Paper Group ANR 1241
Grounded Agreement Games: Emphasizing Conversational Grounding in Visual Dialogue Settings. Real-world Conversational AI for Hotel Bookings. Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation. A Complete Classification of the Complexity and Rewritability of Ontology-Mediated Queries based on the Descrip …
Grounded Agreement Games: Emphasizing Conversational Grounding in Visual Dialogue Settings
| Title | Grounded Agreement Games: Emphasizing Conversational Grounding in Visual Dialogue Settings |
| Authors | David Schlangen |
| Abstract | Where early work on dialogue in Computational Linguistics put much emphasis on dialogue structure and its relation to the mental states of the dialogue participants (e.g., Allen 1979, Grosz & Sidner 1986), current work mostly reduces dialogue to the task of producing at any one time a next utterance; e.g. in neural chatbot or Visual Dialogue settings. As a methodological decision, this is sound: Even the longest journey is a sequence of steps. It becomes detrimental, however, when the tasks and datasets from which dialogue behaviour is to be learned are tailored too much to this framing of the problem. In this short note, we describe a family of settings which still allow to keep dialogues simple, but add a constraint that makes participants care about reaching mutual understanding. In such agreement games, there is a secondary, but explicit goal besides the task level goal, and that is to reach mutual understanding about whether the task level goal has been reached. As we argue, this naturally triggers meta-semantic interaction and mutual engagement, and hence leads to richer data from which to induce models. |
| Tasks | Chatbot, Visual Dialog |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11279v1 |
| https://arxiv.org/pdf/1908.11279v1.pdf | |
| PWC | https://paperswithcode.com/paper/grounded-agreement-games-emphasizing |
| Repo | |
| Framework | |
Real-world Conversational AI for Hotel Bookings
| Title | Real-world Conversational AI for Hotel Bookings |
| Authors | Bai Li, Nanyi Jiang, Joey Sham, Henry Shi, Hussein Fazal |
| Abstract | In this paper, we present a real-world conversational AI system to search for and book hotels through text messaging. Our architecture consists of a frame-based dialogue management system, which calls machine learning models for intent classification, named entity recognition, and information retrieval subtasks. Our chatbot has been deployed on a commercial scale, handling tens of thousands of hotel searches every day. We describe the various opportunities and challenges of developing a chatbot in the travel industry. |
| Tasks | Chatbot, Dialogue Management, Information Retrieval, Intent Classification, Named Entity Recognition |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10001v1 |
| https://arxiv.org/pdf/1908.10001v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-world-conversational-ai-for-hotel |
| Repo | |
| Framework | |
Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
| Title | Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation |
| Authors | Jiawei Wu, Xin Wang, William Yang Wang |
| Abstract | The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural machine translation, where pseudo sentence pairs are generated to train the models with a reconstruction loss. However, the pseudo sentences are usually of low quality as translation errors accumulate during training. To avoid this fundamental issue, we propose an alternative but more effective approach, extract-edit, to extract and then edit real sentences from the target monolingual corpora. Furthermore, we introduce a comparative translation loss to evaluate the translated target sentences and thus train the unsupervised translation systems. Experiments show that the proposed approach consistently outperforms the previous state-of-the-art unsupervised machine translation systems across two benchmarks (English-French and English-German) and two low-resource language pairs (English-Romanian and English-Russian) by more than 2 (up to 3.63) BLEU points. |
| Tasks | Machine Translation, Unsupervised Machine Translation |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02331v1 |
| http://arxiv.org/pdf/1904.02331v1.pdf | |
| PWC | https://paperswithcode.com/paper/extract-and-edit-an-alternative-to-back |
| Repo | |
| Framework | |
A Complete Classification of the Complexity and Rewritability of Ontology-Mediated Queries based on the Description Logic EL
| Title | A Complete Classification of the Complexity and Rewritability of Ontology-Mediated Queries based on the Description Logic EL |
| Authors | Carsten Lutz, Leif Sabellek |
| Abstract | We provide an ultimately fine-grained analysis of the data complexity and rewritability of ontology-mediated queries (OMQs) based on an EL ontology and a conjunctive query (CQ). Our main results are that every such OMQ is in AC0, NL-complete, or PTime-complete and that containment in NL coincides with rewritability into linear Datalog (whereas containment in AC0 coincides with rewritability into first-order logic). We establish natural characterizations of the three cases in terms of bounded depth and (un)bounded pathwidth, and show that every of the associated meta problems such as deciding wether a given OMQ is rewritable into linear Datalog is ExpTime-complete. We also give a way to construct linear Datalog rewritings when they exist and prove that there is no constant Datalog rewritings. |
| Tasks | |
| Published | 2019-04-29 |
| URL | http://arxiv.org/abs/1904.12533v1 |
| http://arxiv.org/pdf/1904.12533v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-complete-classification-of-the-complexity |
| Repo | |
| Framework | |
Improvement of Multiparametric MR Image Segmentation by Augmenting the Data with Generative Adversarial Networks for Glioma Patients
| Title | Improvement of Multiparametric MR Image Segmentation by Augmenting the Data with Generative Adversarial Networks for Glioma Patients |
| Authors | Eric Carver, Zhenzhen Dai, Evan Liang, James Snyder, Ning Wen |
| Abstract | Every year thousands of patients are diagnosed with a glioma, a type of malignant brain tumor. Physicians use MR images as a key tool in the diagnosis and treatment of these patients. Neural networks show great potential to aid physicians in the medical image analysis. This study investigates the use of varying amounts of synthetic brain T1-weighted (T1), post-contrast T1-weighted (T1Gd), T2-weighted (T2), and T2 Fluid Attenuated Inversion Recovery (FLAIR) MR images created by a generative adversarial network to overcome the lack of annotated medical image data in training separate 2D U-Nets to segment enhancing tumor, peritumoral edema, and necrosis (non-enhancing tumor core) regions on gliomas. These synthetic MR images were assessed quantitively (SSIM=0.79) and qualitatively by a physician who found that the synthetic images seem stronger for delineation of structural boundaries but struggle more when gradient is significant, (e.g. edema signal in T2 modalities). Multiple 2D U-Nets were trained with original BraTS data and differing subsets of a quarter, half, three-quarters, and all synthetic MR images. There was not an obvious correlation between the improvement of values of the metrics in separate validation dataset for each structure and amount of synthetic data added, there is a strong correlation between the amount of synthetic data added and the number of best overall validation metrics. In summary, this study showed ability to generate high quality synthetic Flair, T2, T1, and T1CE MR images using the GAN. Using the synthetic MR images showed encouraging results to improve the U-Net segmentation performance which has the potential to address the scarcity of readily available medical images. |
| Tasks | Semantic Segmentation |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00696v1 |
| https://arxiv.org/pdf/1910.00696v1.pdf | |
| PWC | https://paperswithcode.com/paper/improvement-of-multiparametric-mr-image |
| Repo | |
| Framework | |
Embedded Deep Learning for Sleep Staging
| Title | Embedded Deep Learning for Sleep Staging |
| Authors | Engin Türetken, Jérôme Van Zaen, Ricard Delgado-Gonzalo |
| Abstract | The rapidly-advancing technology of deep learning (DL) into the world of the Internet of Things (IoT) has not fully entered in the fields of m-Health yet. Among the main reasons are the high computational demands of DL algorithms and the inherent resource-limitation of wearable devices. In this paper, we present initial results for two deep learning architectures used to diagnose and analyze sleep patterns, and we compare them with a previously presented hand-crafted algorithm. The algorithms are designed to be reliable for consumer healthcare applications and to be integrated into low-power wearables with limited computational resources. |
| Tasks | |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.09905v1 |
| https://arxiv.org/pdf/1906.09905v1.pdf | |
| PWC | https://paperswithcode.com/paper/embedded-deep-learning-for-sleep-staging |
| Repo | |
| Framework | |
Using the Open Meta Kaggle Dataset to Evaluate Tripartite Recommendations in Data Markets
| Title | Using the Open Meta Kaggle Dataset to Evaluate Tripartite Recommendations in Data Markets |
| Authors | Dominik Kowald, Matthias Traub, Dieter Theiler, Heimo Gursch, Emanuel Lacic, Stefanie Lindstaedt, Roman Kern, Elisabeth Lex |
| Abstract | This work addresses the problem of providing and evaluating recommendations in data markets. Since most of the research in recommender systems is focused on the bipartite relationship between users and items (e.g., movies), we extend this view to the tripartite relationship between users, datasets and services, which is present in data markets. Between these entities, we identify four use cases for recommendations: (i) recommendation of datasets for users, (ii) recommendation of services for users, (iii) recommendation of services for datasets, and (iv) recommendation of datasets for services. Using the open Meta Kaggle dataset, we evaluate the recommendation accuracy of a popularity-based as well as a collaborative filtering-based algorithm for these four use cases and find that the recommendation accuracy strongly depends on the given use case. The presented work contributes to the tripartite recommendation problem in general and to the under-researched portfolio of evaluating recommender systems for data markets in particular. |
| Tasks | Recommendation Systems |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04017v2 |
| https://arxiv.org/pdf/1908.04017v2.pdf | |
| PWC | https://paperswithcode.com/paper/using-the-open-meta-kaggle-dataset-to |
| Repo | |
| Framework | |
SkeletonNet: Shape Pixel to Skeleton Pixel
| Title | SkeletonNet: Shape Pixel to Skeleton Pixel |
| Authors | Sabari Nathan, Priya Kansal |
| Abstract | Deep Learning for Geometric Shape Understating has organized a challenge for extracting different kinds of skeletons from the images of different objects. This competition is organized in association with CVPR 2019. There are three different tracks of this competition. The present manuscript describes the method used to train the model for the dataset provided in the first track. The first track aims to extract skeleton pixels from the shape pixels of 89 different objects. For the purpose of extracting the skeleton, a U-net model which is comprised of an encoder-decoder structure has been used. In our proposed architecture, unlike the plain decoder in the traditional Unet, we have designed the decoder in the format of HED architecture, wherein we have introduced 4 side layers and fused them to one dilation convolutional layer to connect the broken links of the skeleton. Our proposed architecture achieved the F1 score of 0.77 on test data. |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01683v1 |
| https://arxiv.org/pdf/1907.01683v1.pdf | |
| PWC | https://paperswithcode.com/paper/skeletonnet-shape-pixel-to-skeleton-pixel |
| Repo | |
| Framework | |
Machine Learning and the future of Supernova Cosmology
| Title | Machine Learning and the future of Supernova Cosmology |
| Authors | Emille E. O. Ishida |
| Abstract | Machine Learning methods will play a fundamental role in our ability to optimize the science output from the next generation of large scale surveys. Given the peculiarities of astronomical data, it is crucial that algorithms are adapted to the data situation at hand. In this comment, I review the recent efforts towards the development of automatic systems to identify and classify supernova with the goal of enabling their use as cosmological standard candles. |
| Tasks | |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.02315v1 |
| https://arxiv.org/pdf/1908.02315v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-and-the-future-of-supernova |
| Repo | |
| Framework | |
Tracking Temporal Evolution of Network Activity for Botnet Detection
| Title | Tracking Temporal Evolution of Network Activity for Botnet Detection |
| Authors | Kapil Sinha, Arun Viswanathan, Julian Bunn |
| Abstract | Botnets are becoming increasingly prevalent as the primary enabling technology in a variety of malicious campaigns such as email spam, click fraud, distributed denial-of-service (DDoS) attacks, and cryptocurrency mining. Botnet technology has continued to evolve rapidly making detection a very challenging problem. There is a fundamental need for robust detection methods that are insensitive to characteristics of a specific botnet and are generalizable across different botnet types. We propose a novel supervised approach to detect malicious botnet hosts by tracking a host’s network activity over time using a Long Short-Term Memory (LSTM) based neural network architecture. We build a prototype to demonstrate the feasibility of our approach, evaluate it on the CTU-13 dataset, and compare our performance against existing detection methods. We show that our approach results in a more generalizable, botnet-agnostic detection methodology, is amenable to real-time implementation, and performs well compared to existing approaches, with an overall accuracy score of 96.2%. |
| Tasks | |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03443v1 |
| https://arxiv.org/pdf/1908.03443v1.pdf | |
| PWC | https://paperswithcode.com/paper/tracking-temporal-evolution-of-network |
| Repo | |
| Framework | |
RTbust: Exploiting Temporal Patterns for Botnet Detection on Twitter
| Title | RTbust: Exploiting Temporal Patterns for Botnet Detection on Twitter |
| Authors | Michele Mazza, Stefano Cresci, Marco Avvenuti, Walter Quattrociocchi, Maurizio Tesconi |
| Abstract | Within OSNs, many of our supposedly online friends may instead be fake accounts called social bots, part of large groups that purposely re-share targeted content. Here, we study retweeting behaviors on Twitter, with the ultimate goal of detecting retweeting social bots. We collect a dataset of 10M retweets. We design a novel visualization that we leverage to highlight benign and malicious patterns of retweeting activity. In this way, we uncover a ‘normal’ retweeting pattern that is peculiar of human-operated accounts, and 3 suspicious patterns related to bot activities. Then, we propose a bot detection technique that stems from the previous exploration of retweeting behaviors. Our technique, called Retweet-Buster (RTbust), leverages unsupervised feature extraction and clustering. An LSTM autoencoder converts the retweet time series into compact and informative latent feature vectors, which are then clustered with a hierarchical density-based algorithm. Accounts belonging to large clusters characterized by malicious retweeting patterns are labeled as bots. RTbust obtains excellent detection results, with F1 = 0.87, whereas competitors achieve F1 < 0.76. Finally, we apply RTbust to a large dataset of retweets, uncovering 2 previously unknown active botnets with hundreds of accounts. |
| Tasks | Time Series |
| Published | 2019-02-12 |
| URL | http://arxiv.org/abs/1902.04506v1 |
| http://arxiv.org/pdf/1902.04506v1.pdf | |
| PWC | https://paperswithcode.com/paper/rtbust-exploiting-temporal-patterns-for |
| Repo | |
| Framework | |
ASNM Datasets: A Collection of Network Traffic Features for Testing of Adversarial Classifiers and Network Intrusion Detectors
| Title | ASNM Datasets: A Collection of Network Traffic Features for Testing of Adversarial Classifiers and Network Intrusion Detectors |
| Authors | Ivan Homoliak, Petr Hanacek |
| Abstract | In this paper, we present three datasets that have been built from network traffic traces using ASNM features, designed in our previous work. The first dataset was built using a state-of-the-art dataset called CDX 2009, while the remaining two datasets were collected by us in 2015 and 2018, respectively. These two datasets contain several adversarial obfuscation techniques that were applied onto malicious as well as legitimate traffic samples during the execution of particular TCP network connections. Adversarial obfuscation techniques were used for evading machine learning-based network intrusion detection classifiers. Further, we showed that the performance of such classifiers can be improved when partially augmenting their training data by samples obtained from obfuscation techniques. In detail, we utilized tunneling obfuscation in HTTP(S) protocol and non-payload-based obfuscations modifying various properties of network traffic by, e.g., TCP segmentation, re-transmissions, corrupting and reordering of packets, etc. To the best of our knowledge, this is the first collection of network traffic metadata that contains adversarial techniques and is intended for non-payload-based network intrusion detection and adversarial classification. Provided datasets enable testing of the evasion resistance of arbitrary classifier that is using ASNM features. |
| Tasks | Intrusion Detection, Network Intrusion Detection |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.10528v1 |
| https://arxiv.org/pdf/1910.10528v1.pdf | |
| PWC | https://paperswithcode.com/paper/asnm-datasets-a-collection-of-network-traffic |
| Repo | |
| Framework | |
Continual Learning in Deep Neural Network by Using a Kalman Optimiser
| Title | Continual Learning in Deep Neural Network by Using a Kalman Optimiser |
| Authors | Honglin Li, Shirin Enshaeifar, Frieder Ganz, Payam Barnaghi |
| Abstract | Learning and adapting to new distributions or learning new tasks sequentially without forgetting the previously learned knowledge is a challenging phenomenon in continual learning models. Most of the conventional deep learning models are not capable of learning new tasks sequentially in one model without forgetting the previously learned ones. We address this issue by using a Kalman Optimiser. The Kalman Optimiser divides the neural network into two parts: the long-term and short-term memory units. The long-term memory unit is used to remember the learned tasks and the short-term memory unit is to adapt to the new task. We have evaluated our method on MNIST, CIFAR10, CIFAR100 datasets and compare our results with state-of-the-art baseline models. The results show that our approach enables the model to continually learn and adapt to the new changes without forgetting the previously learned tasks. |
| Tasks | Continual Learning |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08119v3 |
| https://arxiv.org/pdf/1905.08119v3.pdf | |
| PWC | https://paperswithcode.com/paper/continual-learning-in-deep-neural-networks-by |
| Repo | |
| Framework | |
Draining the Water Hole: Mitigating Social Engineering Attacks with CyberTWEAK
| Title | Draining the Water Hole: Mitigating Social Engineering Attacks with CyberTWEAK |
| Authors | Zheyuan Ryan Shi, Aaron Schlenker, Brian Hay, Daniel Bittleston, Siyu Gao, Emily Peterson, John Trezza, Fei Fang |
| Abstract | Cyber adversaries have increasingly leveraged social engineering attacks to breach large organizations and threaten the well-being of today’s online users. One clever technique, the “watering hole” attack, compromises a legitimate website to execute drive-by download attacks by redirecting users to another malicious domain. We introduce a game-theoretic model that captures the salient aspects for an organization protecting itself from a watering hole attack by altering the environment information in web traffic so as to deceive the attackers. Our main contributions are (1) a novel Social Engineering Deception (SED) game model that features a continuous action set for the attacker, (2) an in-depth analysis of the SED model to identify computationally feasible real-world cases, and (3) the CyberTWEAK algorithm which solves for the optimal protection policy. To illustrate the potential use of our framework, we built a browser extension based on our algorithms which is now publicly available online. The CyberTWEAK extension will be vital to the continued development and deployment of countermeasures for social engineering. |
| Tasks | |
| Published | 2019-01-03 |
| URL | https://arxiv.org/abs/1901.00586v3 |
| https://arxiv.org/pdf/1901.00586v3.pdf | |
| PWC | https://paperswithcode.com/paper/towards-thwarting-social-engineering-attacks |
| Repo | |
| Framework | |
On training deep networks for satellite image super-resolution
| Title | On training deep networks for satellite image super-resolution |
| Authors | Michal Kawulok, Szymon Piechaczek, Krzysztof Hrynczenko, Pawel Benecki, Daniel Kostrzewa, Jakub Nalepa |
| Abstract | The capabilities of super-resolution reconstruction (SRR)—techniques for enhancing image spatial resolution—have been recently improved significantly by the use of deep convolutional neural networks. Commonly, such networks are learned using huge training sets composed of original images alongside their low-resolution counterparts, obtained with bicubic downsampling. In this paper, we investigate how the SRR performance is influenced by the way such low-resolution training data are obtained, which has not been explored up to date. Our extensive experimental study indicates that the training data characteristics have a large impact on the reconstruction accuracy, and the widely-adopted approach is not the most effective for dealing with satellite images. Overall, we argue that developing better training data preparation routines may be pivotal in making SRR suitable for real-world applications. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-06-16 |
| URL | https://arxiv.org/abs/1906.06697v1 |
| https://arxiv.org/pdf/1906.06697v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-training-deep-networks-for-satellite-image |
| Repo | |
| Framework | |
