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 29 for “"Dense Retrieval"”.
-
Building a Robust Retrieval System with Dense Retrieval Models
First-stage retrieval plays a pivotal role in modern search engines, aiming to gather candidates from a large corpus for various downstream tasks, such as question answering, fact-checking, and retrieval-augmented generation. Historically, retrieval using heuristic lexical representations, such as …
-
Neural pseudo-relevance feedback models for information retrieval
… Moreover, even with well-formed user queries, retrieval failures can still occur, caused by lexical or semantic mismatches, or both, between the language of the user’s query and that used in the relevant documents. Pseudo-relevance feedback (PRF) techniques, which modify a query’s …
-
Predicting retrieval failures in conversational recommendation systems
… performance of CRS models by treating them as dense retrieval processes, where both the image retrieved items and textual feedback can be represented with dense embedded representations. In particular, we propose a set of coherence-based dense QPPs specifically designed for …
-
In-Context Retrieval for Molecules and Chemical Synthesis Pathways
… grounded in real-world chemical information retrieval needs, First, in collaboration with domain expert chemists, we developed a graded relevance benchmark comprising 35 diverse query topics, each with 10--30 expert-assessed candidates pooled from a retrieval pipeline combining specialized …
-
Enabling Cross-lingual Information Retrieval for African Languages
… a test collection for cross-lingual information retrieval research in 15 diverse African languages automatically created from Wikipedia. The dataset comprises 6 million queries in English and 23 million relevance judgments automatically extracted from Wikipedia inter-language links. We extract …
-
Improving User Sparse Query Interpretation Through Pseudo-Relevance Retrieval Methods
Despite the rapid development of information retrieval technology, understanding sparse user query remains a significant challenge. Users often input short, ambiguous, or context-lacking queries when searching, making it difficult for retrieval systems to capture user intent. This thesis focuses on …
-
Retrieval-augmented speech-based question answering system
… nad benchmarkem SLUE-SQA5 využívající přepisy, dense retrieval, reranking a extraktivní odpovídání na otázky, následovaná evaluací odpovídání na otázky na základě audia pomocí modelu Qwen2-Audio-7B-Instruct. Práce identifikuje několik omezení tohoto audio-jazykového modelu, mezi která patří …
-
IICON : identifying informative comments in online news
… most insightful comments. We develop sparse and dense retrieval models to work within IICON. To evaluate these methods, we create a training corpus of 18K news articles having 1M user comments from the Guardian. We also create an expert annotated testbed benchmark for which experiments show that …
-
Integrating pre-trained language models into novel query expansion pipelines
… personal and professional life. Information Retrieval (IR) is the academic f ield that focuses on discovering useful information (documents) that fulfil a user’s information need (query). In particular, search systems process a user query and return a ranked list of documents determined by …
-
Evidence-Grounded Biomedical Question Answering: Design, Analysis, and Evaluation
… staged process in which question representation, retrieval, evidence preparation, generation, citation control, and evaluation jointly determine the final answer. The main experimental setting is TREC 2025 BioGen Task B. Five modular systems were developed using sparse and dense retrieval …
-
Utilizing large language models and attention networks as AI copilots for enhanced decision-making in healthcare and defense
… is paramount. Traditional information retrieval systems often struggle with contextual understanding, leading to significant operational inefficiencies. This dissertation presents a novel approach to integrating Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs) and …
-
Beyond Semantic Matching: Integrating Graph Structures, Boolean Logic, and Interactive Aggregation in Modern Retrieval
… Language Processing (NLP) and Information Retrieval (IR) systems have achieved remarkable success in semantic understanding; however, they continue to struggle with complex logical reasoning, structural interactions, and dynamic aggregation. This dissertation presents a comprehensive …
-
Graph-Based Retrieval-Augmented Generation for Cancer Clinical Decision Support: Explainable Paths with Cross-Patient Cohort Reasoning
… and longitudinal outcomes. Conventional retrievalaugmented generation (RAG) systems index these data as flat text chunks, which weakens relational reasoning across patients and limits auditable evidence tracing. This thesis presents GRAG-Cancer, a graph-augmented retrieval framework that …
-
Retrieving Supporting Evidence for Generative Question Answering
… from the MS MARCO (V1) test collection, and a retrieval pipeline consisting of sparse retrieval, dense retrieval and neural rerankers. In the first experiment, we validate the generated answer in its entirety. After presenting a question to an LLM and receiving a generated answer, we query the …
-
An In-Depth Exploration of the High-Quality Entity Linking for Information Retrieval: MMEAD
… unstructured data. While traditional information retrieval primarily relied on keyword-based searches, it often yielded contextually insufficient and ambiguous results. Entity linking fundamentally involves connecting distinct mentions to specific entities in a knowledge base. This process not …
-
Teaching Smaller Language Models To Generalise To Unseen Compositional Questions
… local Wikipedia corpus queried using a multi-hop dense retrieval system with novel extensions, and from rationales generated from a larger Language Model optimised to run in a lower resource environment. Our main contributions to the study of question-answering in this setting are as follows: We …
-
Facilitating Cross-Lingual Information Retrieval Evaluations for African Languages
… the importance of cross-lingual information retrieval (CLIR) in accessing information that is present in a different language. To support CLIR studies, test collections are actively curated in the information retrieval (IR) field for the evaluation of methods and systems. Resources which …
-
Facilitating Information Access for Heterogeneous Data Across Many Languages
… from academia and industry. Systems for document retrieval and question answering have helped people access information in powerful and useful ways. Recently, natural language technologies based on neural network have been applied to various tasks for information access. Specifically, …
-
Multilingual Embeddings: Data, Training, and Understanding
… search engines, question answering systems, retrieval-augmented generation, and nowadays agentic search pipelines. By converting text-space search into vector-space search, embedding models provide semantic matching beyond exact lexical overlap. However, their progress has been uneven across …
-
Page Evidence Promotion for Open-Domain Multimodal Document Question Answering
… model can generate an answer. Although modern retrieval systems may return hundreds or thousands of candidate pages, the answer model typically receives only the highest-ranked few. Consequently, relevant evidence may already be present in the candidate pool yet remain unavailable to the answer …
Page 1 of 2