On the Effects of Regional Spelling Conventions in Retrieval Models [PDF]
SIGIR '23: Proceedings of the 46th International ACM SIGIR
Conference on Research and Development in Information Retrieval, July 2023,
Pages 2220-2224, 2023 One advantage of neural ranking models is that they are meant to generalise well in situations of synonymity i.e. where two words have similar or identical meanings. In this paper, we investigate and quantify how well various ranking models perform in a clear-cut case of synonymity: when words are simply expressed in different surface forms due to ...
arxiv +1 more source
Indian Legal Text Summarization: A Text Normalisation-based Approach [PDF]
, 2022 In the Indian court system, pending cases have long been a problem. There are more than 4 crore cases outstanding. Manually summarising hundreds of documents is a time-consuming and tedious task for legal stakeholders. Many state-of-the-art models for text summarization have emerged as machine learning has progressed. Domain-independent models don't do
arxiv +1 more source
Setting per-field normalisation hyper-parameters for the named-page finding search task [PDF]
, 2007 Per-field normalisation has been shown to be effective for Web search tasks, e.g. named-page finding. However, per-field normalisation also suffers from having hyper-parameters to tune on a per-field basis. In this paper, we argue that the purpose of per-
He, B., Ounis, I.
core +3 more sources
Laparoscopic portosystemic shunt attenuation in two cats
Journal of Feline Medicine and Surgery Open Reports, 2022 Case series summary Gradual attenuation of an extrahepatic portosystemic shunt using cellophane banding was achieved with a laparoscopic technique in two cats.
Francesca Izzo +3 more
doaj +1 more source
Factor model of a comfortable environment for the consumption of cultural services [PDF]
E3S Web of Conferences, 2021 The article presents the results of the research on the comfort of the cultural services consumption environment. The scientific discourses in the segment of the research subject are analysed, and on their basis, 17 evaluation criteria for the empirical ...
Parsieva Larisa +4 more
doaj +1 more source
Normalised clustering accuracy: An asymmetric external cluster validity measure [PDF]
Journal of Classification, 2024, 2022 There is no, nor will there ever be, single best clustering algorithm. Nevertheless, we would still like to be able to distinguish between methods that work well on certain task types and those that systematically underperform. Clustering algorithms are traditionally evaluated using either internal or external validity measures.
arxiv +1 more source
Hypokalaemia in hospitalised patients
Swiss Medical Weekly, 2016 QUESTIONS UNDER STUDY: Hypokalaemia in inpatients is common, and is associated with morbidity and mortality. Its management is risky and not always effective.
Angela Greco +16 more
doaj +1 more source
Integrating simulation into surgical training: a qualitative case study of a national programme
Advances in Simulation, 2023 Background Applying simulation-based education (SBE) into surgical curricula is challenging and exacerbated by the absence of guidance on implementation processes.
Adarsh P. Shah +4 more
doaj +1 more source
Assessing the severity of positive valence symptoms in initial psychiatric evaluation records: Should we use convolutional neural networks? [PDF]
PLoS ONE, 2018 BACKGROUND AND OBJECTIVE:Efficiently capturing the severity of positive valence symptoms could aid in risk stratification for adverse outcomes among patients with psychiatric disorders and identify optimal treatment strategies for patient subgroups ...
Hong-Jie Dai, Jitendra Jonnagaddala
doaj +1 more source
DeepKey: Towards End-to-End Physical Key Replication From a Single Photograph [PDF]
, 2018 This paper describes DeepKey, an end-to-end deep neural architecture capable of taking a digital RGB image of an 'everyday' scene containing a pin tumbler key (e.g.
Alex Krizhevsky +4 more
core +2 more sources