Výsledky vyhledávání - "HOSSEINI, KASRA"

Report

Retrieve, Annotate, Evaluate, Repeat: Leveraging Multimodal LLMs for Large-Scale Product Retrieval Evaluation

Autor: Hosseini, Kasra, Kober, Thomas, Krapac, Josip, Vollgraf, Roland, Cheng, Weiwei, Ramallo, Ana Peleteiro

Evaluating production-level retrieval systems at scale is a crucial yet challenging task due to the limited availability of a large pool of well-trained human annotators. Large Language Models (LLMs) have the potential to address this scaling issue a

Externí odkaz: http://arxiv.org/abs/2409.11860

Zobrazit plný text záznamu

Report

Faking feature importance: A cautionary tale on the use of differentially-private synthetic data

Autor: Giles, Oscar, Hosseini, Kasra, Mingas, Grigorios, Strickson, Oliver, Bowler, Louise, Smith, Camila Rangel, Wilde, Harrison, Lim, Jen Ning, Mateen, Bilal, Amarasinghe, Kasun, Ghani, Rayid, Heppenstall, Alison, Lomax, Nik, Malleson, Nick, O'Reilly, Martin, Vollmerteke, Sebastian

Synthetic datasets are often presented as a silver-bullet solution to the problem of privacy-preserving data publishing. However, for many applications, synthetic data has been shown to have limited utility when used to train predictive models. One p

Externí odkaz: http://arxiv.org/abs/2203.01363

Zobrazit plný text záznamu

Report

MapReader: A Computer Vision Pipeline for the Semantic Exploration of Maps at Scale

Autor: Hosseini, Kasra, Wilson, Daniel C. S., Beelen, Kaspar, McDonough, Katherine

We present MapReader, a free, open-source software library written in Python for analyzing large map collections (scanned or born-digital). This library transforms the way historians can use maps by turning extensive, homogeneous map sets into search

Externí odkaz: http://arxiv.org/abs/2111.15592

Zobrazit plný text záznamu

Report

Neural Language Models for Nineteenth-Century English

Autor: Hosseini, Kasra, Beelen, Kaspar, Colavizza, Giovanni, Ardanuy, Mariona Coll

We present four types of neural language models trained on a large historical dataset of books in English, published between 1760-1900 and comprised of ~5.1 billion tokens. The language model architectures include static (word2vec and fastText) and c

Externí odkaz: http://arxiv.org/abs/2105.11321

Zobrazit plný text záznamu

Report

A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching

Autor: Ardanuy, Mariona Coll, Hosseini, Kasra, McDonough, Katherine, Krause, Amrey, van Strien, Daniel, Nanni, Federico

Recognizing toponyms and resolving them to their real-world referents is required for providing advanced semantic access to textual data. This process is often hindered by the high degree of variation in toponyms. Candidate selection is the task of i

Externí odkaz: http://arxiv.org/abs/2009.08114

Zobrazit plný text záznamu

Report

Living Machines: A study of atypical animacy

Autor: Ardanuy, Mariona Coll, Nanni, Federico, Beelen, Kaspar, Hosseini, Kasra, Ahnert, Ruth, Lawrence, Jon, McDonough, Katherine, Tolfo, Giorgia, Wilson, Daniel CS, McGillivray, Barbara

This paper proposes a new approach to animacy detection, the task of determining whether an entity is represented as animate in a text. In particular, this work is focused on atypical animacy and examines the scenario in which typically inanimate obj

Externí odkaz: http://arxiv.org/abs/2005.11140

Zobrazit plný text záznamu