Paper Group ANR 1722
Landmark Ordinal Embedding. Tifinagh-IRCAM Handwritten character recognition using Deep learning. Query Inseparability for ALC Ontologies. Deep Reinforcement Learning for Synthesizing Functions in Higher-Order Logic. Collaborative Filtering via High-Dimensional Regression. An extended description logic system with knowledge element based on ALC. Th …
Landmark Ordinal Embedding
| Title | Landmark Ordinal Embedding |
| Authors | Nikhil Ghosh, Yuxin Chen, Yisong Yue |
| Abstract | In this paper, we aim to learn a low-dimensional Euclidean representation from a set of constraints of the form “item j is closer to item i than item k”. Existing approaches for this “ordinal embedding” problem require expensive optimization procedures, which cannot scale to handle increasingly larger datasets. To address this issue, we propose a landmark-based strategy, which we call Landmark Ordinal Embedding (LOE). Our approach trades off statistical efficiency for computational efficiency by exploiting the low-dimensionality of the latent embedding. We derive bounds establishing the statistical consistency of LOE under the popular Bradley-Terry-Luce noise model. Through a rigorous analysis of the computational complexity, we show that LOE is significantly more efficient than conventional ordinal embedding approaches as the number of items grows. We validate these characterizations empirically on both synthetic and real datasets. We also present a practical approach that achieves the “best of both worlds”, by using LOE to warm-start existing methods that are more statistically efficient but computationally expensive. |
| Tasks | |
| Published | 2019-10-27 |
| URL | https://arxiv.org/abs/1910.12379v1 |
| https://arxiv.org/pdf/1910.12379v1.pdf | |
| PWC | https://paperswithcode.com/paper/landmark-ordinal-embedding |
| Repo | |
| Framework | |
Tifinagh-IRCAM Handwritten character recognition using Deep learning
| Title | Tifinagh-IRCAM Handwritten character recognition using Deep learning |
| Authors | El Wardani Dadi |
| Abstract | In this paper, we exploit the benefits of the deep learning approach to design an efficient system of Amazigh handwritten recognition. Indeed, this approach has proved a greater efficiency in the various domains, especially recognition tasks. However, to take full advantage of this approach it’s necessary to construct an adequate dataset of training and testing that represent faithfully the concerned problem. To this end, we have prepared our dataset of 102 writers each one contains 33 characters of IRCAM-Tifinagh. Inspired by the MNIST database, the set of characters is size-normalized and centered in a fixed-size image. The resulting is a grey level image of size 28x28, where the black color is the non-color of the character. The number of images produced after this preprocessing step is 3,366. |
| Tasks | |
| Published | 2019-12-21 |
| URL | https://arxiv.org/abs/1912.10338v1 |
| https://arxiv.org/pdf/1912.10338v1.pdf | |
| PWC | https://paperswithcode.com/paper/tifinagh-ircam-handwritten-character |
| Repo | |
| Framework | |
Query Inseparability for ALC Ontologies
| Title | Query Inseparability for ALC Ontologies |
| Authors | Elena Botoeva, Carsten Lutz, Vladislav Ryzhikov, Frank Wolter, Michael Zakharyaschev |
| Abstract | We investigate the problem whether two ALC ontologies are indistinguishable (or inseparable) by means of queries in a given signature, which is fundamental for ontology engineering tasks such as ontology versioning, modularisation, update, and forgetting. We consider both knowledge base (KB) and TBox inseparability. For KBs, we give model-theoretic criteria in terms of (finite partial) homomorphisms and products and prove that this problem is undecidable for conjunctive queries (CQs), but 2ExpTime-complete for unions of CQs (UCQs). The same results hold if (U)CQs are replaced by rooted (U)CQs, where every variable is connected to an answer variable. We also show that inseparability by CQs is still undecidable if one KB is given in the lightweight DL EL and if no restrictions are imposed on the signature of the CQs. We also consider the problem whether two ALC TBoxes give the same answers to any query over any ABox in a given signature and show that, for CQs, this problem is undecidable, too. We then develop model-theoretic criteria for Horn-ALC TBoxes and show using tree automata that, in contrast, inseparability becomes decidable and 2ExpTime-complete, even ExpTime-complete when restricted to (unions of) rooted CQs. |
| Tasks | |
| Published | 2019-01-31 |
| URL | http://arxiv.org/abs/1902.00014v1 |
| http://arxiv.org/pdf/1902.00014v1.pdf | |
| PWC | https://paperswithcode.com/paper/query-inseparability-for-alc-ontologies |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Synthesizing Functions in Higher-Order Logic
| Title | Deep Reinforcement Learning for Synthesizing Functions in Higher-Order Logic |
| Authors | Thibault Gauthier |
| Abstract | The paper describes a deep reinforcement learning framework based on self-supervised learning within the proof assistant HOL4. A close interaction between the machine learning modules and the HOL4 library is achieved by the choice of tree neural networks (TNNs) as machine learning models and the internal use of HOL4 terms to represent tree structures of TNNs. Recursive improvement is possible when a task is expressed as a search problem. In this case, a Monte Carlo Tree Search (MCTS) algorithm guided by a TNN can be used to explore the search space and produce better examples for training the next TNN. As an illustration, term synthesis tasks on combinators and Diophantine equations are specified and learned. We achieve a success rate of 65% on combinator synthesis problems outperforming state-of-the-art ATPs run with their best general set of strategies. We set a precedent for statistically guided synthesis of Diophantine equations by solving 78.5% of the generated test problems. |
| Tasks | Automated Theorem Proving |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11797v2 |
| https://arxiv.org/pdf/1910.11797v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-in-hol4 |
| Repo | |
| Framework | |
Collaborative Filtering via High-Dimensional Regression
| Title | Collaborative Filtering via High-Dimensional Regression |
| Authors | Harald Steck |
| Abstract | While the SLIM approach obtained high ranking-accuracy in many experiments in the literature, it is also known for its high computational cost of learning its parameters from data. For this reason, we focus in this paper on variants of high-dimensional regression problems that have closed-form solutions. Moreover, we motivate a re-scaling rather than a re-weighting approach for dealing with biases regarding item-popularities in the data. We also discuss properties of the sparse solution, and outline a computationally efficient approximation. In experiments on three publicly available data sets, we observed not only extremely reduced training times, but also significantly improved ranking accuracy compared to SLIM. Surprisingly, various state-of-the-art models, including deep non-linear autoencoders, were also outperformed on two of the three data sets in our experiments, in particular for recommendations with highly personalized relevance. |
| Tasks | |
| Published | 2019-04-30 |
| URL | http://arxiv.org/abs/1904.13033v1 |
| http://arxiv.org/pdf/1904.13033v1.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-filtering-via-high-dimensional |
| Repo | |
| Framework | |
An extended description logic system with knowledge element based on ALC
| Title | An extended description logic system with knowledge element based on ALC |
| Authors | Bin Wen, Jianhou Gan, Juan L. G. Guirao, Wei Gao |
| Abstract | With the rise of knowledge management and knowledge economy, the knowledge elements that directly link and embody the knowledge system have become the research focus and hotspot in certain areas. The existing knowledge element representation methods are limited in functions to deal with the formality, logic and reasoning. Based on description logic ALC and the common knowledge element model, in order to describe the knowledge element, the description logic ALC is expanded. The concept is extended to two diferent ones (that is, the object knowledge element concept and the attribute knowledge element concept). The relationship is extended to three (that is, relationship between object knowledge element concept and attribute knowledge element concept, relationship among object knowledge element concepts, relationship among attribute knowledge element concepts), and the inverse relationship constructor is added to propose a description logic KEDL system. By demonstrating, the relevant properties, such as completeness, reliability,of the described logic system KEDL are obtained. Finally, it is verified by the example that the description logic KEDL system has strong knowledge element description ability. |
| Tasks | |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.07469v1 |
| http://arxiv.org/pdf/1904.07469v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-extended-description-logic-system-with |
| Repo | |
| Framework | |
The evolution of argumentation mining: From models to social media and emerging tools
| Title | The evolution of argumentation mining: From models to social media and emerging tools |
| Authors | Anastasios Lytos, Thomas Lagkas, Panagiotis Sarigiannidis, Kalina Bontcheva |
| Abstract | Argumentation mining is a rising subject in the computational linguistics domain focusing on extracting structured arguments from natural text, often from unstructured or noisy text. The initial approaches on modeling arguments was aiming to identify a flawless argument on specific fields (Law, Scientific Papers) serving specific needs (completeness, effectiveness). With the emerge of Web 2.0 and the explosion in the use of social media both the diffusion of the data and the argument structure have changed. In this survey article, we bridge the gap between theoretical approaches of argumentation mining and pragmatic schemes that satisfy the needs of social media generated data, recognizing the need for adapting more flexible and expandable schemes, capable to adjust to the argumentation conditions that exist in social media. We review, compare, and classify existing approaches, techniques and tools, identifying the positive outcome of combining tasks and features, and eventually propose a conceptual architecture framework. The proposed theoretical framework is an argumentation mining scheme able to identify the distinct sub-tasks and capture the needs of social media text, revealing the need for adopting more flexible and extensible frameworks. |
| Tasks | |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02258v1 |
| https://arxiv.org/pdf/1907.02258v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-evolution-of-argumentation-mining-from |
| Repo | |
| Framework | |
Deep Learning-Based Feature-Aware Data Modeling for Complex Physics Simulations
| Title | Deep Learning-Based Feature-Aware Data Modeling for Complex Physics Simulations |
| Authors | Qun Liu, Subhashis Hazarika, John M. Patchett, James Paul Ahrens, Ayan Biswas |
| Abstract | Data modeling and reduction for in situ is important. Feature-driven methods for in situ data analysis and reduction are a priority for future exascale machines as there are currently very few such methods. We investigate a deep-learning based workflow that targets in situ data processing using autoencoders. We propose a Residual Autoencoder integrated Residual in Residual Dense Block (RRDB) to obtain better performance. Our proposed framework compressed our test data into 66 KB from 2.1 MB per 3D volume timestep. |
| Tasks | |
| Published | 2019-12-08 |
| URL | https://arxiv.org/abs/1912.03587v1 |
| https://arxiv.org/pdf/1912.03587v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-feature-aware-data |
| Repo | |
| Framework | |
Recursive Sketches for Modular Deep Learning
| Title | Recursive Sketches for Modular Deep Learning |
| Authors | Badih Ghazi, Rina Panigrahy, Joshua R. Wang |
| Abstract | We present a mechanism to compute a sketch (succinct summary) of how a complex modular deep network processes its inputs. The sketch summarizes essential information about the inputs and outputs of the network and can be used to quickly identify key components and summary statistics of the inputs. Furthermore, the sketch is recursive and can be unrolled to identify sub-components of these components and so forth, capturing a potentially complicated DAG structure. These sketches erase gracefully; even if we erase a fraction of the sketch at random, the remainder still retains the high-weight' information present in the original sketch. The sketches can also be organized in a repository to implicitly form a knowledge graph’; it is possible to quickly retrieve sketches in the repository that are related to a sketch of interest; arranged in this fashion, the sketches can also be used to learn emerging concepts by looking for new clusters in sketch space. Finally, in the scenario where we want to learn a ground truth deep network, we show that augmenting input/output pairs with these sketches can theoretically make it easier to do so. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12730v2 |
| https://arxiv.org/pdf/1905.12730v2.pdf | |
| PWC | https://paperswithcode.com/paper/recursive-sketches-for-modular-deep-learning |
| Repo | |
| Framework | |
A Deterministic plus Stochastic Model of the Residual Signal for Improved Parametric Speech Synthesis
| Title | A Deterministic plus Stochastic Model of the Residual Signal for Improved Parametric Speech Synthesis |
| Authors | Thomas Drugman, Geoffrey Wilfart, Thierry Dutoit |
| Abstract | Speech generated by parametric synthesizers generally suffers from a typical buzziness, similar to what was encountered in old LPC-like vocoders. In order to alleviate this problem, a more suited modeling of the excitation should be adopted. For this, we hereby propose an adaptation of the Deterministic plus Stochastic Model (DSM) for the residual. In this model, the excitation is divided into two distinct spectral bands delimited by the maximum voiced frequency. The deterministic part concerns the low-frequency contents and consists of a decomposition of pitch-synchronous residual frames on an orthonormal basis obtained by Principal Component Analysis. The stochastic component is a high-pass filtered noise whose time structure is modulated by an energy-envelope, similarly to what is done in the Harmonic plus Noise Model (HNM). The proposed residual model is integrated within a HMM-based speech synthesizer and is compared to the traditional excitation through a subjective test. Results show a significative improvement for both male and female voices. In addition the proposed model requires few computational load and memory, which is essential for its integration in commercial applications. |
| Tasks | Speech Synthesis |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/2001.00842v1 |
| https://arxiv.org/pdf/2001.00842v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deterministic-plus-stochastic-model-of-the |
| Repo | |
| Framework | |
Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models
| Title | Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models |
| Authors | César Roberto de Souza, Adrien Gaidon, Yohann Cabon, Naila Murray, Antonio Manuel López |
| Abstract | Deep video action recognition models have been highly successful in recent years but require large quantities of manually annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic training data for video action recognition, as synthetic data have been successfully used to supervise models for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation, physics models and other components of modern game engines. With this model we generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. PHAV contains a total of 39,982 videos, with more than 1,000 examples for each of 35 action categories. Our video generation approach is not limited to existing motion capture sequences: 14 of these 35 categories are procedurally defined synthetic actions. In addition, each video is represented with 6 different data modalities, including RGB, optical flow and pixel-level semantic labels. These modalities are generated almost simultaneously using the Multiple Render Targets feature of modern GPUs. In order to leverage PHAV, we introduce a deep multi-task (i.e. that considers action classes from multiple datasets) representation learning architecture that is able to simultaneously learn from synthetic and real video datasets, even when their action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance. Our approach also significantly outperforms video representations produced by fine-tuning state-of-the-art unsupervised generative models of videos. |
| Tasks | Motion Capture, Optical Flow Estimation, Representation Learning, Temporal Action Localization, Video Generation |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.06699v1 |
| https://arxiv.org/pdf/1910.06699v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-human-action-videos-by-coupling-3d |
| Repo | |
| Framework | |
Women, politics and Twitter: Using machine learning to change the discourse
| Title | Women, politics and Twitter: Using machine learning to change the discourse |
| Authors | Lana Cuthbertson, Alex Kearney, Riley Dawson, Ashia Zawaduk, Eve Cuthbertson, Ann Gordon-Tighe, Kory W Mathewson |
| Abstract | Including diverse voices in political decision-making strengthens our democratic institutions. Within the Canadian political system, there is gender inequality across all levels of elected government. Online abuse, such as hateful tweets, leveled at women engaged in politics contributes to this inequity, particularly tweets focusing on their gender. In this paper, we present ParityBOT: a Twitter bot which counters abusive tweets aimed at women in politics by sending supportive tweets about influential female leaders and facts about women in public life. ParityBOT is the first artificial intelligence-based intervention aimed at affecting online discourse for women in politics for the better. The goal of this project is to: $1$) raise awareness of issues relating to gender inequity in politics, and $2$) positively influence public discourse in politics. The main contribution of this paper is a scalable model to classify and respond to hateful tweets with quantitative and qualitative assessments. The ParityBOT abusive classification system was validated on public online harassment datasets. We conclude with analysis of the impact of ParityBOT, drawing from data gathered during interventions in both the $2019$ Alberta provincial and $2019$ Canadian federal elections. |
| Tasks | Decision Making |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11025v1 |
| https://arxiv.org/pdf/1911.11025v1.pdf | |
| PWC | https://paperswithcode.com/paper/women-politics-and-twitter-using-machine |
| Repo | |
| Framework | |
Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey
| Title | Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey |
| Authors | Vanessa Buhrmester, David Münch, Michael Arens |
| Abstract | Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized to be non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificial datasets, often with bias or contaminated discriminating content. Through their increased distribution, decision-making algorithms can contribute promoting prejudge and unfairness which is not easy to notice due to lack of transparency. Hence, scientists developed several so-called explanators or explainers which try to point out the connection between input and output to represent in a simplified way the inner structure of machine learning black boxes. In this survey we differ the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas. |
| Tasks | Decision Making |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.12116v1 |
| https://arxiv.org/pdf/1911.12116v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-explainers-of-black-box-deep |
| Repo | |
| Framework | |
A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning
| Title | A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning |
| Authors | Xiang Li, Wenhao Yang, Zhihua Zhang |
| Abstract | We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant entropy-regularized MDPs can be cast into our framework. Moreover, under our framework, many regularization terms can bring multi-modality and sparsity, which are potentially useful in reinforcement learning. In particular, we present sufficient and necessary conditions that induce a sparse optimal policy. We also conduct a full mathematical analysis of the proposed regularized MDPs, including the optimality condition, performance error, and sparseness control. We provide a generic method to devise regularization forms and propose off-policy actor critic algorithms in complex environment settings. We empirically analyze the numerical properties of optimal policies and compare the performance of different sparse regularization forms in discrete and continuous environments. |
| Tasks | |
| Published | 2019-03-02 |
| URL | https://arxiv.org/abs/1903.00725v3 |
| https://arxiv.org/pdf/1903.00725v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-framework-for-regularized |
| Repo | |
| Framework | |
Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection
| Title | Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection |
| Authors | Shubhi Tyagi, Marco Nicolis, Jonas Rohnke, Thomas Drugman, Jaime Lorenzo-Trueba |
| Abstract | Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-human capabilities when considering isolated sentences. But something which is still lacking in order to achieve human-like communication is the dynamic variations and adaptability of human speech. This work attempts to solve the problem of achieving a more dynamic and natural intonation in TTS systems, particularly for stylistic speech such as the newscaster speaking style. We propose a novel embedding selection approach which exploits linguistic information, leveraging the speech variability present in the training dataset. We analyze the contribution of both semantic and syntactic features. Our results show that the approach improves the prosody and naturalness for complex utterances as well as in Long Form Reading (LFR). |
| Tasks | Speech Synthesis |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00955v1 |
| https://arxiv.org/pdf/1912.00955v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-prosody-generation-for-speech |
| Repo | |
| Framework | |
