Paper Group ANR 704
Iterative Bayesian Learning for Crowdsourced Regression. A Bayesian computer model analysis of Robust Bayesian analyses. A study on text-score disagreement in online reviews. Intelligent Device Discovery in the Internet of Things - Enabling the Robot Society. To Normalize, or Not to Normalize: The Impact of Normalization on Part-of-Speech Tagging. …
Iterative Bayesian Learning for Crowdsourced Regression
| Title | Iterative Bayesian Learning for Crowdsourced Regression |
| Authors | Jungseul Ok, Sewoong Oh, Yunhun Jang, Jinwoo Shin, Yung Yi |
| Abstract | Crowdsourcing platforms emerged as popular venues for purchasing human intelligence at low cost for large volume of tasks. As many low-paid workers are prone to give noisy answers, a common practice is to add redundancy by assigning multiple workers to each task and then simply average out these answers. However, to fully harness the wisdom of the crowd, one needs to learn the heterogeneous quality of each worker. We resolve this fundamental challenge in crowdsourced regression tasks, i.e., the answer takes continuous labels, where identifying good or bad workers becomes much more non-trivial compared to a classification setting of discrete labels. In particular, we introduce a Bayesian iterative scheme and show that it provably achieves the optimal mean squared error. Our evaluations on synthetic and real-world datasets support our theoretical results and show the superiority of the proposed scheme. |
| Tasks | |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1702.08840v3 |
| http://arxiv.org/pdf/1702.08840v3.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-bayesian-learning-for-crowdsourced |
| Repo | |
| Framework | |
A Bayesian computer model analysis of Robust Bayesian analyses
| Title | A Bayesian computer model analysis of Robust Bayesian analyses |
| Authors | Ian Vernon, John Paul Gosling |
| Abstract | We harness the power of Bayesian emulation techniques, designed to aid the analysis of complex computer models, to examine the structure of complex Bayesian analyses themselves. These techniques facilitate robust Bayesian analyses and/or sensitivity analyses of complex problems, and hence allow global exploration of the impacts of choices made in both the likelihood and prior specification. We show how previously intractable problems in robustness studies can be overcome using emulation techniques, and how these methods allow other scientists to quickly extract approximations to posterior results corresponding to their own particular subjective specification. The utility and flexibility of our method is demonstrated on a reanalysis of a real application where Bayesian methods were employed to capture beliefs about river flow. We discuss the obvious extensions and directions of future research that such an approach opens up. |
| Tasks | |
| Published | 2017-03-03 |
| URL | http://arxiv.org/abs/1703.01234v1 |
| http://arxiv.org/pdf/1703.01234v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-computer-model-analysis-of-robust |
| Repo | |
| Framework | |
A study on text-score disagreement in online reviews
| Title | A study on text-score disagreement in online reviews |
| Authors | Michela Fazzolari, Vittoria Cozza, Marinella Petrocchi, Angelo Spognardi |
| Abstract | In this paper, we focus on online reviews and employ artificial intelligence tools, taken from the cognitive computing field, to help understanding the relationships between the textual part of the review and the assigned numerical score. We move from the intuitions that 1) a set of textual reviews expressing different sentiments may feature the same score (and vice-versa); and 2) detecting and analyzing the mismatches between the review content and the actual score may benefit both service providers and consumers, by highlighting specific factors of satisfaction (and dissatisfaction) in texts. To prove the intuitions, we adopt sentiment analysis techniques and we concentrate on hotel reviews, to find polarity mismatches therein. In particular, we first train a text classifier with a set of annotated hotel reviews, taken from the Booking website. Then, we analyze a large dataset, with around 160k hotel reviews collected from Tripadvisor, with the aim of detecting a polarity mismatch, indicating if the textual content of the review is in line, or not, with the associated score. Using well established artificial intelligence techniques and analyzing in depth the reviews featuring a mismatch between the text polarity and the score, we find that -on a scale of five stars- those reviews ranked with middle scores include a mixture of positive and negative aspects. The approach proposed here, beside acting as a polarity detector, provides an effective selection of reviews -on an initial very large dataset- that may allow both consumers and providers to focus directly on the review subset featuring a text/score disagreement, which conveniently convey to the user a summary of positive and negative features of the review target. |
| Tasks | Sentiment Analysis |
| Published | 2017-07-21 |
| URL | http://arxiv.org/abs/1707.06932v1 |
| http://arxiv.org/pdf/1707.06932v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-study-on-text-score-disagreement-in-online |
| Repo | |
| Framework | |
Intelligent Device Discovery in the Internet of Things - Enabling the Robot Society
| Title | Intelligent Device Discovery in the Internet of Things - Enabling the Robot Society |
| Authors | James Sunthonlap, Phuoc Nguyen, Zilong Ye |
| Abstract | The Internet of Things (IoT) is continuously growing to connect billions of smart devices anywhere and anytime in an Internet-like structure, which enables a variety of applications, services and interactions between human and objects. In the future, the smart devices are supposed to be able to autonomously discover a target device with desired features and generate a set of entirely new services and applications that are not supervised or even imagined by human beings. The pervasiveness of smart devices, as well as the heterogeneity of their design and functionalities, raise a major concern: How can a smart device efficiently discover a desired target device? In this paper, we propose a Social-Aware and Distributed (SAND) scheme that achieves a fast, scalable and efficient device discovery in the IoT. The proposed SAND scheme adopts a novel device ranking criteria that measures the device’s degree, social relationship diversity, clustering coefficient and betweenness. Based on the device ranking criteria, the discovery request can be guided to travel through critical devices that stand at the major intersections of the network, and thus quickly reach the desired target device by contacting only a limited number of intermediate devices. With the help of such an intelligent device discovery as SAND, the IoT devices, as well as other computing facilities, software and data on the Internet, can autonomously establish new social connections with each other as human being do. They can formulate self-organized computing groups to perform required computing tasks, facilitate a fusion of a variety of computing service, network service and data to generate novel applications and services, evolve from the individual aritificial intelligence to the collaborative intelligence, and eventually enable the birth of a robot society. |
| Tasks | |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.08296v2 |
| http://arxiv.org/pdf/1712.08296v2.pdf | |
| PWC | https://paperswithcode.com/paper/intelligent-device-discovery-in-the-internet |
| Repo | |
| Framework | |
To Normalize, or Not to Normalize: The Impact of Normalization on Part-of-Speech Tagging
| Title | To Normalize, or Not to Normalize: The Impact of Normalization on Part-of-Speech Tagging |
| Authors | Rob van der Goot, Barbara Plank, Malvina Nissim |
| Abstract | Does normalization help Part-of-Speech (POS) tagging accuracy on noisy, non-canonical data? To the best of our knowledge, little is known on the actual impact of normalization in a real-world scenario, where gold error detection is not available. We investigate the effect of automatic normalization on POS tagging of tweets. We also compare normalization to strategies that leverage large amounts of unlabeled data kept in its raw form. Our results show that normalization helps, but does not add consistently beyond just word embedding layer initialization. The latter approach yields a tagging model that is competitive with a Twitter state-of-the-art tagger. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2017-07-17 |
| URL | http://arxiv.org/abs/1707.05116v1 |
| http://arxiv.org/pdf/1707.05116v1.pdf | |
| PWC | https://paperswithcode.com/paper/to-normalize-or-not-to-normalize-the-impact |
| Repo | |
| Framework | |
Generalized Ideals and Co-Granular Rough Sets
| Title | Generalized Ideals and Co-Granular Rough Sets |
| Authors | A Mani |
| Abstract | Lattice-theoretic ideals have been used to define and generate non granular rough approximations over general approximation spaces over the last few years by few authors. The goal of these studies, in relation based rough sets, have been to obtain nice properties comparable to those of classical rough approximations. In this research paper, these ideas are generalized in a severe way by the present author and associated semantic features are investigated by her. Granules are used in the construction of approximations in implicit ways and so a concept of co-granularity is introduced. Knowledge interpretation associable with the approaches is also investigated. This research will be of relevance for a number of logico-algebraic approaches to rough sets that proceed from point-wise definitions of approximations and also for using alternative approximations in spatial mereological contexts involving actual contact relations. The antichain based semantics invented in earlier papers by the present author also applies to the contexts considered. |
| Tasks | |
| Published | 2017-04-18 |
| URL | http://arxiv.org/abs/1704.05477v1 |
| http://arxiv.org/pdf/1704.05477v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-ideals-and-co-granular-rough-sets |
| Repo | |
| Framework | |
Convolution with Logarithmic Filter Groups for Efficient Shallow CNN
| Title | Convolution with Logarithmic Filter Groups for Efficient Shallow CNN |
| Authors | Tae Kwan Lee, Wissam J. Baddar, Seong Tae Kim, Yong Man Ro |
| Abstract | In convolutional neural networks (CNNs), the filter grouping in convolution layers is known to be useful to reduce the network parameter size. In this paper, we propose a new logarithmic filter grouping which can capture the nonlinearity of filter distribution in CNNs. The proposed logarithmic filter grouping is installed in shallow CNNs applicable in a mobile application. Experiments were performed with the shallow CNNs for classification tasks. Our classification results on Multi-PIE dataset for facial expression recognition and CIFAR-10 dataset for object classification reveal that the compact CNN with the proposed logarithmic filter grouping scheme outperforms the same network with the uniform filter grouping in terms of accuracy and parameter efficiency. Our results indicate that the efficiency of shallow CNNs can be improved by the proposed logarithmic filter grouping. |
| Tasks | Facial Expression Recognition, Object Classification |
| Published | 2017-07-31 |
| URL | http://arxiv.org/abs/1707.09855v2 |
| http://arxiv.org/pdf/1707.09855v2.pdf | |
| PWC | https://paperswithcode.com/paper/convolution-with-logarithmic-filter-groups |
| Repo | |
| Framework | |
Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems
| Title | Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems |
| Authors | Trong Nghia Hoang, Yuchen Xiao, Kavinayan Sivakumar, Christopher Amato, Jonathan How |
| Abstract | A key challenge in multi-robot and multi-agent systems is generating solutions that are robust to other self-interested or even adversarial parties who actively try to prevent the agents from achieving their goals. The practicality of existing works addressing this challenge is limited to only small-scale synchronous decision-making scenarios or a single agent planning its best response against a single adversary with fixed, procedurally characterized strategies. In contrast this paper considers a more realistic class of problems where a team of asynchronous agents with limited observation and communication capabilities need to compete against multiple strategic adversaries with changing strategies. This problem necessitates agents that can coordinate to detect changes in adversary strategies and plan the best response accordingly. Our approach first optimizes a set of stratagems that represent these best responses. These optimized stratagems are then integrated into a unified policy that can detect and respond when the adversaries change their strategies. The near-optimality of the proposed framework is established theoretically as well as demonstrated empirically in simulation and hardware. |
| Tasks | Decision Making |
| Published | 2017-10-17 |
| URL | http://arxiv.org/abs/1710.06525v1 |
| http://arxiv.org/pdf/1710.06525v1.pdf | |
| PWC | https://paperswithcode.com/paper/near-optimal-adversarial-policy-switching-for |
| Repo | |
| Framework | |
Basic tasks of sentiment analysis
| Title | Basic tasks of sentiment analysis |
| Authors | Iti Chaturvedi, Soujanya Poria, Erik Cambria |
| Abstract | Subjectivity detection is the task of identifying objective and subjective sentences. Objective sentences are those which do not exhibit any sentiment. So, it is desired for a sentiment analysis engine to find and separate the objective sentences for further analysis, e.g., polarity detection. In subjective sentences, opinions can often be expressed on one or multiple topics. Aspect extraction is a subtask of sentiment analysis that consists in identifying opinion targets in opinionated text, i.e., in detecting the specific aspects of a product or service the opinion holder is either praising or complaining about. |
| Tasks | Aspect Extraction, Sentiment Analysis |
| Published | 2017-10-18 |
| URL | http://arxiv.org/abs/1710.06536v1 |
| http://arxiv.org/pdf/1710.06536v1.pdf | |
| PWC | https://paperswithcode.com/paper/basic-tasks-of-sentiment-analysis |
| Repo | |
| Framework | |
The Internet as Quantitative Social Science Platform: Insights from a Trillion Observations
| Title | The Internet as Quantitative Social Science Platform: Insights from a Trillion Observations |
| Authors | Klaus Ackermann, Simon D Angus, Paul A Raschky |
| Abstract | With the large-scale penetration of the internet, for the first time, humanity has become linked by a single, open, communications platform. Harnessing this fact, we report insights arising from a unified internet activity and location dataset of an unparalleled scope and accuracy drawn from over a trillion (1.5$\times 10^{12}$) observations of end-user internet connections, with temporal resolution of just 15min over 2006-2012. We first apply this dataset to the expansion of the internet itself over 1,647 urban agglomerations globally. We find that unique IP per capita counts reach saturation at approximately one IP per three people, and take, on average, 16.1 years to achieve; eclipsing the estimated 100- and 60- year saturation times for steam-power and electrification respectively. Next, we use intra-diurnal internet activity features to up-scale traditional over-night sleep observations, producing the first global estimate of over-night sleep duration in 645 cities over 7 years. We find statistically significant variation between continental, national and regional sleep durations including some evidence of global sleep duration convergence. Finally, we estimate the relationship between internet concentration and economic outcomes in 411 OECD regions and find that the internet’s expansion is associated with negative or positive productivity gains, depending strongly on sectoral considerations. To our knowledge, our study is the first of its kind to use online/offline activity of the entire internet to infer social science insights, demonstrating the unparalleled potential of the internet as a social data-science platform. |
| Tasks | |
| Published | 2017-01-19 |
| URL | http://arxiv.org/abs/1701.05632v1 |
| http://arxiv.org/pdf/1701.05632v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-internet-as-quantitative-social-science |
| Repo | |
| Framework | |
Heuristic Online Goal Recognition in Continuous Domains
| Title | Heuristic Online Goal Recognition in Continuous Domains |
| Authors | Mor Vered, Gal A. Kaminka |
| Abstract | Goal recognition is the problem of inferring the goal of an agent, based on its observed actions. An inspiring approach - plan recognition by planning (PRP) - uses off-the-shelf planners to dynamically generate plans for given goals, eliminating the need for the traditional plan library. However, existing PRP formulation is inherently inefficient in online recognition, and cannot be used with motion planners for continuous spaces. In this paper, we utilize a different PRP formulation which allows for online goal recognition, and for application in continuous spaces. We present an online recognition algorithm, where two heuristic decision points may be used to improve run-time significantly over existing work. We specify heuristics for continuous domains, prove guarantees on their use, and empirically evaluate the algorithm over hundreds of experiments in both a 3D navigational environment and a cooperative robotic team task. |
| Tasks | |
| Published | 2017-09-28 |
| URL | http://arxiv.org/abs/1709.09839v1 |
| http://arxiv.org/pdf/1709.09839v1.pdf | |
| PWC | https://paperswithcode.com/paper/heuristic-online-goal-recognition-in |
| Repo | |
| Framework | |
Deep generative-contrastive networks for facial expression recognition
| Title | Deep generative-contrastive networks for facial expression recognition |
| Authors | Youngsung Kim, ByungIn Yoo, Youngjun Kwak, Changkyu Choi, Junmo Kim |
| Abstract | As the expressive depth of an emotional face differs with individuals or expressions, recognizing an expression using a single facial image at a moment is difficult. A relative expression of a query face compared to a reference face might alleviate this difficulty. In this paper, we propose to utilize contrastive representation that embeds a distinctive expressive factor for a discriminative purpose. The contrastive representation is calculated at the embedding layer of deep networks by comparing a given (query) image with the reference image. We attempt to utilize a generative reference image that is estimated based on the given image. Consequently, we deploy deep neural networks that embed a combination of a generative model, a contrastive model, and a discriminative model with an end-to-end training manner. In our proposed networks, we attempt to disentangle a facial expressive factor in two steps including learning of a generator network and a contrastive encoder network. We conducted extensive experiments on publicly available face expression databases (CK+, MMI, Oulu-CASIA, and in-the-wild databases) that have been widely adopted in the recent literatures. The proposed method outperforms the known state-of-the art methods in terms of the recognition accuracy. |
| Tasks | Facial Expression Recognition |
| Published | 2017-03-21 |
| URL | https://arxiv.org/abs/1703.07140v3 |
| https://arxiv.org/pdf/1703.07140v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-generative-contrastive-networks-for |
| Repo | |
| Framework | |
Leveraging Cognitive Features for Sentiment Analysis
| Title | Leveraging Cognitive Features for Sentiment Analysis |
| Authors | Abhijit Mishra, Diptesh Kanojia, Seema Nagar, Kuntal Dey, Pushpak Bhattacharyya |
| Abstract | Sentiments expressed in user-generated short text and sentences are nuanced by subtleties at lexical, syntactic, semantic and pragmatic levels. To address this, we propose to augment traditional features used for sentiment analysis and sarcasm detection, with cognitive features derived from the eye-movement patterns of readers. Statistical classification using our enhanced feature set improves the performance (F-score) of polarity detection by a maximum of 3.7% and 9.3% on two datasets, over the systems that use only traditional features. We perform feature significance analysis, and experiment on a held-out dataset, showing that cognitive features indeed empower sentiment analyzers to handle complex constructs. |
| Tasks | Sarcasm Detection, Sentiment Analysis |
| Published | 2017-01-19 |
| URL | http://arxiv.org/abs/1701.05581v1 |
| http://arxiv.org/pdf/1701.05581v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-cognitive-features-for-sentiment |
| Repo | |
| Framework | |
Safe Medicine Recommendation via Medical Knowledge Graph Embedding
| Title | Safe Medicine Recommendation via Medical Knowledge Graph Embedding |
| Authors | Meng Wang, Mengyue Liu, Jun Liu, Sen Wang, Guodong Long, Buyue Qian |
| Abstract | Most of the existing medicine recommendation systems that are mainly based on electronic medical records (EMRs) are significantly assisting doctors to make better clinical decisions benefiting both patients and caregivers. Even though the growth of EMRs is at a lighting fast speed in the era of big data, content limitations in EMRs restrain the existed recommendation systems to reflect relevant medical facts, such as drug-drug interactions. Many medical knowledge graphs that contain drug-related information, such as DrugBank, may give hope for the recommendation systems. However, the direct use of these knowledge graphs in the systems suffers from robustness caused by the incompleteness of the graphs. To address these challenges, we stand on recent advances in graph embedding learning techniques and propose a novel framework, called Safe Medicine Recommendation (SMR), in this paper. Specifically, SMR first constructs a high-quality heterogeneous graph by bridging EMRs (MIMIC-III) and medical knowledge graphs (ICD-9 ontology and DrugBank). Then, SMR jointly embeds diseases, medicines, patients, and their corresponding relations into a shared lower dimensional space. Finally, SMR uses the embeddings to decompose the medicine recommendation into a link prediction process while considering the patient’s diagnoses and adverse drug reactions. To our best knowledge, SMR is the first to learn embeddings of a patient-disease-medicine graph for medicine recommendation in the world. Extensive experiments on real datasets are conducted to evaluate the effectiveness of proposed framework. |
| Tasks | Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs, Link Prediction, Recommendation Systems |
| Published | 2017-10-16 |
| URL | http://arxiv.org/abs/1710.05980v2 |
| http://arxiv.org/pdf/1710.05980v2.pdf | |
| PWC | https://paperswithcode.com/paper/safe-medicine-recommendation-via-medical |
| Repo | |
| Framework | |
Spatio-Temporal Facial Expression Recognition Using Convolutional Neural Networks and Conditional Random Fields
| Title | Spatio-Temporal Facial Expression Recognition Using Convolutional Neural Networks and Conditional Random Fields |
| Authors | Behzad Hasani, Mohammad H. Mahoor |
| Abstract | Automated Facial Expression Recognition (FER) has been a challenging task for decades. Many of the existing works use hand-crafted features such as LBP, HOG, LPQ, and Histogram of Optical Flow (HOF) combined with classifiers such as Support Vector Machines for expression recognition. These methods often require rigorous hyperparameter tuning to achieve good results. Recently Deep Neural Networks (DNN) have shown to outperform traditional methods in visual object recognition. In this paper, we propose a two-part network consisting of a DNN-based architecture followed by a Conditional Random Field (CRF) module for facial expression recognition in videos. The first part captures the spatial relation within facial images using convolutional layers followed by three Inception-ResNet modules and two fully-connected layers. To capture the temporal relation between the image frames, we use linear chain CRF in the second part of our network. We evaluate our proposed network on three publicly available databases, viz. CK+, MMI, and FERA. Experiments are performed in subject-independent and cross-database manners. Our experimental results show that cascading the deep network architecture with the CRF module considerably increases the recognition of facial expressions in videos and in particular it outperforms the state-of-the-art methods in the cross-database experiments and yields comparable results in the subject-independent experiments. |
| Tasks | Facial Expression Recognition, Object Recognition, Optical Flow Estimation |
| Published | 2017-03-20 |
| URL | http://arxiv.org/abs/1703.06995v2 |
| http://arxiv.org/pdf/1703.06995v2.pdf | |
| PWC | https://paperswithcode.com/paper/spatio-temporal-facial-expression-recognition |
| Repo | |
| Framework | |
