Paper Group NANR 60
Deep Reinforcement Learning for NLP. 3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children With Autism. Proceedings of the BioNLP 2018 workshop. A Detailed Evaluation of Neural Sequence-to-Sequence Models for In-domain and Cross-domain Text Simplification. Testing for Families of Distributions via the Fourier Transf …
Deep Reinforcement Learning for NLP
Title | Deep Reinforcement Learning for NLP |
Authors | William Yang Wang, Jiwei Li, Xiaodong He |
Abstract | Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems. |
Tasks | Atari Games, Coreference Resolution, Decision Making, Hierarchical Reinforcement Learning, Representation Learning, Text Classification, Video Captioning |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-5007/ |
https://www.aclweb.org/anthology/P18-5007 | |
PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-nlp |
Repo | |
Framework | |
3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children With Autism
Title | 3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children With Autism |
Authors | Elisabeta Marinoiu, Mihai Zanfir, Vlad Olaru, Cristian Sminchisescu |
Abstract | We introduce new, fine-grained action and emotion recognition tasks defined on non-staged videos, recorded during robot-assisted therapy sessions of children with autism. The tasks present several challenges: a large dataset with long videos, a large number of highly variable actions, children that are only partially visible, have different ages and may show unpredictable behaviour, as well as non-standard camera viewpoints. We investigate how state-of-the-art 3d human pose reconstruction methods perform on the newly introduced tasks and propose extensions to adapt them to deal with these challenges. We also analyze multiple approaches in action and emotion recognition from 3d human pose data, establish several baselines, and discuss results and their implications in the context of child-robot interaction. |
Tasks | Emotion Recognition |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Marinoiu_3D_Human_Sensing_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Marinoiu_3D_Human_Sensing_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/3d-human-sensing-action-and-emotion |
Repo | |
Framework | |
Proceedings of the BioNLP 2018 workshop
Title | Proceedings of the BioNLP 2018 workshop |
Authors | |
Abstract | |
Tasks | |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-2300/ |
https://www.aclweb.org/anthology/W18-2300 | |
PWC | https://paperswithcode.com/paper/proceedings-of-the-bionlp-2018-workshop |
Repo | |
Framework | |
A Detailed Evaluation of Neural Sequence-to-Sequence Models for In-domain and Cross-domain Text Simplification
Title | A Detailed Evaluation of Neural Sequence-to-Sequence Models for In-domain and Cross-domain Text Simplification |
Authors | Sanja {\v{S}}tajner, Sergiu Nisioi |
Abstract | |
Tasks | Machine Translation, Text Simplification |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1479/ |
https://www.aclweb.org/anthology/L18-1479 | |
PWC | https://paperswithcode.com/paper/a-detailed-evaluation-of-neural-sequence-to |
Repo | |
Framework | |
Testing for Families of Distributions via the Fourier Transform
Title | Testing for Families of Distributions via the Fourier Transform |
Authors | Alistair Stewart, Ilias Diakonikolas, Clement Canonne |
Abstract | We study the general problem of testing whether an unknown discrete distribution belongs to a specified family of distributions. More specifically, given a distribution family P and sample access to an unknown discrete distribution D , we want to distinguish (with high probability) between the case that D in P and the case that D is ε-far, in total variation distance, from every distribution in P . This is the prototypical hypothesis testing problem that has received significant attention in statistics and, more recently, in computer science. The main contribution of this work is a simple and general testing technique that is applicable to all distribution families whose Fourier spectrum satisfies a certain approximate sparsity property. We apply our Fourier-based framework to obtain near sample-optimal and computationally efficient testers for the following fundamental distribution families: Sums of Independent Integer Random Variables (SIIRVs), Poisson Multinomial Distributions (PMDs), and Discrete Log-Concave Distributions. For the first two, ours are the first non-trivial testers in the literature, vastly generalizing previous work on testing Poisson Binomial Distributions. For the third, our tester improves on prior work in both sample and time complexity. |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8210-testing-for-families-of-distributions-via-the-fourier-transform |
http://papers.nips.cc/paper/8210-testing-for-families-of-distributions-via-the-fourier-transform.pdf | |
PWC | https://paperswithcode.com/paper/testing-for-families-of-distributions-via-the |
Repo | |
Framework | |
A single channel sleep-spindle detector based on multivariate classification of EEG epochs: MUSSDET.
Title | A single channel sleep-spindle detector based on multivariate classification of EEG epochs: MUSSDET. |
Authors | DanielLachner-Piza, Nino Epitashvili, Andreas Schulze-Bonhage, Thomas Stieglitz, Julia Jacobs, Matthias Dümpelmann |
Abstract | BACKGROUND: Studies on sleep-spindles are typically based on visual-marks performed by experts, however this process is time consuming and presents a low inter-expert agreement, causing the data to be limited in quantity and prone to bias. An automatic detector would tackle these issues by generating large amounts of objectively marked data. NEW METHOD: Our goal was to develop a sensitive, precise and robust sleep-spindle detection method. Emphasis has been placed on achieving a consistent performance across heterogeneous recordings and without the need for further parameter fine tuning. The developed detector runs on a single channel and is based on multivariate classification using a support vector machine. Scalp-electroencephalogram recordings were segmented into epochs which were then characterized by a selection of relevant and non-redundant features. The training and validation data came from the Medical Center-University of Freiburg, the test data consisted of 27 records coming from 2 public databases. RESULTS: Using a sample based assessment, 53% sensitivity, 37% precision and 96% specificity was achieved on the DREAMS database. On the MASS database, 77% sensitivity, 46% precision and 96% specificity was achieved. The developed detector performed favorably when compared to previous detectors. The classification of normalized EEG epochs in a multidimensional space, as well as the use of a validation set, allowed to objectively define a single detection threshold for all databases and participants. CONCLUSIONS: The use of the developed tool will allow increasing the data-size and statistical significance of research studies on the role of sleep-spindles. |
Tasks | EEG, Spindle Detection |
Published | 2018-03-01 |
URL | https://doi.org/10.1016/j.jneumeth.2017.12.023 |
https://www.deepdyve.com/lp/elsevier/a-single-channel-sleep-spindle-detector-based-on-multivariate-grFKFTd9gR#bsSignUpModal | |
PWC | https://paperswithcode.com/paper/a-single-channel-sleep-spindle-detector-based |
Repo | |
Framework | |
Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces
Title | Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces |
Authors | Boyla Mainsah, Dmitry Kalika, Leslie Collins, Siyuan Liu, Chandra Throckmorton |
Abstract | Stimulus-driven brain-computer interfaces (BCIs), such as the P300 speller, rely on using a sequence of sensory stimuli to elicit specific neural responses as control signals, while a user attends to relevant target stimuli that occur within the sequence. In current BCIs, the stimulus presentation schedule is typically generated in a pseudo-random fashion. Given the non-stationarity of brain electrical signals, a better strategy could be to adapt the stimulus presentation schedule in real-time by selecting the optimal stimuli that will maximize the signal-to-noise ratios of the elicited neural responses and provide the most information about the user’s intent based on the uncertainties of the data being measured. However, the high-dimensional stimulus space limits the development of algorithms with tractable solutions for optimized stimulus selection to allow for real-time decision-making within the stringent time requirements of BCI processing. We derive a simple analytical solution of an information-based objective function for BCI stimulus selection by transforming the high-dimensional stimulus space into a one-dimensional space that parameterizes the objective function - the prior probability mass of the stimulus under consideration, irrespective of its contents. We demonstrate the utility of our adaptive stimulus selection algorithm in improving BCI performance with results from simulation and real-time human experiments. |
Tasks | Decision Making |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7731-information-based-adaptive-stimulus-selection-to-optimize-communication-efficiency-in-brain-computer-interfaces |
http://papers.nips.cc/paper/7731-information-based-adaptive-stimulus-selection-to-optimize-communication-efficiency-in-brain-computer-interfaces.pdf | |
PWC | https://paperswithcode.com/paper/information-based-adaptive-stimulus-selection |
Repo | |
Framework | |
LanguageNet: Learning to Find Sense Relevant Example Sentences
Title | LanguageNet: Learning to Find Sense Relevant Example Sentences |
Authors | Shang-Chien Cheng, Jhih-Jie Chen, Chingyu Yang, Jason Chang |
Abstract | In this paper, we present a system, LanguageNet, which can help second language learners to search for different meanings and usages of a word. We disambiguate word senses based on the pairs of an English word and its corresponding Chinese translations in a parallel corpus, UM-Corpus. The process involved performing word alignment, learning vector space representations of words and training a classifier to distinguish words into groups of senses. LanguageNet directly shows the definition of a sense, bilingual synonyms and sense relevant examples. |
Tasks | Word Alignment |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-2022/ |
https://www.aclweb.org/anthology/C18-2022 | |
PWC | https://paperswithcode.com/paper/languagenet-learning-to-find-sense-relevant |
Repo | |
Framework | |
Face Recognition with Contrastive Convolution
Title | Face Recognition with Contrastive Convolution |
Authors | Chunrui Han, Shiguang Shan, Meina Kan, Shuzhe Wu, Xilin Chen |
Abstract | In current face recognition approaches with convolutional neural network (CNN), a pair of faces to compare are independently fed into the CNN for feature extraction. For both faces the same kernels are applied and hence the representation of a face stays fixed regardless of who it is compared with. As for us humans, however, one generally focuses on varied characteristics of a face when comparing it with distinct persons. Inspired, we propose a novel CNN structure with what we referred to as contrastive convolution, which specifically focuses on the distinct characteristics between the two faces to compare, i.e., those contrastive characteristics. Extensive experiments on the challenging LFW, and IJB-A show that our proposed contrastive convolution significantly improves the vanilla CNN and achieves quite promising performance in face verification task. |
Tasks | Face Recognition, Face Verification |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Chunrui_Han_Face_Recognition_with_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Chunrui_Han_Face_Recognition_with_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/face-recognition-with-contrastive-convolution |
Repo | |
Framework | |
Conditional Generative Adversarial Network for Structured Domain Adaptation
Title | Conditional Generative Adversarial Network for Structured Domain Adaptation |
Authors | Weixiang Hong, Zhenzhen Wang, Ming Yang, Junsong Yuan |
Abstract | In recent years, deep neural nets have triumphed over many computer vision problems, including semantic segmentation, which is a critical task in emerging autonomous driving and medical image diagnostics applications. In general, training deep neural nets requires a humongous amount of labeled data, which is laborious and costly to collect and annotate. Recent advances in computer graphics shed light on utilizing photo-realistic synthetic data with computer generated annotations to train neural nets. Nevertheless, the domain mismatch between real images and synthetic ones is the major challenge against harnessing the generated data and labels. In this paper, we propose a principled way to conduct structured domain adaption for semantic segmentation, i.e., integrating GAN into the FCN framework to mitigate the gap between source and target domains. Specifically, we learn a conditional generator to transform features of synthetic images to real-image like features, and a discriminator to distinguish them. For each training batch, the conditional generator and the discriminator compete against each other so that the generator learns to produce real-image like features to fool the discriminator; afterwards, the FCN parameters are updated to accommodate the changes of GAN. In experiments, without using labels of real image data, our method significantly outperforms the baselines as well as state-of-the-art methods by 12% â¼ 20% mean IoU on the Cityscapes dataset. |
Tasks | Autonomous Driving, Domain Adaptation, Semantic Segmentation |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Hong_Conditional_Generative_Adversarial_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Hong_Conditional_Generative_Adversarial_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/conditional-generative-adversarial-network |
Repo | |
Framework | |
Regret Bounds for Online Portfolio Selection with a Cardinality Constraint
Title | Regret Bounds for Online Portfolio Selection with a Cardinality Constraint |
Authors | Shinji Ito, Daisuke Hatano, Sumita Hanna, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, Ken-Ichi Kawarabayashi |
Abstract | Online portfolio selection is a sequential decision-making problem in which a learner repetitively selects a portfolio over a set of assets, aiming to maximize long-term return. In this paper, we study the problem with the cardinality constraint that the number of assets in a portfolio is restricted to be at most k, and consider two scenarios: (i) in the full-feedback setting, the learner can observe price relatives (rates of return to cost) for all assets, and (ii) in the bandit-feedback setting, the learner can observe price relatives only for invested assets. We propose efficient algorithms for these scenarios that achieve sublinear regrets. We also provide regret (statistical) lower bounds for both scenarios which nearly match the upper bounds when k is a constant. In addition, we give a computational lower bound which implies that no algorithm maintains both computational efficiency, as well as a small regret upper bound. |
Tasks | Decision Making |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8258-regret-bounds-for-online-portfolio-selection-with-a-cardinality-constraint |
http://papers.nips.cc/paper/8258-regret-bounds-for-online-portfolio-selection-with-a-cardinality-constraint.pdf | |
PWC | https://paperswithcode.com/paper/regret-bounds-for-online-portfolio-selection |
Repo | |
Framework | |
Improving Unsupervised Keyphrase Extraction using Background Knowledge
Title | Improving Unsupervised Keyphrase Extraction using Background Knowledge |
Authors | Yang Yu, Vincent Ng |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1588/ |
https://www.aclweb.org/anthology/L18-1588 | |
PWC | https://paperswithcode.com/paper/improving-unsupervised-keyphrase-extraction |
Repo | |
Framework | |
Interpretable Neural Architectures for Attributing an Ad’s Performance to its Writing Style
Title | Interpretable Neural Architectures for Attributing an Ad’s Performance to its Writing Style |
Authors | Reid Pryzant, Sugato Basu, Kazoo Sone |
Abstract | How much does {``}free shipping!{''} help an advertisement{'}s ability to persuade? This paper presents two methods for \textit{performance attribution}: finding the degree to which an outcome can be attributed to parts of a text while controlling for potential confounders. Both algorithms are based on interpreting the behaviors and parameters of trained neural networks. One method uses a CNN to encode the text, an adversarial objective function to control for confounders, and projects its weights onto its activations to interpret the importance of each phrase towards each output class. The other method leverages residualization to control for confounds and performs interpretation by aggregating over learned word vectors. We demonstrate these algorithms{'} efficacy on 118,000 internet search advertisements and outcomes, finding language indicative of high and low click through rate (CTR) regardless of who the ad is by or what it is for. Our results suggest the proposed algorithms are high performance and data efficient, able to glean actionable insights from fewer than 10,000 data points. We find that quick, easy, and authoritative language is associated with success, while lackluster embellishment is related to failure. These findings agree with the advertising industry{'}s emperical wisdom, automatically revealing insights which previously required manual A/B testing to discover. | |
Tasks | Interpretable Machine Learning |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-5415/ |
https://www.aclweb.org/anthology/W18-5415 | |
PWC | https://paperswithcode.com/paper/interpretable-neural-architectures-for |
Repo | |
Framework | |
Leveraging Gloss Knowledge in Neural Word Sense Disambiguation by Hierarchical Co-Attention
Title | Leveraging Gloss Knowledge in Neural Word Sense Disambiguation by Hierarchical Co-Attention |
Authors | Fuli Luo, Tianyu Liu, Zexue He, Qiaolin Xia, Zhifang Sui, Baobao Chang |
Abstract | The goal of Word Sense Disambiguation (WSD) is to identify the correct meaning of a word in the particular context. Traditional supervised methods only use labeled data (context), while missing rich lexical knowledge such as the gloss which defines the meaning of a word sense. Recent studies have shown that incorporating glosses into neural networks for WSD has made significant improvement. However, the previous models usually build the context representation and gloss representation separately. In this paper, we find that the learning for the context and gloss representation can benefit from each other. Gloss can help to highlight the important words in the context, thus building a better context representation. Context can also help to locate the key words in the gloss of the correct word sense. Therefore, we introduce a co-attention mechanism to generate co-dependent representations for the context and gloss. Furthermore, in order to capture both word-level and sentence-level information, we extend the attention mechanism in a hierarchical fashion. Experimental results show that our model achieves the state-of-the-art results on several standard English all-words WSD test datasets. |
Tasks | Word Sense Disambiguation |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1170/ |
https://www.aclweb.org/anthology/D18-1170 | |
PWC | https://paperswithcode.com/paper/leveraging-gloss-knowledge-in-neural-word |
Repo | |
Framework | |
Deep Parametric Continuous Convolutional Neural Networks
Title | Deep Parametric Continuous Convolutional Neural Networks |
Authors | Shenlong Wang, Simon Suo, Wei-Chiu Ma, Andrei Pokrovsky, Raquel Urtasun |
Abstract | Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes. |
Tasks | Motion Estimation |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Deep_Parametric_Continuous_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Deep_Parametric_Continuous_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/deep-parametric-continuous-convolutional |
Repo | |
Framework | |