Paper Group NANR 113
On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos. ACTRCE: Augmenting Experience via Teacher’s Advice. Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks. A Guider Network for Multi-Dual Learning. Efficient Meta Learning via Minibatch Proximal Update. Towards Automating Healthcare Question Answ …
On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos
| Title | On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos |
| Authors | Zhi Li, Xuan Wang, Fei Wang, Peilin Jiang |
| Abstract | The premise of training an accurate 3D human pose estimation network is the possession of huge amount of richly annotated training data. Nonetheless, manually obtaining rich and accurate annotations is, even not impossible, tedious and slow. In this paper, we propose to exploit monocular videos to complement the training dataset for the single-image 3D human pose estimation tasks. At the beginning, a baseline model is trained with a small set of annotations. By fixing some reliable estimations produced by the resulting model, our method automatically collects the annotations across the entire video as solving the 3D trajectory completion problem. Then, the baseline model is further trained with the collected annotations to learn the new poses. We evaluate our method on the broadly-adopted Human3.6M and MPI-INF-3DHP datasets. As illustrated in experiments, given only a small set of annotations, our method successfully makes the model to learn new poses from unlabelled monocular videos, promoting the accuracies of the baseline model by about 10%. By contrast with previous approaches, our method does not rely on either multi-view imagery or any explicit 2D keypoint annotations. |
| Tasks | 3D Human Pose Estimation, Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Li_On_Boosting_Single-Frame_3D_Human_Pose_Estimation_via_Monocular_Videos_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_On_Boosting_Single-Frame_3D_Human_Pose_Estimation_via_Monocular_Videos_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/on-boosting-single-frame-3d-human-pose |
| Repo | |
| Framework | |
ACTRCE: Augmenting Experience via Teacher’s Advice
| Title | ACTRCE: Augmenting Experience via Teacher’s Advice |
| Authors | Yuhuai Wu, Harris Chan, Jamie Kiros, Sanja Fidler, Jimmy Ba |
| Abstract | Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failure experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and universal goal representation. We present Augmenting experienCe via TeacheR’s adviCE (ACTRCE), an efficient reinforcement learning technique that extends the HER framework using natural language as the goal representation. We first analyze the differences among goal representation, and show that ACTRCE can efficiently solve difficult reinforcement learning problems in challenging 3D navigation tasks, whereas HER with non-language goal representation failed to learn. We also show that with language goal representations, the agent can generalize to unseen instructions, and even generalize to instructions with unseen lexicons. We further demonstrate it is crucial to use hindsight advice to solve challenging tasks, but we also found that little amount of hindsight advice is sufficient for the learning to take off, showing the practical aspect of the method. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HyM8V2A9Km |
| https://openreview.net/pdf?id=HyM8V2A9Km | |
| PWC | https://paperswithcode.com/paper/actrce-augmenting-experience-via-teachers-1 |
| Repo | |
| Framework | |
Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks
| Title | Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks |
| Authors | Hao Cheng, Dongze Lian, Bowen Deng, Shenghua Gao, Tao Tan, Yanlin Geng |
| Abstract | We propose a new learning paradigm, Local to Global Learning (LGL), for Deep Neural Networks (DNNs) to improve the performance of classification problems. The core of LGL is to learn a DNN model from fewer categories (local) to more categories (global) gradually within the entire training set. LGL is most related to the Self-Paced Learning (SPL) algorithm but its formulation is different from SPL. SPL trains its data from simple to complex, while LGL from local to global. In this paper, we incorporate the idea of LGL into the learning objective of DNNs and explain why LGL works better from an information-theoretic perspective. Experiments on the toy data, CIFAR-10, CIFAR-100, and ImageNet dataset show that LGL outperforms the baseline and SPL-based algorithms. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Cheng_Local_to_Global_Learning_Gradually_Adding_Classes_for_Training_Deep_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Cheng_Local_to_Global_Learning_Gradually_Adding_Classes_for_Training_Deep_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/local-to-global-learning-gradually-adding |
| Repo | |
| Framework | |
A Guider Network for Multi-Dual Learning
| Title | A Guider Network for Multi-Dual Learning |
| Authors | Wenpeng Hu, Zhengwei Tao, Zhanxing Zhu, Bing Liu, Zhou Lin, Jinwen Ma, Dongyan Zhao, Rui Yan |
| Abstract | A large amount of parallel data is needed to train a strong neural machine translation (NMT) system. This is a major challenge for low-resource languages. Building on recent work on unsupervised and semi-supervised methods, we propose a multi-dual learning framework to improve the performance of NMT by using an almost infinite amount of available monolingual data and some parallel data of other languages. Since our framework involves multiple languages and components, we further propose a timing optimization method that uses reinforcement learning (RL) to optimally schedule the different components in order to avoid imbalanced training. Experimental results demonstrate the validity of our model, and confirm its superiority to existing dual learning methods. |
| Tasks | Machine Translation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1eO9oA5Km |
| https://openreview.net/pdf?id=B1eO9oA5Km | |
| PWC | https://paperswithcode.com/paper/a-guider-network-for-multi-dual-learning |
| Repo | |
| Framework | |
Efficient Meta Learning via Minibatch Proximal Update
| Title | Efficient Meta Learning via Minibatch Proximal Update |
| Authors | Pan Zhou, Xiaotong Yuan, Huan Xu, Shuicheng Yan, Jiashi Feng |
| Abstract | We address the problem of meta-learning which learns a prior over hypothesis from a sample of meta-training tasks for fast adaptation on meta-testing tasks. A particularly simple yet successful paradigm for this research is model-agnostic meta-learning (MAML). Implementation and analysis of MAML, however, can be tricky; first-order approximation is usually adopted to avoid directly computing Hessian matrix but as a result the convergence and generalization guarantees remain largely mysterious for MAML. To remedy this deficiency, in this paper we propose a minibatch proximal update based meta-learning approach for learning to efficient hypothesis transfer. The principle is to learn a prior hypothesis shared across tasks such that the minibatch risk minimization biased regularized by this prior can quickly converge to the optimal hypothesis in each training task. The prior hypothesis training model can be efficiently optimized via SGD with provable convergence guarantees for both convex and non-convex problems. Moreover, we theoretically justify the benefit of the learnt prior hypothesis for fast adaptation to new few-shot learning tasks via minibatch proximal update. Experimental results on several few-shot regression and classification tasks demonstrate the advantages of our method over state-of-the-arts. |
| Tasks | Few-Shot Learning, few-shot regression, Meta-Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8432-efficient-meta-learning-via-minibatch-proximal-update |
| http://papers.nips.cc/paper/8432-efficient-meta-learning-via-minibatch-proximal-update.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-meta-learning-via-minibatch |
| Repo | |
| Framework | |
Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting
| Title | Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting |
| Authors | Jeanne E. Daniel, Willie Brink, Ryan Eloff, Charles Copley |
| Abstract | We discuss ongoing work into automating a multilingual digital helpdesk service available via text messaging to pregnant and breastfeeding mothers in South Africa. Our anonymized dataset consists of short informal questions, often in low-resource languages, with unreliable language labels, spelling errors and code-mixing, as well as template answers with some inconsistencies. We explore cross-lingual word embeddings, and train parametric and non-parametric models on 90K samples for answer selection from a set of 126 templates. Preliminary results indicate that LSTMs trained end-to-end perform best, with a test accuracy of 62.13{%} and a recall@5 of 89.56{%}, and demonstrate that we can accelerate response time by several orders of magnitude. |
| Tasks | Answer Selection, Question Answering, Word Embeddings |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1090/ |
| https://www.aclweb.org/anthology/P19-1090 | |
| PWC | https://paperswithcode.com/paper/towards-automating-healthcare-question |
| Repo | |
| Framework | |
Phrase-Based Attentions
| Title | Phrase-Based Attentions |
| Authors | Phi Xuan Nguyen, Shafiq Joty |
| Abstract | Most state-of-the-art neural machine translation systems, despite being different in architectural skeletons (e.g., recurrence, convolutional), share an indispensable feature: the Attention. However, most existing attention methods are token-based and ignore the importance of phrasal alignments, the key ingredient for the success of phrase-based statistical machine translation. In this paper, we propose novel phrase-based attention methods to model n-grams of tokens as attention entities. We incorporate our phrase-based attentions into the recently proposed Transformer network, and demonstrate that our approach yields improvements of 1.3 BLEU for English-to-German and 0.5 BLEU for German-to-English translation tasks, and 1.75 and 1.35 BLEU points in English-to-Russian and Russian-to-English translation tasks on WMT newstest2014 using WMT’16 training data. |
| Tasks | Machine Translation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1xN5oA5tm |
| https://openreview.net/pdf?id=r1xN5oA5tm | |
| PWC | https://paperswithcode.com/paper/phrase-based-attentions |
| Repo | |
| Framework | |
GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation
| Title | GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation |
| Authors | Xinhong Ma, Tianzhu Zhang, Changsheng Xu |
| Abstract | To bridge source and target domains for domain adaptation, there are three important types of information including data structure, domain label, and class label. Most existing domain adaptation approaches exploit only one or two types of this information and cannot make them complement and enhance each other. Different from existing methods, we propose an end-to-end Graph Convolutional Adversarial Network (GCAN) for unsupervised domain adaptation by jointly modeling data structure, domain label, and class label in a unified deep framework. The proposed GCAN model enjoys several merits. First, to the best of our knowledge, this is the first work to model the three kinds of information jointly in a deep model for unsupervised domain adaptation. Second, the proposed model has designed three effective alignment mechanisms including structure-aware alignment, domain alignment, and class centroid alignment, which can learn domain-invariant and semantic representations effectively to reduce the domain discrepancy for domain adaptation. Extensive experimental results on five standard benchmarks demonstrate that the proposed GCAN algorithm performs favorably against state-of-the-art unsupervised domain adaptation methods. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Ma_GCAN_Graph_Convolutional_Adversarial_Network_for_Unsupervised_Domain_Adaptation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Ma_GCAN_Graph_Convolutional_Adversarial_Network_for_Unsupervised_Domain_Adaptation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/gcan-graph-convolutional-adversarial-network |
| Repo | |
| Framework | |
Reducing Word Omission Errors in Neural Machine Translation: A Contrastive Learning Approach
| Title | Reducing Word Omission Errors in Neural Machine Translation: A Contrastive Learning Approach |
| Authors | Zonghan Yang, Yong Cheng, Yang Liu, Maosong Sun |
| Abstract | While neural machine translation (NMT) has achieved remarkable success, NMT systems are prone to make word omission errors. In this work, we propose a contrastive learning approach to reducing word omission errors in NMT. The basic idea is to enable the NMT model to assign a higher probability to a ground-truth translation and a lower probability to an erroneous translation, which is automatically constructed from the ground-truth translation by omitting words. We design different types of negative examples depending on the number of omitted words, word frequency, and part of speech. Experiments on Chinese-to-English, German-to-English, and Russian-to-English translation tasks show that our approach is effective in reducing word omission errors and achieves better translation performance than three baseline methods. |
| Tasks | Machine Translation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1623/ |
| https://www.aclweb.org/anthology/P19-1623 | |
| PWC | https://paperswithcode.com/paper/reducing-word-omission-errors-in-neural |
| Repo | |
| Framework | |
A quantifiable testing of global translational invariance in Convolutional and Capsule Networks
| Title | A quantifiable testing of global translational invariance in Convolutional and Capsule Networks |
| Authors | Weikai Qi |
| Abstract | We design simple and quantifiable testing of global translation-invariance in deep learning models trained on the MNIST dataset. Experiments on convolutional and capsules neural networks show that both models have poor performance in dealing with global translation-invariance; however, the performance improved by using data augmentation. Although the capsule network is better on the MNIST testing dataset, the convolutional neural network generally has better performance on the translation-invariance. |
| Tasks | Data Augmentation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJlgOjAqYQ |
| https://openreview.net/pdf?id=SJlgOjAqYQ | |
| PWC | https://paperswithcode.com/paper/a-quantifiable-testing-of-global |
| Repo | |
| Framework | |
Term-Based Extraction of Medical Information: Pre-Operative Patient Education Use Case
| Title | Term-Based Extraction of Medical Information: Pre-Operative Patient Education Use Case |
| Authors | Martin Wolf, Volha Petukhova, Dietrich Klakow |
| Abstract | The processing of medical information is not a trivial task for medical non-experts. The paper presents an artificial assistant designed to facilitate a reliable access to medical online contents. Interactions are modelled as doctor-patient Question Answering sessions within a pre-operative patient education scenario where the system addresses patient{'}s information needs explaining medical events and procedures. This implies an accurate medical information extraction from and reasoning with available medical knowledge and large amounts of unstructured multilingual online data. Bridging the gap between medical knowledge and data, we explore a language-agnostic approach to medical concepts mining from the standard terminologies, and the data-driven collection of the corresponding seed terms in a distant supervision setting for German. Experimenting with different terminologies, features and term matching strategies, we achieved a promising F-score of 0.91 on the medical term extraction task. The concepts and terms are used to search and retrieve definitions from the verified online free resources. The proof-of-concept definition retrieval system is designed and evaluated showing promising results, acceptable by humans in 92{%} of cases. |
| Tasks | Question Answering |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1154/ |
| https://www.aclweb.org/anthology/R19-1154 | |
| PWC | https://paperswithcode.com/paper/term-based-extraction-of-medical-information |
| Repo | |
| Framework | |
Deep Learning for Natural Language Inference
| Title | Deep Learning for Natural Language Inference |
| Authors | Samuel Bowman, Xiaodan Zhu |
| Abstract | This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development, cutting-edge deep learning models, and highlights from recent research on using NLI to understand capabilities and limits of deep learning models for language understanding and reasoning. |
| Tasks | Natural Language Inference |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-5002/ |
| https://www.aclweb.org/anthology/N19-5002 | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-natural-language-inference |
| Repo | |
| Framework | |
How Pre-trained Word Representations Capture Commonsense Physical Comparisons
| Title | How Pre-trained Word Representations Capture Commonsense Physical Comparisons |
| Authors | Pranav Goel, Shi Feng, Jordan Boyd-Graber |
| Abstract | Understanding common sense is important for effective natural language reasoning. One type of common sense is how two objects compare on physical properties such as size and weight: e.g., {`}is a house bigger than a person?{'}. We probe whether pre-trained representations capture comparisons and find they, in fact, have higher accuracy than previous approaches. They also generalize to comparisons involving objects not seen during training. We investigate \textit{how} such comparisons are made: models learn a consistent ordering over all the objects in the comparisons. Probing models have significantly higher accuracy than those baseline models which use dataset artifacts: e.g., memorizing some words are larger than any other word. | |
| Tasks | Common Sense Reasoning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6016/ |
| https://www.aclweb.org/anthology/D19-6016 | |
| PWC | https://paperswithcode.com/paper/how-pre-trained-word-representations-capture |
| Repo | |
| Framework | |
Normalization Gradients are Least-squares Residuals
| Title | Normalization Gradients are Least-squares Residuals |
| Authors | Yi Liu |
| Abstract | Batch Normalization (BN) and its variants have seen widespread adoption in the deep learning community because they improve the training of deep neural networks. Discussions of why this normalization works so well remain unsettled. We make explicit the relationship between ordinary least squares and partial derivatives computed when back-propagating through BN. We recast the back-propagation of BN as a least squares fit, which zero-centers and decorrelates partial derivatives from normalized activations. This view, which we term {\em gradient-least-squares}, is an extensible and arithmetically accurate description of BN. To further explore this perspective, we motivate, interpret, and evaluate two adjustments to BN. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BkMq0oRqFQ |
| https://openreview.net/pdf?id=BkMq0oRqFQ | |
| PWC | https://paperswithcode.com/paper/normalization-gradients-are-least-squares |
| Repo | |
| Framework | |
Improving full-text search results on d'uchas.ie using language technology
| Title | Improving full-text search results on d'uchas.ie using language technology |
| Authors | Brian {'O} Raghallaigh, Kevin Scannell, Meghan Dowling |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6909/ |
| https://www.aclweb.org/anthology/W19-6909 | |
| PWC | https://paperswithcode.com/paper/improving-full-text-search-results-on |
| Repo | |
| Framework | |
