17 Hits in 5.8 sec

A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach [article]

Xiaohan Lan, Yitian Yuan, Xin Wang, Long Chen, Zhi Wang, Lin Ma, Wenwu Zhu
2022 arXiv   pre-print
In this paper, we take a closer look at existing evaluation protocols, and find both the prevailing dataset and evaluation metrics are the devils that lead to untrustworthy benchmarking.  ...  Temporal Sentence Grounding in Videos (TSGV), which aims to ground a natural language sentence in an untrimmed video, has drawn widespread attention over the past few years.  ...  CONCLUSION In this paper, we take a closer look at mainstream benchmark datasets for temporal sentence grounding in videos and finds that there exists significant annotation bias, resulting in highly untrustworthy  ... 
arXiv:2203.05243v1 fatcat:lkyv5znigvdedfsffmnsslxq2e

A Roadmap for Big Model [article]

Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han (+88 others)
2022 arXiv   pre-print
In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view.  ...  At present, there is a lack of research work that sorts out the overall progress of BMs and guides the follow-up research.  ...  -KoBE [1303] is a simple and effective metric that grounds the entities detected in the source and translated sentences and then calculate the recall of the grounded entities found in the translated  ... 
arXiv:2203.14101v4 fatcat:rdikzudoezak5b36cf6hhne5u4

Synthetic Data – what, why and how? [article]

James Jordon, Lukasz Szpruch, Florimond Houssiau, Mirko Bottarelli, Giovanni Cherubin, Carsten Maple, Samuel N. Cohen, Adrian Weller
2022 arXiv   pre-print
We do believe that synthetic data is a very useful tool, and our hope is that this report highlights that, while drawing attention to nuances that can easily be overlooked in its deployment.  ...  The article is intended for a non-technical audience, though some formal definitions have been given to provide clarity to specialists.  ...  Acknowledgements We would like to thank Accenture, Hazy, HSBC, MOSTLY AI, and the Office for National Statistics for their participation in our interviews.  ... 
arXiv:2205.03257v1 fatcat:2sdjqyfdivb4hnxn3jr2j5e6q4

DMoG : A Data-Based Morphological Guesser

Vojtěch Kovář, Pavel Rychlý
2021 Zenodo  
We present a novel corpus-based approach to lemmatization of unknown words.  ...  A lemma candidate then comes from the pattern whose predictions are really found in the corpus. We present a prototype implementation and an initial evaluation on Czech, which shows promising results.  ...  The South Moravian Centre graciously funded the second author's work for International Mobility as a part of the Brno PhD. Talent project.  ... 
doi:10.5281/zenodo.6935329 fatcat:6jqt25fjcfe5fmcwfkmv2al4oe

Deep Reinforcement Learning [article]

Yuxi Li
2018 arXiv   pre-print
We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details.  ...  We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts.  ...  The authors propose policy-space response oracle (PSRO), and its approximation, deep cognitive hierarchies (DCH), to compute best responses to a mixture of policies using deep RL, and to compute new meta-strategy  ... 
arXiv:1810.06339v1 fatcat:kp7atz5pdbeqta352e6b3nmuhy

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
2022 arXiv   pre-print
We discuss different approaches and levels of attention to these topics, making them tangible, and distill them into a set of best practices for the curation of novel resources.  ...  In this work, we target data documentation debt by surveying over two hundred datasets employed in algorithmic fairness research, and producing standardized and searchable documentation for each of them  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc Behaghel, Asia Biega, Marko Bohanec, Chris  ... 
arXiv:2202.01711v3 fatcat:kd546yklwjhvtkrbhtzgbzb2xm

Health Misinformation in Search and Social Media

Amira Ghenai
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
with Yelena Mejova in the parts presented in Chapters 3 and 4.  ...  Yelena was a scientist in the Qatar Computing Research Institute, a member of the Qatar Foundation organization where I received my doctoral scholarship, during the time we were collaborating.  ...  Extending the work proposed in Chapter 4, it would be interesting to identify who is spreading such information and how it is reaching the public.  ... 
doi:10.1145/3077136.3084153 dblp:conf/sigir/Ghenai17 fatcat:na5rjxfgw5e6togqpdkgwmk4se

Learning from Multimodal Web Data

John Miles Hessel
captioning dataset (because post-hoc annotators only mention "London" in captions if the image is iconically so), but not in a Flickr image tagging dataset (because users may tag any image that happens  ...  To this end, we present algorithms that discover grounded image-text relationships from noisy, long documents, e.g., Wikipedia articles and the images they contain.  ...  A Closer Look at the Generation Task To better understand the generation task, we computed lower and upper bounds for generation performance using a constant-prediction baseline and human performance,  ... 
doi:10.7298/fzce-qv86 fatcat:limoc6b6xjgm5b2dbzh3f72tuq

Challenges in Ensuring Financial Competencies: Essays on How to Measure Financial Knowledge, Target Beneficiaries and Deliver Educational Programmes

Nadia Linciano, Paola Soccorso, Daniela Di Cagno, Luca Panaccione, Gianni Nicolini, Matteo Ploner, Caterina Lucarelli, Gianni Brighetti, Enrico Maria Cervellati, Emanuela Rinaldi, Riccardo Viale, Duccio Martelli (+6 others)
2017 Social Science Research Network  
Essays on how to measure financial knowledge, target beneficiaries and deliver educational programmes N. Linciano and P.  ...  I Quaderni giuridici accolgono lavori di ricerca volti a contribuire al dibattito accademico su questioni di diritto.  ...  On policy grounds, regulators aiming to make financial education truly effective at overcoming knowledge and cognitive gaps should also worry about debiasing the financial education process.  ... 
doi:10.2139/ssrn.3067333 fatcat:fnub2qx72jc5nnxpyj7fkyhwem

Patterns, predictions, and actions: A story about machine learning [article]

Moritz Hardt, Benjamin Recht
2021 arXiv   pre-print
A chapter on datasets as benchmarks examines their histories and scientific bases.  ...  This graduate textbook on machine learning tells a story of how patterns in data support predictions and consequential actions.  ...  In this chapter, we take a closer look at popular datasets in the field of machine learning and the benchmarks that they support.  ... 
arXiv:2102.05242v2 fatcat:wy47g4fojnfuxngklyewtjtqdi

Transparent Analysis of Multi-Modal Embeddings

Anita Lilla Verő, Apollo-University Of Cambridge Repository, Copestake Ann
Multi-modal semantics aims to enhance Embeddings with perceptual input, based on the assumption that the representation of meaning in humans is grounded in sensory experience.  ...  Firstly, we present comprehensive analyses of how various visual and linguistic models behave in semantic similarity and brain imaging evaluation tasks.  ...  This can include low level features such as edges and corners, or higher level ones such as objects of an image or temporal patterns on a video.  ... 
doi:10.17863/cam.86224 fatcat:yffvb47l4bayjm27jnz27ixu7e

Socio-cognitive factors that affect decision-making in cancer multidisciplinary team meetings

Tajana Soukup Ascencao, Nick Sevdalis, James Green, Ara Darzi, National Institute For Health Research (Great Britain)
While they facilitate diverse disciplinary input into formulation of treatment recommendations, evidence of this approach is unclear with a common pattern of skewed inputs by senior physicians and biomedical  ...  The decision-making (DM) in MDMs is a highly intricate process, however.  ...  In these sessions, we watched the videos while looking at the transcripts, noting down elements of interaction, discussing them and their interpretation, formulating points of interest in the data, and  ... 
doi:10.25560/79603 fatcat:qyn5paimlbbbfoedhrdccr3via

A Topic is Not a Theme: Towards a Contextualised Approach to Topic Modelling

There is a disconnect between an understanding of the processes of machine learning at a technical level and the societal impact of these technologies.  ...  Researchers have increasingly applied topic models to social media datasets to study social phenomena.  ...  Acknowledgments We thank Callum Waugh, who was instrumental in the initial stages of this study, and Elliot Freeman and Elizabeth Daniels who conducted the expert annotations.  ... 
doi:10.26180/20280312 fatcat:uib2xvkuxnfcngei352y56kvme

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
We discuss different approaches and levels of attention to these topics, making them tangible, and distill them into a set of best practices for the curation of novel datasets.  ...  In this work, we survey over two hundred datasets employed in algorithmic fairness research, producing standardized and searchable documentation for each of them, along with in-depth documentation for  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc  ... 
doi:10.48550/arxiv.2202.01711 fatcat:mav36x3w5namjhurzpevtsmsju

TeaP 2020 - Abstracts of the 62nd Conference of Experimental Psychologists

(:Unkn) Unknown, Leibniz Institut Für Psychologie (ZPID), Christian Dobel, Carina Giesen, Laura Anne Grigutsch, Jürgen M. Kaufmann, Gyula Kovács, Franziska Meissner, Klaus Rothermund, Stefan R. Schweinberger
Contains Keynote Lectures, Contributions and Author Index of the 62nd Conference of Experimental Psychologists  ...  A special opportunity for automated individual mobility lies in the possibility to perform office work during traveling and commuting.  ...  However, traditional (automotive and office) user interfaces were not optimized for this purpose, and thus, may be preventing effective productivity and even present a safety risk in conditional automation  ... 
doi:10.23668/psycharchives.5176 fatcat:67c63hw2bnal5bnfydwg5nvuta
« Previous Showing results 1 — 15 out of 17 results