model to increase its performance. …
-
Don’t Judge a Malware by its Binary
… for the reports were computed with both BM25 combined with cosine similarity and a transformer encoder. When we projected sandbox reports into text-embedding space, both BM25 combined with cosine similarity and a transformer encoder revealed finer-grained behavioral structure. In …
-
Math Information Retrieval using a Text Search Engine
… explores how to adapt the state-of-the-art BM25 text ranking method to work well when searching for math and text together. Symbol layout trees are used to represent math formulas, and features are extracted from the trees, which are then used as search terms for BM25. This thesis explores …
-
Improvement in Probabilistic Information Retrieval Model: Rewarding Terms with High Relative Term Frequency
… fundamental probabilistic weighting function, BM25. The study aims to exploit the properties of the combination of relative term frequency and BM25. The extensive experiments and analyses conducted in the thesis are based on six of the TREC official datasets, and the results presented have …
-
End-to-end Neural Information Retrieval
… information retrieval models (QL, QL+RM3, BM25, BM25+RM3), including a strong pseudo-relevance feedback baseline: RM3. With the neural network toolkit MatchZoo, we offer an empirical study of a number of popular neural network ranking models (DSSM, CDSSM, KNRM, DUET, DRMM). Experiments on …
-
iKNOWx Forum Search: a system for case retrieval in online medical forums
… that by adding semantic query weighting to Okapi BM25, we are able to achieve, on average, better search performance when compared with the standard BM25 model. For example, precision at 5 was improved by 8.5% while recall at 100 was improved by 5.31%. In addition, we describe in detail the …
-
Exploring Relations and Graphs for Information Retrieval
… implements many proposed improvements to the BM25 ranking algorithm. In a large-scale reproduction study, we compare these improvements and find that the differences in effectiveness are smaller than we would expect, given the literature. We can easily change between versions of BM25 by …
-
Building a Robust Retrieval System with Dense Retrieval Models
… using heuristic lexical representations, such as BM25, has been widely employed as a first-stage retriever. Recently, driven by advancements in pre-trained transformers and approximate nearest neighbor search, transformer-based dense retrieval models have emerged as a strong alternative to BM25. …
-
Vícejazyčný systém pro odpovídání na otázky nad otevřenou doménou
… dokumentov v rôznych jazykoch pomocou algoritmu BM25 a porovnávam ju s anglickým retrievalom. Používanie viacjazyčných dôkazov sa javí ako prospešné a zlepšuje výkonnosť systému systémov.
-
Answer Re-ranking with bilingual LDA and social QA forum corpus
… compared to a simple matching system via Okapi/BM25. In addition, this thesis compares the performance in several experimental settings to clarify the factor of the result.
-
Developing a Llama-Based Chatbot for CI/CD Question Answering: A Case Study at Ericsson
… indicates that an ensemble retriever, combining BM25 and embedding retrievers, yields the best performance. When evaluated against a ground truth of 72 CI/CD questions and answers at Ericsson, our most accurate chatbot configuration provides fully correct answers for 61.11% of the questions, …
-
Decoupling structure and knowledge: ontology-guided retrieval over neural embeddings
… recall, narrowing the performance gap with a BM25 baseline while maintaining competitive ranking quality. However, this improvement comes with increased computational overhead, highlighting a key trade-off between explainability and efficiency. Overall, this work demonstrates that …
-
Enabling Cross-lingual Information Retrieval for African Languages
… resource for researchers, we also release BM25, dense retrieval, and sparse-dense hybrid baselines to establish a starting point for the development of future systems. We hope that our efforts will stimulate further research in information retrieval for African languages and lead to the …
-
Sistema conversacional RAG para el acceso al conocimiento organizacional mediante búsqueda híbrida y LLM en una empresa logística
… híbrida que combina recuperación léxica (BM25) y semántica (embeddings vectoriales), complementado con reranking mediante Cohere y generación de respuestas mediante un modelo de lenguaje de gran escala (LLM) desplegado en Azure OpenAI. El sistema fue puesto en producción como interfaz …
-
Additive deductive embeddings for planning of natural language proofs
… embeddings in addition to sparse embeddings from BM25. We devise three experiments to demonstrate the effectiveness of embedding models for natural language planning. The first experiment consists of two intrinsic evaluations of Additive Deduction using two off-the-shelf sentence encoders. The …
-
IICON : identifying informative comments in online news
… are based on term matching, such as TF-IDF or BM25, which do not adequately address the issue of identifying comments that do not significantly share terms with the article but are relevant to its context. This paper presents a framework, IICON, specifically designed for online news that takes …
-
Strengthening weak supervision for information retrieval
… a result, unsupervised scoring methods, such as BM25 and TF-IDF, remain strong competitors to deep learning approaches whose counterparts have brought on dramatic improvements in other domains, such as computer vision and natural language processing. However, recent works have shown that it is …
Page 1 of 3