Paper Group ANR 558
Measuring similarity between geo-tagged videos using largest common view. HAMNER: Headword Amplified Multi-span Distantly Supervised Method for Domain Specific Named Entity Recognition. Learning Quantum Graphical Models using Constrained Gradient Descent on the Stiefel Manifold. Populating Web Scale Knowledge Graphs using Distantly Supervised Relat …
Measuring similarity between geo-tagged videos using largest common view
| Title | Measuring similarity between geo-tagged videos using largest common view |
| Authors | Wei Ding, KwangSoo Yang, Kwang Woo Nam |
| Abstract | This paper presents a novel problem for discovering the similar trajectories based on the field of view (FoV) of the video data. The problem is important for many societal applications such as grouping moving objects, classifying geo-images, and identifying the interesting trajectory patterns. Prior work consider only either spatial locations or spatial relationship between two line-segments. However, these approaches show a limitation to find the similar moving objects with common views. In this paper, we propose new algorithm that can group both spatial locations and points of view to identify similar trajectories. We also propose novel methods that reduce the computational cost for the proposed work. Experimental results using real-world datasets demonstrates that the proposed approach outperforms prior work and reduces the computational cost. |
| Tasks | |
| Published | 2019-04-28 |
| URL | http://arxiv.org/abs/1905.03695v1 |
| http://arxiv.org/pdf/1905.03695v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503695 |
| Repo | |
| Framework | |
HAMNER: Headword Amplified Multi-span Distantly Supervised Method for Domain Specific Named Entity Recognition
| Title | HAMNER: Headword Amplified Multi-span Distantly Supervised Method for Domain Specific Named Entity Recognition |
| Authors | Shifeng Liu, Yifang Sun, Bing Li, Wei Wang, Xiang Zhao |
| Abstract | To tackle Named Entity Recognition (NER) tasks, supervised methods need to obtain sufficient cleanly annotated data, which is labor and time consuming. On the contrary, distantly supervised methods acquire automatically annotated data using dictionaries to alleviate this requirement. Unfortunately, dictionaries hinder the effectiveness of distantly supervised methods for NER due to its limited coverage, especially in specific domains. In this paper, we aim at the limitations of the dictionary usage and mention boundary detection. We generalize the distant supervision by extending the dictionary with headword based non-exact matching. We apply a function to better weight the matched entity mentions. We propose a span-level model, which classifies all the possible spans then infers the selected spans with a proposed dynamic programming algorithm. Experiments on all three benchmark datasets demonstrate that our method outperforms previous state-of-the-art distantly supervised methods. |
| Tasks | Boundary Detection, Named Entity Recognition |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01731v1 |
| https://arxiv.org/pdf/1912.01731v1.pdf | |
| PWC | https://paperswithcode.com/paper/hamner-headword-amplified-multi-span |
| Repo | |
| Framework | |
Learning Quantum Graphical Models using Constrained Gradient Descent on the Stiefel Manifold
| Title | Learning Quantum Graphical Models using Constrained Gradient Descent on the Stiefel Manifold |
| Authors | Sandesh Adhikary, Siddarth Srinivasan, Byron Boots |
| Abstract | Quantum graphical models (QGMs) extend the classical framework for reasoning about uncertainty by incorporating the quantum mechanical view of probability. Prior work on QGMs has focused on hidden quantum Markov models (HQMMs), which can be formulated using quantum analogues of the sum rule and Bayes rule used in classical graphical models. Despite the focus on developing the QGM framework, there has been little progress in learning these models from data. The existing state-of-the-art approach randomly initializes parameters and iteratively finds unitary transformations that increase the likelihood of the data. While this algorithm demonstrated theoretical strengths of HQMMs over HMMs, it is slow and can only handle a small number of hidden states. In this paper, we tackle the learning problem by solving a constrained optimization problem on the Stiefel manifold using a well-known retraction-based algorithm. We demonstrate that this approach is not only faster and yields better solutions on several datasets, but also scales to larger models that were prohibitively slow to train via the earlier method. |
| Tasks | |
| Published | 2019-03-09 |
| URL | http://arxiv.org/abs/1903.03730v1 |
| http://arxiv.org/pdf/1903.03730v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-quantum-graphical-models-using |
| Repo | |
| Framework | |
Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation
| Title | Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation |
| Authors | Sarthak Dash, Michael R. Glass, Alfio Gliozzo, Mustafa Canim |
| Abstract | In this paper, we propose a fully automated system to extend knowledge graphs using external information from web-scale corpora. The designed system leverages a deep learning based technology for relation extraction that can be trained by a distantly supervised approach. In addition to that, the system uses a deep learning approach for knowledge base completion by utilizing the global structure information of the induced KG to further refine the confidence of the newly discovered relations. The designed system does not require any effort for adaptation to new languages and domains as it does not use any hand-labeled data, NLP analytics and inference rules. Our experiments, performed on a popular academic benchmark demonstrate that the suggested system boosts the performance of relation extraction by a wide margin, reporting error reductions of 50%, resulting in relative improvement of up to 100%. Also, a web-scale experiment conducted to extend DBPedia with knowledge from Common Crawl shows that our system is not only scalable but also does not require any adaptation cost, while yielding substantial accuracy gain. |
| Tasks | Knowledge Base Completion, Knowledge Graphs, Relation Extraction |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.08104v2 |
| https://arxiv.org/pdf/1908.08104v2.pdf | |
| PWC | https://paperswithcode.com/paper/populating-web-scale-knowledge-graphs-using |
| Repo | |
| Framework | |
On the negation of a Dempster-Shafer belief structure based on maximum uncertainty allocation
| Title | On the negation of a Dempster-Shafer belief structure based on maximum uncertainty allocation |
| Authors | Xinyang Deng, Wen Jiang |
| Abstract | Probability theory and Dempster-Shafer theory are two germane theories to represent and handle uncertain information. Recent study suggested a transformation to obtain the negation of a probability distribution based on the maximum entropy. Correspondingly, determining the negation of a belief structure, however, is still an open issue in Dempster-Shafer theory, which is very important in theoretical research and practical applications. In this paper, a negation transformation for belief structures is proposed based on maximum uncertainty allocation, and several important properties satisfied by the transformation have been studied. The proposed negation transformation is more general and could totally compatible with existing transformation for probability distributions. |
| Tasks | |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10072v1 |
| http://arxiv.org/pdf/1901.10072v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-negation-of-a-dempster-shafer-belief |
| Repo | |
| Framework | |
Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
| Title | Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation |
| Authors | Erik Englesson, Hossein Azizpour |
| Abstract | In this work we aim to obtain computationally-efficient uncertainty estimates with deep networks. For this, we propose a modified knowledge distillation procedure that achieves state-of-the-art uncertainty estimates both for in and out-of-distribution samples. Our contributions include a) demonstrating and adapting to distillation’s regularization effect b) proposing a novel target teacher distribution c) a simple augmentation procedure to improve out-of-distribution uncertainty estimates d) shedding light on the distillation procedure through comprehensive set of experiments. |
| Tasks | |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.05419v1 |
| https://arxiv.org/pdf/1906.05419v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-evaluation-time-uncertainty |
| Repo | |
| Framework | |
Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining
| Title | Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining |
| Authors | Wen-Chin Huang, Tomoki Hayashi, Yi-Chiao Wu, Hirokazu Kameoka, Tomoki Toda |
| Abstract | We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining. Seq2seq VC models are attractive owing to their ability to convert prosody. While seq2seq models based on recurrent neural networks (RNNs) and convolutional neural networks (CNNs) have been successfully applied to VC, the use of the Transformer network, which has shown promising results in various speech processing tasks, has not yet been investigated. Nonetheless, their data-hungry property and the mispronunciation of converted speech make seq2seq models far from practical. To this end, we propose a simple yet effective pretraining technique to transfer knowledge from learned TTS models, which benefit from large-scale, easily accessible TTS corpora. VC models initialized with such pretrained model parameters are able to generate effective hidden representations for high-fidelity, highly intelligible converted speech. Experimental results show that such a pretraining scheme can facilitate data-efficient training and outperform an RNN-based seq2seq VC model in terms of intelligibility, naturalness, and similarity. |
| Tasks | Voice Conversion |
| Published | 2019-12-14 |
| URL | https://arxiv.org/abs/1912.06813v1 |
| https://arxiv.org/pdf/1912.06813v1.pdf | |
| PWC | https://paperswithcode.com/paper/voice-transformer-network-sequence-to |
| Repo | |
| Framework | |
An Optimal Algorithm for Multiplayer Multi-Armed Bandits
| Title | An Optimal Algorithm for Multiplayer Multi-Armed Bandits |
| Authors | Alexandre Proutiere, Po-An Wang |
| Abstract | The paper addresses the Multiplayer Multi-Armed Bandit (MMAB) problem, where $M$ decision makers or players collaborate to maximize their cumulative reward. When several players select the same arm, a collision occurs and no reward is collected on this arm. Players involved in a collision are informed about this collision. We present DPE (Decentralized Parsimonious Exploration), a decentralized algorithm that achieves the same regret as that obtained by an optimal centralized algorithm. Our algorithm has better regret guarantees than the state-of-the-art algorithm SIC-MMAB \cite{boursier2019}. As in SIC-MMAB, players communicate through collisions only. An additional important advantage of DPE is that it requires very little communication. Specifically, the expected number of rounds where players use collisions to communicate is finite. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-09-28 |
| URL | https://arxiv.org/abs/1909.13079v2 |
| https://arxiv.org/pdf/1909.13079v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-optimal-algorithm-in-multiplayer-multi |
| Repo | |
| Framework | |
Lingua Custodia at WMT’19: Attempts to Control Terminology
| Title | Lingua Custodia at WMT’19: Attempts to Control Terminology |
| Authors | Franck Burlot |
| Abstract | This paper describes Lingua Custodia’s submission to the WMT’19 news shared task for German-to-French on the topic of the EU elections. We report experiments on the adaptation of the terminology of a machine translation system to a specific topic, aimed at providing more accurate translations of specific entities like political parties and person names, given that the shared task provided no in-domain training parallel data dealing with the restricted topic. Our primary submission to the shared task uses backtranslation generated with a type of decoding allowing the insertion of constraints in the output in order to guarantee the correct translation of specific terms that are not necessarily observed in the data. |
| Tasks | Machine Translation |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04618v1 |
| https://arxiv.org/pdf/1907.04618v1.pdf | |
| PWC | https://paperswithcode.com/paper/lingua-custodia-at-wmt19-attempts-to-control |
| Repo | |
| Framework | |
Provenance Data in the Machine Learning Lifecycle in Computational Science and Engineering
| Title | Provenance Data in the Machine Learning Lifecycle in Computational Science and Engineering |
| Authors | Renan Souza, Leonardo Azevedo, Vítor Lourenço, Elton Soares, Raphael Thiago, Rafael Brandão, Daniel Civitarese, Emilio Vital Brazil, Marcio Moreno, Patrick Valduriez, Marta Mattoso, Renato Cerqueira, Marco A. S. Netto |
| Abstract | Machine Learning (ML) has become essential in several industries. In Computational Science and Engineering (CSE), the complexity of the ML lifecycle comes from the large variety of data, scientists’ expertise, tools, and workflows. If data are not tracked properly during the lifecycle, it becomes unfeasible to recreate a ML model from scratch or to explain to stakeholders how it was created. The main limitation of provenance tracking solutions is that they cannot cope with provenance capture and integration of domain and ML data processed in the multiple workflows in the lifecycle while keeping the provenance capture overhead low. To handle this problem, in this paper we contribute with a detailed characterization of provenance data in the ML lifecycle in CSE; a new provenance data representation, called PROV-ML, built on top of W3C PROV and ML Schema; and extensions to a system that tracks provenance from multiple workflows to address the characteristics of ML and CSE, and to allow for provenance queries with a standard vocabulary. We show a practical use in a real case in the Oil and Gas industry, along with its evaluation using 48 GPUs in parallel. |
| Tasks | |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04223v2 |
| https://arxiv.org/pdf/1910.04223v2.pdf | |
| PWC | https://paperswithcode.com/paper/provenance-data-in-the-machine-learning |
| Repo | |
| Framework | |
Recognizing long-form speech using streaming end-to-end models
| Title | Recognizing long-form speech using streaming end-to-end models |
| Authors | Arun Narayanan, Rohit Prabhavalkar, Chung-Cheng Chiu, David Rybach, Tara N. Sainath, Trevor Strohman |
| Abstract | All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the ability of E2E models to generalize to unseen domains, where we find that models trained on short utterances fail to generalize to long-form speech. We propose two complementary solutions to address this: training on diverse acoustic data, and LSTM state manipulation to simulate long-form audio when training using short utterances. On a synthesized long-form test set, adding data diversity improves word error rate (WER) by 90% relative, while simulating long-form training improves it by 67% relative, though the combination doesn’t improve over data diversity alone. On a real long-form call-center test set, adding data diversity improves WER by 40% relative. Simulating long-form training on top of data diversity improves performance by an additional 27% relative. |
| Tasks | Speech Recognition |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11455v1 |
| https://arxiv.org/pdf/1910.11455v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognizing-long-form-speech-using-streaming |
| Repo | |
| Framework | |
A computational model for grid maps in neural populations
| Title | A computational model for grid maps in neural populations |
| Authors | Fabio Anselmi, Micah M. Murray, Benedetta Franceschiello |
| Abstract | Grid cells in the entorhinal cortex, together with head direction, place, speed and border cells, are major contributors to the organization of spatial representations in the brain. In this work we introduce a novel theoretical and algorithmic framework able to explain the emergence of hexagonal grid-like response patterns from head direction cells’ responses. We show that this pattern is a result of minimal variance encoding of neurons. The novelty lies into the formulation of the encoding problem through the modern Frame Theory language, specifically that of equiangular Frames, providing new insights about the optimality of hexagonal grid receptive fields. The model proposed overcomes some crucial limitations of the current attractor and oscillatory models. It is based on the well-accepted and tested hypothesis of Hebbian learning, providing a simplified cortical-based framework that does not require the presence of theta velocity-driven oscillations (oscillatory model) or translational symmetries in the synaptic connections (attractor model). We moreover demonstrate that the proposed encoding mechanism naturally explains axis alignment of neighbor grid cells and maps shifts, rotations and scaling of the stimuli onto the shape of grid cells’ receptive fields, giving a straightforward explanation of the experimental evidence of grid cells remapping under transformations of environmental cues. |
| Tasks | |
| Published | 2019-02-18 |
| URL | https://arxiv.org/abs/1902.06553v3 |
| https://arxiv.org/pdf/1902.06553v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-computational-model-for-grid-maps-in-neural |
| Repo | |
| Framework | |
Deep Reinforcement Learning Based Parameter Control in Differential Evolution
| Title | Deep Reinforcement Learning Based Parameter Control in Differential Evolution |
| Authors | Mudita Sharma, Alexandros Komninos, Manuel Lopez Ibanez, Dimitar Kazakov |
| Abstract | Adaptive Operator Selection (AOS) is an approach that controls discrete parameters of an Evolutionary Algorithm (EA) during the run. In this paper, we propose an AOS method based on Double Deep Q-Learning (DDQN), a Deep Reinforcement Learning method, to control the mutation strategies of Differential Evolution (DE). The application of DDQN to DE requires two phases. First, a neural network is trained offline by collecting data about the DE state and the benefit (reward) of applying each mutation strategy during multiple runs of DE tackling benchmark functions. We define the DE state as the combination of 99 different features and we analyze three alternative reward functions. Second, when DDQN is applied as a parameter controller within DE to a different test set of benchmark functions, DDQN uses the trained neural network to predict which mutation strategy should be applied to each parent at each generation according to the DE state. Benchmark functions for training and testing are taken from the CEC2005 benchmark with dimensions 10 and 30. We compare the results of the proposed DE-DDQN algorithm to several baseline DE algorithms using no online selection, random selection and other AOS methods, and also to the two winners of the CEC2005 competition. The results show that DE-DDQN outperforms the non-adaptive methods for all functions in the test set; while its results are comparable with the last two algorithms. |
| Tasks | Q-Learning |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08006v1 |
| https://arxiv.org/pdf/1905.08006v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-based-parameter |
| Repo | |
| Framework | |
Compressing complex convolutional neural network based on an improved deep compression algorithm
| Title | Compressing complex convolutional neural network based on an improved deep compression algorithm |
| Authors | Jiasong Wu, Hongshan Ren, Youyong Kong, Chunfeng Yang, Lotfi Senhadji, Huazhong Shu |
| Abstract | Although convolutional neural network (CNN) has made great progress, large redundant parameters restrict its deployment on embedded devices, especially mobile devices. The recent compression works are focused on real-value convolutional neural network (Real CNN), however, to our knowledge, there is no attempt for the compression of complex-value convolutional neural network (Complex CNN). Compared with the real-valued network, the complex-value neural network is easier to optimize, generalize, and has better learning potential. This paper extends the commonly used deep compression algorithm from real domain to complex domain and proposes an improved deep compression algorithm for the compression of Complex CNN. The proposed algorithm compresses the network about 8 times on CIFAR-10 dataset with less than 3% accuracy loss. On the ImageNet dataset, our method compresses the model about 16 times and the accuracy loss is about 2% without retraining. |
| Tasks | |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.02358v1 |
| http://arxiv.org/pdf/1903.02358v1.pdf | |
| PWC | https://paperswithcode.com/paper/compressing-complex-convolutional-neural |
| Repo | |
| Framework | |
Real-time Visual Object Tracking with Natural Language Description
| Title | Real-time Visual Object Tracking with Natural Language Description |
| Authors | Qi Feng, Vitaly Ablavsky, Qinxun Bai, Guorong Li, Stan Sclaroff |
| Abstract | In recent years, deep-learning-based visual object trackers have been studied thoroughly, but handling occlusions and/or rapid motion of the target remains challenging. In this work, we argue that conditioning on the natural language (NL) description of a target provides information for longer-term invariance, and thus helps cope with typical tracking challenges. However, deriving a formulation to combine the strengths of appearance-based tracking with the language modality is not straightforward. We propose a novel deep tracking-by-detection formulation that can take advantage of NL descriptions. Regions that are related to the given NL description are generated by a proposal network during the detection phase of the tracker. Our LSTM based tracker then predicts the update of the target from regions proposed by the NL based detection phase. In benchmarks, our method is competitive with state of the art trackers, while it outperforms all other trackers on targets with unambiguous and precise language annotations. It also beats the state-of-the-art NL tracker when initializing without a bounding box. Our method runs at over 30 fps on a single GPU. |
| Tasks | Object Tracking, Visual Object Tracking |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11751v3 |
| https://arxiv.org/pdf/1907.11751v3.pdf | |
| PWC | https://paperswithcode.com/paper/tell-me-what-to-track |
| Repo | |
| Framework | |
