May 7, 2019

2813 words 14 mins read

Paper Group ANR 147

Summarizing Situational and Topical Information During Crises. Cost-sensitive Learning for Utility Optimization in Online Advertising Auctions. Finding Optimal Combination of Kernels using Genetic Programming. Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses. Introducing a Calculus of Effects and Handlers for Natur …

Summarizing Situational and Topical Information During Crises


Title	Summarizing Situational and Topical Information During Crises
Authors	Koustav Rudra, Siddhartha Banerjee, Niloy Ganguly, Pawan Goyal, Muhammad Imran, Prasenjit Mitra
Abstract	The use of microblogging platforms such as Twitter during crises has become widespread. More importantly, information disseminated by affected people contains useful information like reports of missing and found people, requests for urgent needs etc. For rapid crisis response, humanitarian organizations look for situational awareness information to understand and assess the severity of the crisis. In this paper, we present a novel framework (i) to generate abstractive summaries useful for situational awareness, and (ii) to capture sub-topics and present a short informative summary for each of these topics. A summary is generated using a two stage framework that first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique and then follows a word graph and concept event based abstractive summarization technique to produce the final summary. High accuracies obtained for all the tasks show the effectiveness of the proposed framework.
Tasks	Abstractive Text Summarization
Published	2016-10-05
URL	http://arxiv.org/abs/1610.01561v1
PDF	http://arxiv.org/pdf/1610.01561v1.pdf
PWC	https://paperswithcode.com/paper/summarizing-situational-and-topical
Repo
Framework

Cost-sensitive Learning for Utility Optimization in Online Advertising Auctions


Title	Cost-sensitive Learning for Utility Optimization in Online Advertising Auctions
Authors	Flavian Vasile, Damien Lefortier, Olivier Chapelle
Abstract	One of the most challenging problems in computational advertising is the prediction of click-through and conversion rates for bidding in online advertising auctions. An unaddressed problem in previous approaches is the existence of highly non-uniform misprediction costs. While for model evaluation these costs have been taken into account through recently proposed business-aware offline metrics – such as the Utility metric which measures the impact on advertiser profit – this is not the case when training the models themselves. In this paper, to bridge the gap, we formally analyze the relationship between optimizing the Utility metric and the log loss, which is considered as one of the state-of-the-art approaches in conversion modeling. Our analysis motivates the idea of weighting the log loss with the business value of the predicted outcome. We present and analyze a new cost weighting scheme and show that significant gains in offline and online performance can be achieved.
Tasks
Published	2016-03-11
URL	http://arxiv.org/abs/1603.03713v3
PDF	http://arxiv.org/pdf/1603.03713v3.pdf
PWC	https://paperswithcode.com/paper/cost-sensitive-learning-for-utility
Repo
Framework

Finding Optimal Combination of Kernels using Genetic Programming


Title	Finding Optimal Combination of Kernels using Genetic Programming
Authors	Jyothi Korra
Abstract	In Computer Vision, problem of identifying or classifying the objects present in an image is called Object Categorization. It is a challenging problem, especially when the images have clutter background, occlusions or different lighting conditions. Many vision features have been proposed which aid object categorization even in such adverse conditions. Past research has shown that, employing multiple features rather than any single features leads to better recognition. Multiple Kernel Learning (MKL) framework has been developed for learning an optimal combination of features for object categorization. Existing MKL methods use linear combination of base kernels which may not be optimal for object categorization. Real-world object categorization may need to consider complex combination of kernels(non-linear) and not only linear combination. Evolving non-linear functions of base kernels using Genetic Programming is proposed in this report. Experiment results show that non-kernel generated using genetic programming gives good accuracy as compared to linear combination of kernels.
Tasks
Published	2016-04-08
URL	http://arxiv.org/abs/1604.02376v2
PDF	http://arxiv.org/pdf/1604.02376v2.pdf
PWC	https://paperswithcode.com/paper/finding-optimal-combination-of-kernels-using
Repo
Framework

Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses


Title	Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
Authors	Christian Rupprecht, Iro Laina, Robert DiPietro, Maximilian Baust, Federico Tombari, Nassir Navab, Gregory D. Hager
Abstract	Many prediction tasks contain uncertainty. In some cases, uncertainty is inherent in the task itself. In future prediction, for example, many distinct outcomes are equally valid. In other cases, uncertainty arises from the way data is labeled. For example, in object detection, many objects of interest often go unlabeled, and in human pose estimation, occluded joints are often labeled with ambiguous values. In this work we focus on a principled approach for handling such scenarios. In particular, we propose a framework for reformulating existing single-prediction models as multiple hypothesis prediction (MHP) models and an associated meta loss and optimization procedure to train them. To demonstrate our approach, we consider four diverse applications: human pose estimation, future prediction, image classification and segmentation. We find that MHP models outperform their single-hypothesis counterparts in all cases, and that MHP models simultaneously expose valuable insights into the variability of predictions.
Tasks	Future prediction, Image Classification, Object Detection, Pose Estimation
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00197v3
PDF	http://arxiv.org/pdf/1612.00197v3.pdf
PWC	https://paperswithcode.com/paper/learning-in-an-uncertain-world-representing
Repo
Framework

Introducing a Calculus of Effects and Handlers for Natural Language Semantics


Title	Introducing a Calculus of Effects and Handlers for Natural Language Semantics
Authors	Jirka Maršík, Maxime Amblard
Abstract	In compositional model-theoretic semantics, researchers assemble truth-conditions or other kinds of denotations using the lambda calculus. It was previously observed that the lambda terms and/or the denotations studied tend to follow the same pattern: they are instances of a monad. In this paper, we present an extension of the simply-typed lambda calculus that exploits this uniformity using the recently discovered technique of effect handlers. We prove that our calculus exhibits some of the key formal properties of the lambda calculus and we use it to construct a modular semantics for a small fragment that involves multiple distinct semantic phenomena.
Tasks
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06125v2
PDF	http://arxiv.org/pdf/1606.06125v2.pdf
PWC	https://paperswithcode.com/paper/introducing-a-calculus-of-effects-and
Repo
Framework

Dialog-based Language Learning


Title	Dialog-based Language Learning
Authors	Jason Weston
Abstract	A long-term goal of machine learning research is to build an intelligent dialog agent. Most research in natural language understanding has focused on learning from fixed training sets of labeled data, with supervision either at the word level (tagging, parsing tasks) or sentence level (question answering, machine translation). This kind of supervision is not realistic of how humans learn, where language is both learned by, and used for, communication. In this work, we study dialog-based language learning, where supervision is given naturally and implicitly in the response of the dialog partner during the conversation. We study this setup in two domains: the bAbI dataset of (Weston et al., 2015) and large-scale question answering from (Dodge et al., 2015). We evaluate a set of baseline learning strategies on these tasks, and show that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher’s response. In particular, a surprising result is that it can learn to answer questions correctly without any reward-based supervision at all.
Tasks	Machine Translation, Question Answering
Published	2016-04-20
URL	http://arxiv.org/abs/1604.06045v7
PDF	http://arxiv.org/pdf/1604.06045v7.pdf
PWC	https://paperswithcode.com/paper/dialog-based-language-learning
Repo
Framework

Symmetric and antisymmetric properties of solutions to kernel-based machine learning problems


Title	Symmetric and antisymmetric properties of solutions to kernel-based machine learning problems
Authors	Giorgio Gnecco
Abstract	A particularly interesting instance of supervised learning with kernels is when each training example is associated with two objects, as in pairwise classification (Brunner et al., 2012), and in supervised learning of preference relations (Herbrich et al., 1998). In these cases, one may want to embed additional prior knowledge into the optimization problem associated with the training of the learning machine, modeled, respectively, by the symmetry of its optimal solution with respect to an exchange of order between the two objects, and by its antisymmetry. Extending the approach proposed in (Brunner et al., 2012) (where the only symmetric case was considered), we show, focusing on support vector binary classification, how such embedding is possible through the choice of a suitable pairwise kernel, which takes as inputs the individual feature vectors and also the group feature vectors associated with the two objects. We also prove that the symmetry/antisymmetry constraints still hold when considering the sequence of suboptimal solutions generated by one version of the Sequential Minimal Optimization (SMO) algorithm, and we present numerical results supporting the theoretical findings. We conclude discussing extensions of the main results to support vector regression, to transductive support vector machines, and to several kinds of graph kernels, including diffusion kernels.
Tasks
Published	2016-06-27
URL	http://arxiv.org/abs/1606.08501v2
PDF	http://arxiv.org/pdf/1606.08501v2.pdf
PWC	https://paperswithcode.com/paper/symmetric-and-antisymmetric-properties-of
Repo
Framework

Defining the Pose of any 3D Rigid Object and an Associated Distance


Title	Defining the Pose of any 3D Rigid Object and an Associated Distance
Authors	Romain Brégier, Frédéric Devernay, Laetitia Leyrit, James Crowley
Abstract	The pose of a rigid object is usually regarded as a rigid transformation, described by a translation and a rotation. However, equating the pose space with the space of rigid transformations is in general abusive, as it does not account for objects with proper symmetries – which are common among man-made objects.In this article, we define pose as a distinguishable static state of an object, and equate a pose with a set of rigid transformations. Based solely on geometric considerations, we propose a frame-invariant metric on the space of possible poses, valid for any physical rigid object, and requiring no arbitrary tuning. This distance can be evaluated efficiently using a representation of poses within an Euclidean space of at most 12 dimensions depending on the object’s symmetries. This makes it possible to efficiently perform neighborhood queries such as radius searches or k-nearest neighbor searches within a large set of poses using off-the-shelf methods. Pose averaging considering this metric can similarly be performed easily, using a projection function from the Euclidean space onto the pose space. The practical value of those theoretical developments is illustrated with an application of pose estimation of instances of a 3D rigid object given an input depth map, via a Mean Shift procedure.
Tasks	Pose Estimation
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04631v3
PDF	http://arxiv.org/pdf/1612.04631v3.pdf
PWC	https://paperswithcode.com/paper/defining-the-pose-of-any-3d-rigid-object-and
Repo
Framework

Some Experimental Issues in Financial Fraud Detection: An Investigation


Title	Some Experimental Issues in Financial Fraud Detection: An Investigation
Authors	J. West, Maumita Bhattacharya
Abstract	Financial fraud detection is an important problem with a number of design aspects to consider. Issues such as algorithm selection and performance analysis will affect the perceived ability of proposed solutions, so for auditors and re-searchers to be able to sufficiently detect financial fraud it is necessary that these issues be thoroughly explored. In this paper we will revisit the key performance metrics used for financial fraud detection with a focus on credit card fraud, critiquing the prevailing ideas and offering our own understandings. There are many different performance metrics that have been employed in prior financial fraud detection research. We will analyse several of the popular metrics and compare their effectiveness at measuring the ability of detection mechanisms. We further investigated the performance of a range of computational intelligence techniques when applied to this problem domain, and explored the efficacy of several binary classification methods.
Tasks	Fraud Detection
Published	2016-01-06
URL	http://arxiv.org/abs/1601.01228v1
PDF	http://arxiv.org/pdf/1601.01228v1.pdf
PWC	https://paperswithcode.com/paper/some-experimental-issues-in-financial-fraud
Repo
Framework

Learning a Pose Lexicon for Semantic Action Recognition


Title	Learning a Pose Lexicon for Semantic Action Recognition
Authors	Lijuan Zhou, Wanqing Li, Philip Ogunbona
Abstract	This paper presents a novel method for learning a pose lexicon comprising semantic poses defined by textual instructions and their associated visual poses defined by visual features. The proposed method simultaneously takes two input streams, semantic poses and visual pose candidates, and statistically learns a mapping between them to construct the lexicon. With the learned lexicon, action recognition can be cast as the problem of finding the maximum translation probability of a sequence of semantic poses given a stream of visual pose candidates. Experiments evaluating pre-trained and zero-shot action recognition conducted on MSRC-12 gesture and WorkoutSu-10 exercise datasets were used to verify the efficacy of the proposed method.
Tasks	Temporal Action Localization
Published	2016-04-01
URL	http://arxiv.org/abs/1604.00147v1
PDF	http://arxiv.org/pdf/1604.00147v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-pose-lexicon-for-semantic-action
Repo
Framework

Challenges of Integrating A Priori Information Efficiently in the Discovery of Spatio-Temporal Objects in Large Databases


Title	Challenges of Integrating A Priori Information Efficiently in the Discovery of Spatio-Temporal Objects in Large Databases
Authors	Benjamin Schott, Johannes Stegmaier, Masanari Takamiya, Ralf Mikut
Abstract	Using the knowledge discovery framework, it is possible to explore object databases and extract groups of objects with highly heterogeneous movement behavior by efficiently integrating a priori knowledge through interacting with the framework. The whole process is modular expandable and is therefore adaptive to any problem formulation. Further, the flexible use of different information allocation processes reveal a great potential to efficiently incorporate the a priori knowledge of different users in different ways. Therefore, the stepwise knowledge discovery process embedded in the knowledge discovery framework is described in detail to point out the flexibility of such a system incorporating object databases from different applications. The described framework can be used to gain knowledge out of object databases in many different fields. This knowledge can be used to gain further insights and improve the understanding of underlying phenomena. The functionality of the proposed framework is exemplarily demonstrated using a benchmark database based on real biological object data.
Tasks
Published	2016-02-09
URL	http://arxiv.org/abs/1602.02938v1
PDF	http://arxiv.org/pdf/1602.02938v1.pdf
PWC	https://paperswithcode.com/paper/challenges-of-integrating-a-priori
Repo
Framework

A Simple Practical Accelerated Method for Finite Sums


Title	A Simple Practical Accelerated Method for Finite Sums
Authors	Aaron Defazio
Abstract	We describe a novel optimization method for finite sums (such as empirical risk minimization problems) building on the recently introduced SAGA method. Our method achieves an accelerated convergence rate on strongly convex smooth problems. Our method has only one parameter (a step size), and is radically simpler than other accelerated methods for finite sums. Additionally it can be applied when the terms are non-smooth, yielding a method applicable in many areas where operator splitting methods would traditionally be applied.
Tasks
Published	2016-02-08
URL	http://arxiv.org/abs/1602.02442v2
PDF	http://arxiv.org/pdf/1602.02442v2.pdf
PWC	https://paperswithcode.com/paper/a-simple-practical-accelerated-method-for
Repo
Framework

Distributed Entity Disambiguation with Per-Mention Learning


Title	Distributed Entity Disambiguation with Per-Mention Learning
Authors	Tiep Mai, Bichen Shi, Patrick K. Nicholson, Deepak Ajwani, Alessandra Sala
Abstract	Entity disambiguation, or mapping a phrase to its canonical representation in a knowledge base, is a fundamental step in many natural language processing applications. Existing techniques based on global ranking models fail to capture the individual peculiarities of the words and hence, either struggle to meet the accuracy requirements of many real-world applications or they are too complex to satisfy real-time constraints of applications. In this paper, we propose a new disambiguation system that learns specialized features and models for disambiguating each ambiguous phrase in the English language. To train and validate the hundreds of thousands of learning models for this purpose, we use a Wikipedia hyperlink dataset with more than 170 million labelled annotations. We provide an extensive experimental evaluation to show that the accuracy of our approach compares favourably with respect to many state-of-the-art disambiguation systems. The training required for our approach can be easily distributed over a cluster. Furthermore, updating our system for new entities or calibrating it for special ones is a computationally fast process, that does not affect the disambiguation of the other entities.
Tasks	Entity Disambiguation
Published	2016-04-20
URL	http://arxiv.org/abs/1604.05875v1
PDF	http://arxiv.org/pdf/1604.05875v1.pdf
PWC	https://paperswithcode.com/paper/distributed-entity-disambiguation-with-per
Repo
Framework

Hard Negative Mining for Metric Learning Based Zero-Shot Classification


Title	Hard Negative Mining for Metric Learning Based Zero-Shot Classification
Authors	Maxime Bucher, Stéphane Herbin, Frédéric Jurie
Abstract	Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by introducing a novel metric learning based objective function. This objective function allows to learn an optimal embedding of the attributes jointly with a measure of similarity between images and attributes. This paper extends their approach by proposing several schemes to control the generation of the negative pairs, resulting in a significant improvement of the performance and giving above state-of-the-art results on three challenging ZSC datasets.
Tasks	Domain Adaptation, Metric Learning, Zero-Shot Learning
Published	2016-08-26
URL	http://arxiv.org/abs/1608.07441v1
PDF	http://arxiv.org/pdf/1608.07441v1.pdf
PWC	https://paperswithcode.com/paper/hard-negative-mining-for-metric-learning
Repo
Framework

Evaluating the word-expert approach for Named-Entity Disambiguation


Title	Evaluating the word-expert approach for Named-Entity Disambiguation
Authors	Angel X. Chang, Valentin I. Spitkovsky, Christopher D. Manning, Eneko Agirre
Abstract	Named Entity Disambiguation (NED) is the task of linking a named-entity mention to an instance in a knowledge-base, typically Wikipedia. This task is closely related to word-sense disambiguation (WSD), where the supervised word-expert approach has prevailed. In this work we present the results of the word-expert approach to NED, where one classifier is built for each target entity mention string. The resources necessary to build the system, a dictionary and a set of training instances, have been automatically derived from Wikipedia. We provide empirical evidence of the value of this approach, as well as a study of the differences between WSD and NED, including ambiguity and synonymy statistics.
Tasks	Entity Disambiguation, Word Sense Disambiguation
Published	2016-03-15
URL	http://arxiv.org/abs/1603.04767v1
PDF	http://arxiv.org/pdf/1603.04767v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-the-word-expert-approach-for-named
Repo
Framework