Filters








92 Hits in 6.4 sec

Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding [article]

Zexue He, Bodhisattwa Prasad Majumder, Julian McAuley
2021 arXiv   pre-print
We propose a gradient-based rewriting framework, Detect and Perturb to Neutralize (DEPEN), that first detects sensitive components and masks them for regeneration, then perturbs the generation model at  ...  decoding time under a neutralizing constraint that pushes the (predicted) distribution of sensitive attributes towards a uniform distribution.  ...  To this end, we propose a gradient-based decoding framework for text re-generation by neutralizing a sensitive attribute: Detect and Perturb to Neutralize (DEPEN).  ... 
arXiv:2109.11708v1 fatcat:vytlja3uundx7avleaiuxw33ly

Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding

Zexue He, Bodhisattwa Prasad Majumder, Julian McAuley
2021 Findings of the Association for Computational Linguistics: EMNLP 2021   unpublished
We propose a gradient-based rewriting framework, Detect and Perturb to Neutralize (DEPEN), that first detects sensitive components and masks them for regeneration, then perturbs the generation model at  ...  decoding time under a neutralizing constraint that pushes the (predicted) distribution of sensitive attributes towards a uniform distribution.  ...  Acknowledgments We thank Taylor Berg-Kirkpatrick, Jianmo Ni, Yuheng Zhi, and anonymous reviewers for their valuable suggestions to this work. Our Reference  ... 
doi:10.18653/v1/2021.findings-emnlp.352 fatcat:wwggrmcfajfbjl7il4q2zynzoi

Towards a demonstrator for autonomous object detection on board Gaia

Shan Mignot, Jacobus M. Oschmann, Jr., Mark C. Clampin, Howard A. MacEwen
2010 Space Telescopes and Instrumentation 2010: Optical, Infrared, and Millimeter Wave  
The on-board detection scheme which is the object of this text belongs to this category.  ...  In such systems, the TC decoder and the TM encoder are directly connected to the various equipments via point-to-point links.  ...  The segmentation also corresponds to subdividing the previous operations in pixel-based and object-based domains.  ... 
doi:10.1117/12.857118 fatcat:5z6jahmhszec3bgsvnmapxudym

Deep Learning for Text Style Transfer: A Survey [article]

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 arXiv   pre-print
Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others.  ...  We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data.  ...  Wiki Neutrality Corpus (Pryzant et al. 2020) is the first corpus of biased and neutralized sentence pairs.  ... 
arXiv:2011.00416v5 fatcat:wfw3jfh2mjfupbzrmnztsqy4ny

Deep Learning for Text Style Transfer: A Survey

Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2021 Computational Linguistics  
Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others.  ...  We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data.  ...  Wiki Neutrality Corpus (Pryzant et al. 2020) is the first corpus of biased and neutralized sentence pairs.  ... 
doi:10.1162/coli_a_00426 fatcat:v7vmb62ckfcu5k5mpu2pydnrxy

Text Style Transfer: A Review and Experimental Evaluation [article]

Zhiqiang Hu, Roy Ka-Wei Lee, Charu C. Aggarwal, Aston Zhang
2021 arXiv   pre-print
More concretely, we create a taxonomy to organize the TST models and provide a comprehensive summary of the state of the art.  ...  The stylistic properties of text have intrigued computational linguistics researchers in recent years.  ...  The inferred latent representation is then used to generate the sentence of a specific style via a decoder.  ... 
arXiv:2010.12742v2 fatcat:gmkjxf7f7jhivbo6mayaxjsk7q

Artificial intelligence in the creative industries: a review

Nantheera Anantrasirichai, David Bull
2021 Artificial Intelligence Review  
We critically examine the successes and limitations of this rapidly advancing technology in each of these areas.  ...  The potential of AI (or its developers) to win awards for its original creations in competition with human creatives is also limited, based on contemporary technologies.  ...  It takes an initial set of object detections (see Sect. 3.4), creates a unique ID for each of these initial detections, and then tracks each of the objects, via their properties, over time.  ... 
doi:10.1007/s10462-021-10039-7 fatcat:tcctdi7vprfx7mlujvqmpiy3ru

Cosmology at low frequencies: The 21cm transition and the high-redshift Universe

Steven R. Furlanetto, S. Peng Oh, Frank H. Briggs
2006 Physics reports  
Observations of the high-redshift Universe with the 21 cm hyperfine line of neutral hydrogen promise to open an entirely new window onto the early phases of cosmic structure formation.  ...  We also discuss the experimental challenges involved in detecting this signal, with an emphasis on the Galactic and extragalactic foregrounds.  ...  We are grateful to our editor and referee, Marc Kamionkowski, for his patience, careful reading of the manuscript, and incisive criticism. We also thank C. Carilli, M. Morales, J. Pritchard, and O.  ... 
doi:10.1016/j.physrep.2006.08.002 fatcat:viqrqngp2ze7lfd4e7rszhoqpy

Towards Explainable Fact Checking [article]

Isabelle Augenstein
2021 arXiv   pre-print
This development has spurred research in the area of automatic fact checking, from approaches to detect check-worthy claims and determining the stance of tweets towards claims, to methods to determine  ...  These automatic methods are often content-based, using natural language processing methods, which in turn utilise deep neural networks to learn higher-order features from text in order to make predictions  ...  • We study and compare the characteristics of different groups of explainability techniques (gradient-based, perturbation-based, simplification-based) in three different application tasks  ... 
arXiv:2108.10274v2 fatcat:5s4an6irezcjfmvvhmiaeqarh4

Steps Towards a Theory of Visual Information: Active Perception, Signal-to-Symbol Conversion and the Interplay Between Sensing and Control [article]

Stefano Soatto
2017 arXiv   pre-print
It has ramifications in vision-based control, navigation, 3-D reconstruction and rendering, as well as detection, localization, recognition and categorization of objects and scenes in live video.  ...  This manuscript describes the elements of a theory of information tailored to control and decision tasks and specifically to visual data.  ...  therefore it can be neutralized ("inverted") by performing co-variant detection on the image.  ... 
arXiv:1110.2053v4 fatcat:utdycuug75drzkm2a4s74ozeg4

A high-bias, low-variance introduction to Machine Learning for physicists [article]

Pankaj Mehta, Marin Bukov, Ching-Hao Wang, Alexandre G.R. Day, Clint Richardson, Charles K. Fisher, David J. Schwab
2019 arXiv   pre-print
Topics covered in the review include ensemble models, deep learning and neural networks, clustering and data visualization, energy-based models (including MaxEnt models and Restricted Boltzmann Machines  ...  The review begins by covering fundamental concepts in ML and modern statistics such as the bias-variance tradeoff, overfitting, regularization, generalization, and gradient descent before moving on to  ...  via gradient descent (see section IV).  ... 
arXiv:1803.08823v2 fatcat:vmtp62jyvjfxhpidpdcozfnza4

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.  ...  Throughout, the text discusses historical context and societal impact. We invite readers from all backgrounds; some experience with probability, calculus, and linear algebra suffices.  ...  based on the received reward at this perturbed value.  ... 
arXiv:2102.05242v2 fatcat:wy47g4fojnfuxngklyewtjtqdi

What is quantitative plant biology?

Daphné Autran, George W. Bassel, Eunyoung Chae, Daphne Ezer, Ali Ferjani, Christian Fleck, Olivier Hamant, Félix P. Hartmann, Yuling Jiao, Iain G. Johnston, Dorota Kwiatkowska, Boon L. Lim (+9 others)
2021 Quantitative Plant Biology  
Quantitative plant biology is an interdisciplinary field that builds on a long history of biomathematics and biophysics.  ...  Quantitative features such as variability, noise, robustness, delays or feedback loops are included to account for the inner dynamics of plants and their interactions with the environment.  ...  Acknowledgement We are thankful to our colleagues and the larger community for fruitful discussions on this topic.  ... 
doi:10.1017/qpb.2021.8 fatcat:6v6d6zki5ne6ngjhd6zb73obwq

Functional Representation of Prototypes in LVQ and Relevance Learning [chapter]

Friedrich Melchert, Udo Seiffert, Michael Biehl
2016 Advances in Intelligent Systems and Computing  
Held yearly, the objective of BNAIC is to promote and disseminate recent research developments in Artificial Intelligence within Belgium, Luxembourg and the Netherlands.  ...  We received 93 submissions, consisting of 24 regular papers, 47 short papers, 11 demonstration abstracts and 11 thesis abstracts.  ...  This work successfully builds on previous theories from the field of new media and linguistics.  ... 
doi:10.1007/978-3-319-28518-4_28 fatcat:uwxvq6txmrba3ajulmblafgh2a

Ranking to Learn and Learning to Rank: On the Role of Ranking in Pattern Recognition Applications [article]

Giorgio Roffo
2017 arXiv   pre-print
The last decade has seen a revolution in the theory and application of machine learning and pattern recognition.  ...  For example, in pattern classification tasks, different data representations can complicate and hide the different explanatory factors of variation behind the data.  ...  weights and biases.  ... 
arXiv:1706.05933v1 fatcat:oc4xtmyqkvf4njpqsojewv75qu
« Previous Showing results 1 — 15 out of 92 results