Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Information": models, code, and papers

A Feature Analysis for Multimodal News Retrieval

Jul 13, 2020
Golsa Tahmasebzadeh, Sherzod Hakimov, Eric Müller-Budack, Ralph Ewerth

Content-based information retrieval is based on the information contained in documents rather than using metadata such as keywords. Most information retrieval methods are either based on text or image. In this paper, we investigate the usefulness of multimodal features for cross-lingual news search in various domains: politics, health, environment, sport, and finance. To this end, we consider five feature types for image and text and compare the performance of the retrieval system using different combinations. Experimental results show that retrieval results can be improved when considering both visual and textual information. In addition, it is observed that among textual features entity overlap outperforms word embeddings, while geolocation embeddings achieve better performance among visual features in the retrieval task.

* CLEOPATRA Workshop co-located with ESWC 2020 

  Access Paper or Ask Questions

DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker

Mar 03, 2017
Matej Moravčík, Martin Schmid, Neil Burch, Viliam Lisý, Dustin Morrill, Nolan Bard, Trevor Davis, Kevin Waugh, Michael Johanson, Michael Bowling

Artificial intelligence has seen several breakthroughs in recent years, with games often serving as milestones. A common feature of these games is that players have perfect information. Poker is the quintessential game of imperfect information, and a longstanding challenge problem in artificial intelligence. We introduce DeepStack, an algorithm for imperfect information settings. It combines recursive reasoning to handle information asymmetry, decomposition to focus computation on the relevant decision, and a form of intuition that is automatically learned from self-play using deep learning. In a study involving 44,000 hands of poker, DeepStack defeated with statistical significance professional poker players in heads-up no-limit Texas hold'em. The approach is theoretically sound and is shown to produce more difficult to exploit strategies than prior approaches.


  Access Paper or Ask Questions

Techniques for Feature Extraction In Speech Recognition System : A Comparative Study

May 06, 2013
Urmila Shrawankar, V M Thakare

The time domain waveform of a speech signal carries all of the auditory information. From the phonological point of view, it little can be said on the basis of the waveform itself. However, past research in mathematics, acoustics, and speech technology have provided many methods for converting data that can be considered as information if interpreted correctly. In order to find some statistically relevant information from incoming data, it is important to have mechanisms for reducing the information of each segment in the audio signal into a relatively small number of parameters, or features. These features should describe each segment in such a characteristic way that other similar segments can be grouped together by comparing their features. There are enormous interesting and exceptional ways to describe the speech signal in terms of parameters. Though, they all have their strengths and weaknesses, we have presented some of the most used methods with their importance.

* International Journal Of Computer Applications In Engineering, Technology and Sciences (IJCAETS),ISSN 0974-3596,2010,pp 412-418 
* Pages: 9 Figures : 3 

  Access Paper or Ask Questions

Distributed Self Management for Distributed Security Systems

May 13, 2008
Michael Hilker

Distributed system as e.g. artificial immune systems, complex adaptive systems, or multi-agent systems are widely used in Computer Science, e.g. for network security, optimisations, or simulations. In these systems, small entities move through the network and perform certain tasks. At some time, the entities move to another place and require therefore information where to move is most profitable. Common used systems do not provide any information or use a centralised approach where a center delegates the entities. This article discusses whether small information about the neighbours enhances the performance of the overall system or not. Therefore, two information-protocols are introduced and analysed. In addition, the protocols are implemented and tested using the artificial immune system SANA that protects a network against intrusions.

* Proceedings of the 2nd International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA 2007), September 2007, Zhengzhou, China 
* 12 pages, 3 figures 

  Access Paper or Ask Questions

Cross-language Information Retrieval

Nov 10, 2021
Petra Galuščáková, Douglas W. Oard, Suraj Nair

Two key assumptions shape the usual view of ranked retrieval: (1) that the searcher can choose words for their query that might appear in the documents that they wish to see, and (2) that ranking retrieved documents will suffice because the searcher will be able to recognize those which they wished to find. When the documents to be searched are in a language not known by the searcher, neither assumption is true. In such cases, Cross-Language Information Retrieval (CLIR) is needed. This chapter reviews the state of the art for cross-language information retrieval and outlines some open research questions.

* 45 pages, 0 figures 

  Access Paper or Ask Questions

Multi-Level Network for High-Speed Multi-Person Pose Estimation

Nov 26, 2019
Ying Huang, Jiankai Zhuang, Zengchang Qin

In multi-person pose estimation, the left/right joint type discrimination is always a hard problem because of the similar appearance. Traditionally, we solve this problem by stacking multiple refinement modules to increase network's receptive fields and capture more global context, which can also increase a great amount of computation. In this paper, we propose a Multi-level Network (MLN) that learns to aggregate features from lower-level (left/right information), upper-level (localization information), joint-limb level (complementary information) and global-level (context) information for discrimination of joint type. Through feature reuse and its intra-relation, MLN can attain comparable performance to other conventional methods while runtime speed retains at 42.2 FPS.

* 5 pages, published at ICIP 2019 

  Access Paper or Ask Questions

Métodos de Otimização Combinatória Aplicados ao Problema de Compressão MultiFrases

Mar 19, 2017
Elvys Linhares Pontes, Thiago Gouveia da Silva, Andréa Carneiro Linhares, Juan-Manuel Torres-Moreno, Stéphane Huet

The Internet has led to a dramatic increase in the amount of available information. In this context, reading and understanding this flow of information have become costly tasks. In the last years, to assist people to understand textual data, various Natural Language Processing (NLP) applications based on Combinatorial Optimization have been devised. However, for Multi-Sentences Compression (MSC), method which reduces the sentence length without removing core information, the insertion of optimization methods requires further study to improve the performance of MSC. This article describes a method for MSC using Combinatorial Optimization and Graph Theory to generate more informative sentences while maintaining their grammaticality. An experiment led on a corpus of 40 clusters of sentences shows that our system has achieved a very good quality and is better than the state-of-the-art.

* 12 pages, 1 figure, 3 tables (paper in Portuguese), Preprint of XLVIII Simp\'osio Brasileiro de Pesquisa Operacional, 2016, Vit\'oria, ES, (Brazil) 

  Access Paper or Ask Questions

On-Average KL-Privacy and its equivalence to Generalization for Max-Entropy Mechanisms

May 08, 2016
Yu-Xiang Wang, Jing Lei, Stephen E. Fienberg

We define On-Average KL-Privacy and present its properties and connections to differential privacy, generalization and information-theoretic quantities including max-information and mutual information. The new definition significantly weakens differential privacy, while preserving its minimalistic design features such as composition over small group and multiple queries as well as closeness to post-processing. Moreover, we show that On-Average KL-Privacy is **equivalent** to generalization for a large class of commonly-used tools in statistics and machine learning that samples from Gibbs distributions---a class of distributions that arises naturally from the maximum entropy principle. In addition, a byproduct of our analysis yields a lower bound for generalization error in terms of mutual information which reveals an interesting interplay with known upper bounds that use the same quantity.


  Access Paper or Ask Questions

Voxel-informed Language Grounding

May 19, 2022
Rodolfo Corona, Shizhan Zhu, Dan Klein, Trevor Darrell

Natural language applied to natural 2D images describes a fundamentally 3D world. We present the Voxel-informed Language Grounder (VLG), a language grounding model that leverages 3D geometric information in the form of voxel maps derived from the visual input using a volumetric reconstruction model. We show that VLG significantly improves grounding accuracy on SNARE, an object reference game task. At the time of writing, VLG holds the top place on the SNARE leaderboard, achieving SOTA results with a 2.0% absolute improvement.

* ACL 2022 

  Access Paper or Ask Questions

Kernel-based Information Criterion

Dec 15, 2014
Somayeh Danafar, Kenji Fukumizu, Faustino Gomez

This paper introduces Kernel-based Information Criterion (KIC) for model selection in regression analysis. The novel kernel-based complexity measure in KIC efficiently computes the interdependency between parameters of the model using a variable-wise variance and yields selection of better, more robust regressors. Experimental results show superior performance on both simulated and real data sets compared to Leave-One-Out Cross-Validation (LOOCV), kernel-based Information Complexity (ICOMP), and maximum log of marginal likelihood in Gaussian Process Regression (GPR).

* We modified the reference 17, and the subcaptions of Figure 3 

  Access Paper or Ask Questions

<<
282
283
284
285
286
287
288
289
290
291
292
293
294
>>