<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "Quantity-centric Search and Retrieval"^^ . "Quantities are essential in documents to describe factual information in domains such as finance, business, medicine, and science.\r\nThis thesis alone encompasses 1,423 quantities within its text. \r\nWhile these account for just 1% of the overall word count, these values contain the most precise and crucial information necessary for analysis and system comparison.\r\nDespite the importance of quantities, only a handful of studies focus on their representation in text and their impact on Information Retrieval (IR).\r\nIn many cases, the information needs of a user revolve around quantities and cannot be resolved without understanding their semantics. \r\nFor instance, in the query ``a used car that has less than 200hp'', the user is looking for a car with a specific parameter range.\r\nTo provide an accurate response, the retrieval method should not only recognize the connection between the car and the quantity in the query but it must also comprehend value comparisons and units. \r\nFurthermore, the retrieved results should contain values less than ``200'' for this specific attribute of a car, requiring an understanding of numerical proximity.\r\n%More specifically, it should identify that the quantity refers to the power of an engine in terms of horsepower, distinct from ``bhp'' or ``brake horsepower'', which measures the power sent to the wheels and is frequently used in the same context. \r\n%Furthermore, the retrieval model should retrieve results that contain values less than ``200'' for this specific attribute of the car, requiring an understanding of numerical proximity.\r\n\r\nHowever, current quantity models often analyze values and units in isolation, disregarding their relationships to other tokens in the text. \r\nAdditionally, modern search engines apply the same ranking mechanisms to both words and quantities, overlooking magnitude and unit information.\r\nAs a result, quantity-centric queries yield sub-par results and often cost the users valuable time navigating through irrelevant content. \\\\\r\nIn this thesis, we address these shortcomings and aim to enhance the quantity understanding of current IR models.\r\nWe start by presenting a holistic quantity model that efficiently models combinations of values and units, changes in the behavior of a\r\n quantity in the given context (e.g., rising or falling), and the concept (related entities or events) of a quantity.\r\nThis quantity model leads to the development of an extraction framework called Comprehensive Quantity Extraction (CQE), which is designed to detect and normalize quantities in text. \r\nAdditionally, we introduce a novel benchmark dataset tailored to evaluate quantity extraction.\r\n \\\\\r\nUsing the quantity extractor, we introduce two quantity-aware retrieval techniques that encompass both classical and neural models.\r\nThese models are designed to rank documents based on the proximity of quantities in the text as well as the textual content. \r\nOne method is the disjoint quantity-aware ranker, which is designed to separate the ranking of quantities and textual tokens by means of a quantity index structure.\r\nThe second method is the joint quantity-aware ranker, which focuses on the joint ranking of quantities and textual tokens by fine-tuning a neural retrieval model on quantity-rich data. \r\nThese techniques incorporate quantity information during ranking in both neural and lexical models, with minimal overhead in terms of efficiency and without the change in the system.\r\nThese models can answer queries containing the numerical conditions equal, greater than, and less than as well as keyword search. \r\nTo evaluate the effectiveness of our ranking models, we introduce two novel benchmark datasets in the domains of finance and medicine. \r\nWe compare our methods on the benchmarks against various classical and neural retrieval systems and show significant improvement in answering quantity-centric queries."^^ . "2024" . . . . . . . "Shideh Satya"^^ . "Almasian"^^ . "Shideh Satya Almasian"^^ . . . . . . "Quantity-centric Search and Retrieval (PDF)"^^ . . . "Thesis.pdf"^^ . . . "Quantity-centric Search and Retrieval (Other)"^^ . . . . . . "indexcodes.txt"^^ . . . "Quantity-centric Search and Retrieval (Other)"^^ . . . . . . "lightbox.jpg"^^ . . . "Quantity-centric Search and Retrieval (Other)"^^ . . . . . . "preview.jpg"^^ . . . "Quantity-centric Search and Retrieval (Other)"^^ . . . . . . "medium.jpg"^^ . . . "Quantity-centric Search and Retrieval (Other)"^^ . . . . . . "small.jpg"^^ . . "HTML Summary of #35543 \n\nQuantity-centric Search and Retrieval\n\n" . "text/html" . . . "004 Informatik"@de . "004 Data processing Computer science"@en . . . "420 Englisch"@de . "420 English"@en . .