Paper Group NAWR 7
Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline. Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation. Leveraging Context Information for Natural Question Generation. Jointly Learning Convolutional Representations to Compress Radiological Images and Classify Thoracic D …
Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline
| Title | Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline |
| Authors | Zhenbo Xu, Wei Yang, Ajin Meng, Nanxue Lu, Huan Huang, Changchun Ying, Liusheng Huang |
| Abstract | Most current license plate (LP) detection and recognition approaches are evaluated on a small and usually unrepresentative dataset since there are no publicly available large diverse datasets. In this paper, we introduce CCPD, a large and comprehensive LP dataset. All images are taken manually by workers of a roadside parking management company and are annotated carefully. To our best knowledge, CCPD is the largest publicly available LP dataset to date with over 250k unique car images, and the only one provides vertices location annotations. With CCPD, we present a novel network model which can predict the bounding box and recognize the corresponding LP number simultaneously with high speed and accuracy. Through comparative experiments, we demonstrate our model outperforms current object detection and recognition approaches in both accuracy and speed. In real-world applications, our model recognizes LP numbers directly from relatively high-resolution images at over 61 fps and 98.5% accuracy. |
| Tasks | Object Detection |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Zhenbo_Xu_Towards_End-to-End_License_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Zhenbo_Xu_Towards_End-to-End_License_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/towards-end-to-end-license-plate-detection |
| Repo | https://github.com/detectRecog/CCPD |
| Framework | pytorch |
Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation
| Title | Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation |
| Authors | Shivapratap Gopakumar, Sunil Gupta, Santu Rana, Vu Nguyen, Svetha Venkatesh |
| Abstract | We introduce algorithmic assurance, the problem of testing whether machine learning algorithms are conforming to their intended design goal. We address this problem by proposing an efficient framework for algorithmic testing. To provide assurance, we need to efficiently discover scenarios where an algorithm decision deviates maximally from its intended gold standard. We mathematically formulate this task as an optimisation problem of an expensive, black-box function. We use an active learning approach based on Bayesian optimisation to solve this optimisation problem. We extend this framework to algorithms with vector-valued outputs by making appropriate modification in Bayesian optimisation via the EXP3 algorithm. We theoretically analyse our methods for convergence. Using two real-world applications, we demonstrate the efficiency of our methods. The significance of our problem formulation and initial solutions is that it will serve as the foundation in assuring humans about machines making complex decisions. |
| Tasks | Active Learning, Bayesian Optimisation |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7791-algorithmic-assurance-an-active-approach-to-algorithmic-testing-using-bayesian-optimisation |
| http://papers.nips.cc/paper/7791-algorithmic-assurance-an-active-approach-to-algorithmic-testing-using-bayesian-optimisation.pdf | |
| PWC | https://paperswithcode.com/paper/algorithmic-assurance-an-active-approach-to |
| Repo | https://github.com/ntienvu/AlgorithmicAssurance_NIPS2018 |
| Framework | none |
Leveraging Context Information for Natural Question Generation
| Title | Leveraging Context Information for Natural Question Generation |
| Authors | Linfeng Song, Zhiguo Wang, Wael Hamza, Yue Zhang, Daniel Gildea |
| Abstract | The task of natural question generation is to generate a corresponding question given the input passage (fact) and answer. It is useful for enlarging the training set of QA systems. Previous work has adopted sequence-to-sequence models that take a passage with an additional bit to indicate answer position as input. However, they do not explicitly model the information between answer and other context within the passage. We propose a model that matches the answer with the passage before generating the question. Experiments show that our model outperforms the existing state of the art using rich features. |
| Tasks | Question Generation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2090/ |
| https://www.aclweb.org/anthology/N18-2090 | |
| PWC | https://paperswithcode.com/paper/leveraging-context-information-for-natural |
| Repo | https://github.com/freesunshine0316/MPQG |
| Framework | tf |
Jointly Learning Convolutional Representations to Compress Radiological Images and Classify Thoracic Diseases in the Compressed Domain
| Title | Jointly Learning Convolutional Representations to Compress Radiological Images and Classify Thoracic Diseases in the Compressed Domain |
| Authors | Ekagra Ranjan, Soumava Paul, Siddharth Kapoor, Aupendu Kar, Ramanathan Sethuraman, Debdoot Sheet |
| Abstract | Deep learning models trained in natural images are commonly used for different classification tasks in the medical domain. Generally, very high dimensional medical images are down-sampled by us- ing interpolation techniques before feeding them to deep learning models that are ImageNet compliant and accept only low-resolution images of size 224 × 224 px. This popular technique may lead to the loss of key information thus hampering the classification. Signifi- cant pathological features in medical images typically being small sized and highly affected. To combat this problem, we introduce a convolutional neural network (CNN) based classification approach which learns to reduce the resolution of the image using an autoen- coder and at the same time classify it using another network, while both the tasks are trained jointly. This algorithm guides the model to learn essential representations from high-resolution images for classification along with reconstruction. We have used the publicly available dataset of chest x-rays to evaluate this approach and have outperformed state-of-the-art on test data. Besides, we have experi- mented with the effects of different augmentation approaches in this dataset and report baselines using some well known ImageNet class of CNNs. |
| Tasks | Pneumonia Detection, Thoracic Disease Classification |
| Published | 2018-12-18 |
| URL | https://drive.google.com/file/d/1i2jl5M0ddr-STAma0a2Bsr5rOMtcCSyB/view |
| https://drive.google.com/file/d/1i2jl5M0ddr-STAma0a2Bsr5rOMtcCSyB/view | |
| PWC | https://paperswithcode.com/paper/jointly-learning-convolutional |
| Repo | https://github.com/ekagra-ranjan/AE-CNN |
| Framework | pytorch |
Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms
| Title | Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms |
| Authors | Yubo Chen, Hang Yang, Kang Liu, Jun Zhao, Yantao Jia |
| Abstract | Traditional approaches to the task of ACE event detection primarily regard multiple events in one sentence as independent ones and recognize them separately by using sentence-level information. However, events in one sentence are usually interdependent and sentence-level information is often insufficient to resolve ambiguities for some types of events. This paper proposes a novel framework dubbed as Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms (HBTNGMA) to solve the two problems simultaneously. Firstly, we propose a hierachical and bias tagging networks to detect multiple events in one sentence collectively. Then, we devise a gated multi-level attention to automatically extract and dynamically fuse the sentence-level and document-level information. The experimental results on the widely used ACE 2005 dataset show that our approach significantly outperforms other state-of-the-art methods. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1158/ |
| https://www.aclweb.org/anthology/D18-1158 | |
| PWC | https://paperswithcode.com/paper/collective-event-detection-via-a-hierarchical |
| Repo | https://github.com/yubochen/NBTNGMA4ED |
| Framework | tf |
Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism
| Title | Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism |
| Authors | Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu |
| Abstract | Named entity recognition (NER) is an important task in natural language processing area, which needs to determine entities boundaries and classify them into pre-defined categories. For Chinese NER task, there is only a very small amount of annotated data available. Chinese NER task and Chinese word segmentation (CWS) task have many similar word boundaries. There are also specificities in each task. However, existing methods for Chinese NER either do not exploit word boundary information from CWS or cannot filter the specific information of CWS. In this paper, we propose a novel adversarial transfer learning framework to make full use of task-shared boundaries information and prevent the task-specific features of CWS. Besides, since arbitrary character can provide important cues when predicting entity type, we exploit self-attention to explicitly capture long range dependencies between two tokens. Experimental results on two different widely used datasets show that our proposed model significantly and consistently outperforms other state-of-the-art methods. |
| Tasks | Chinese Named Entity Recognition, Chinese Word Segmentation, Named Entity Recognition, Transfer Learning |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1017/ |
| https://www.aclweb.org/anthology/D18-1017 | |
| PWC | https://paperswithcode.com/paper/adversarial-transfer-learning-for-chinese |
| Repo | https://github.com/CPF-NLPR/AT4ChineseNER |
| Framework | tf |
Learning Word Representations with Cross-Sentence Dependency for End-to-End Co-reference Resolution
| Title | Learning Word Representations with Cross-Sentence Dependency for End-to-End Co-reference Resolution |
| Authors | Hongyin Luo, Jim Glass |
| Abstract | In this work, we present a word embedding model that learns cross-sentence dependency for improving end-to-end co-reference resolution (E2E-CR). While the traditional E2E-CR model generates word representations by running long short-term memory (LSTM) recurrent neural networks on each sentence of an input article or conversation separately, we propose linear sentence linking and attentional sentence linking models to learn cross-sentence dependency. Both sentence linking strategies enable the LSTMs to make use of valuable information from context sentences while calculating the representation of the current input word. With this approach, the LSTMs learn word embeddings considering knowledge not only from the current sentence but also from the entire input document. Experiments show that learning cross-sentence dependency enriches information contained by the word representations, and improves the performance of the co-reference resolution model compared with our baseline. |
| Tasks | Coreference Resolution |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1518/ |
| https://www.aclweb.org/anthology/D18-1518 | |
| PWC | https://paperswithcode.com/paper/learning-word-representations-with-cross |
| Repo | https://github.com/luohongyin/coatt-coref |
| Framework | tf |
A Hierarchical Neural Attention-based Text Classifier
| Title | A Hierarchical Neural Attention-based Text Classifier |
| Authors | Koustuv Sinha, Yue Dong, Jackie Chi Kit Cheung, Derek Ruths |
| Abstract | Deep neural networks have been displaying superior performance over traditional supervised classifiers in text classification. They learn to extract useful features automatically when sufficient amount of data is presented. However, along with the growth in the number of documents comes the increase in the number of categories, which often results in poor performance of the multiclass classifiers. In this work, we use external knowledge in the form of topic category taxonomies to aide the classification by introducing a deep hierarchical neural attention-based classifier. Our model performs better than or comparable to state-of-the-art hierarchical models at significantly lower computational cost while maintaining high interpretability. |
| Tasks | Text Classification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1094/ |
| https://www.aclweb.org/anthology/D18-1094 | |
| PWC | https://paperswithcode.com/paper/a-hierarchical-neural-attention-based-text |
| Repo | https://github.com/koustuvsinha/hier-class |
| Framework | pytorch |
ELDEN: Improved Entity Linking Using Densified Knowledge Graphs
| Title | ELDEN: Improved Entity Linking Using Densified Knowledge Graphs |
| Authors | Priya Radhakrishnan, Partha Talukdar, Vasudeva Varma |
| Abstract | Entity Linking (EL) systems aim to automatically map mentions of an entity in text to the corresponding entity in a Knowledge Graph (KG). Degree of connectivity of an entity in the KG directly affects an EL system{'}s ability to correctly link mentions in text to the entity in KG. This causes many EL systems to perform well for entities well connected to other entities in KG, bringing into focus the role of KG density in EL. In this paper, we propose Entity Linking using Densified Knowledge Graphs (ELDEN). ELDEN is an EL system which first densifies the KG with co-occurrence statistics from a large text corpus, and then uses the densified KG to train entity embeddings. Entity similarity measured using these trained entity embeddings result in improved EL. ELDEN outperforms state-of-the-art EL system on benchmark datasets. Due to such densification, ELDEN performs well for sparsely connected entities in the KG too. ELDEN{'}s approach is simple, yet effective. We have made ELDEN{'}s code and data publicly available. |
| Tasks | Entity Embeddings, Entity Linking, Knowledge Graphs |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1167/ |
| https://www.aclweb.org/anthology/N18-1167 | |
| PWC | https://paperswithcode.com/paper/elden-improved-entity-linking-using-densified |
| Repo | https://github.com/priyaradhakrishnan0/ELDEN |
| Framework | pytorch |
WikiDragon: A Java Framework For Diachronic Content And Network Analysis Of MediaWikis
| Title | WikiDragon: A Java Framework For Diachronic Content And Network Analysis Of MediaWikis |
| Authors | R{"u}diger Gleim, Alex Mehler, er, Sung Y. Song |
| Abstract | |
| Tasks | Named Entity Recognition, Word Sense Disambiguation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1589/ |
| https://www.aclweb.org/anthology/L18-1589 | |
| PWC | https://paperswithcode.com/paper/wikidragon-a-java-framework-for-diachronic |
| Repo | https://github.com/texttechnologylab/WikiDragon |
| Framework | none |
Adaptive Methods for Nonconvex Optimization
| Title | Adaptive Methods for Nonconvex Optimization |
| Authors | Manzil Zaheer, Sashank Reddi, Devendra Sachan, Satyen Kale, Sanjiv Kumar |
| Abstract | Adaptive gradient methods that rely on scaling gradients down by the square root of exponential moving averages of past squared gradients, such RMSProp, Adam, Adadelta have found wide application in optimizing the nonconvex problems that arise in deep learning. However, it has been recently demonstrated that such methods can fail to converge even in simple convex optimization settings. In this work, we provide a new analysis of such methods applied to nonconvex stochastic optimization problems, characterizing the effect of increasing minibatch size. Our analysis shows that under this scenario such methods do converge to stationarity up to the statistical limit of variance in the stochastic gradients (scaled by a constant factor). In particular, our result implies that increasing minibatch sizes enables convergence, thus providing a way to circumvent the non-convergence issues. Furthermore, we provide a new adaptive optimization algorithm, Yogi, which controls the increase in effective learning rate, leading to even better performance with similar theoretical guarantees on convergence. Extensive experiments show that Yogi with very little hyperparameter tuning outperforms methods such as Adam in several challenging machine learning tasks. |
| Tasks | Stochastic Optimization |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8186-adaptive-methods-for-nonconvex-optimization |
| http://papers.nips.cc/paper/8186-adaptive-methods-for-nonconvex-optimization.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-methods-for-nonconvex-optimization |
| Repo | https://github.com/jettify/pytorch-optimizer |
| Framework | pytorch |
Neural Program Synthesis from Diverse Demonstration Videos
| Title | Neural Program Synthesis from Diverse Demonstration Videos |
| Authors | Shao-Hua Sun, Hyeonwoo Noh, Sriram Somasundaram, Joseph Lim |
| Abstract | Interpreting decision making logic in demonstration videos is key to collaborating with and mimicking humans. To empower machines with this ability, we propose a neural program synthesizer that is able to explicitly synthesize underlying programs from behaviorally diverse and visually complicated demonstration videos. We introduce a summarizer module as part of our model to improve the network’s ability to integrate multiple demonstrations varying in behavior. We also employ a multi-task objective to encourage the model to learn meaningful intermediate representations for end-to-end training. We show that our model is able to reliably synthesize underlying programs as well as capture diverse behaviors exhibited in demonstrations. The code is available at https://shaohua0116.github.io/demo2program. |
| Tasks | Decision Making, Program Synthesis |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1909 |
| http://proceedings.mlr.press/v80/sun18a/sun18a.pdf | |
| PWC | https://paperswithcode.com/paper/neural-program-synthesis-from-diverse |
| Repo | https://github.com/shaohua0116/demo2program |
| Framework | tf |
Multiple Context Features in Siamese Networks for Visual Object Tracking
| Title | Multiple Context Features in Siamese Networks for Visual Object Tracking |
| Authors | Henrique Morimitsu |
| Abstract | Siamese networks have been successfully utilized to learn a robust matching function between pairs of images. Visual object tracking methods based on siamese networks have been gaining popularity recently due to their robustness and speed. However, existing siamese approaches are still unable to perform on par with the most accurate trackers. In this paper, we propose to extend the SiamFC tracker to extract features at multiple context and semantic levels from very deep networks. We show that our approach effectively extracts complementary features for siamese matching from different layers, which provides a significant performance boost when fused. Experimental results on VOT and OTB datasets show that our multi-context tracker is comparable to the most accurate methods, while still being faster than most of them. In particular, we outperform several other state-of-the-art siamese methods. |
| Tasks | Object Tracking, Visual Object Tracking |
| Published | 2018-09-01 |
| URL | http://thoth.inrialpes.fr/people/hmorimit/publications.php |
| http://openaccess.thecvf.com/content_ECCVW_2018/papers/11129/Morimitsu_Multiple_Context_Features_in_Siamese_Networks_for_Visual_Object_Tracking_ECCVW_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-context-features-in-siamese-networks |
| Repo | https://github.com/hmorimitsu/siam-mcf |
| Framework | tf |
Specialising Word Vectors for Lexical Entailment
| Title | Specialising Word Vectors for Lexical Entailment |
| Authors | Ivan Vuli{'c}, Nikola Mrk{\v{s}}i{'c} |
| Abstract | We present LEAR (Lexical Entailment Attract-Repel), a novel post-processing method that transforms any input word vector space to emphasise the asymmetric relation of lexical entailment (LE), also known as the IS-A or hyponymy-hypernymy relation. By injecting external linguistic constraints (e.g., WordNet links) into the initial vector space, the LE specialisation procedure brings true hyponymy-hypernymy pairs closer together in the transformed Euclidean space. The proposed asymmetric distance measure adjusts the norms of word vectors to reflect the actual WordNet-style hierarchy of concepts. Simultaneously, a joint objective enforces semantic similarity using the symmetric cosine distance, yielding a vector space specialised for both lexical relations at once. LEAR specialisation achieves state-of-the-art performance in the tasks of hypernymy directionality, hypernymy detection, and graded lexical entailment, demonstrating the effectiveness and robustness of the proposed asymmetric specialisation model. |
| Tasks | Dialogue State Tracking, Machine Translation, Natural Language Inference, Representation Learning, Semantic Similarity, Semantic Textual Similarity, Text Generation, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1103/ |
| https://www.aclweb.org/anthology/N18-1103 | |
| PWC | https://paperswithcode.com/paper/specialising-word-vectors-for-lexical |
| Repo | https://github.com/nmrksic/lear |
| Framework | tf |
Coupled Variational Bayes via Optimization Embedding
| Title | Coupled Variational Bayes via Optimization Embedding |
| Authors | Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song |
| Abstract | Variational inference plays a vital role in learning graphical models, especially on large-scale datasets. Much of its success depends on a proper choice of auxiliary distribution class for posterior approximation. However, how to pursue an auxiliary distribution class that achieves both good approximation ability and computation efficiency remains a core challenge. In this paper, we proposed coupled variational Bayes which exploits the primal-dual view of the ELBO with the variational distribution class generated by an optimization procedure, which is termed optimization embedding. This flexible function class couples the variational distribution with the original parameters in the graphical models, allowing end-to-end learning of the graphical models by back-propagation through the variational distribution. Theoretically, we establish an interesting connection to gradient flow and demonstrate the extreme flexibility of this implicit distribution family in the limit sense. Empirically, we demonstrate the effectiveness of the proposed method on multiple graphical models with either continuous or discrete latent variables comparing to state-of-the-art methods. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8177-coupled-variational-bayes-via-optimization-embedding |
| http://papers.nips.cc/paper/8177-coupled-variational-bayes-via-optimization-embedding.pdf | |
| PWC | https://paperswithcode.com/paper/coupled-variational-bayes-via-optimization |
| Repo | https://github.com/Hanjun-Dai/cvb |
| Framework | pytorch |
