Paper Group NAWR 44
SemEval-2019 Task 10: Math Question Answering. ST-LSTM: A Deep Learning Approach Combined Spatio-Temporal Features for Short-Term. Memory-oriented Decoder for Light Field Salient Object Detection. MarginGAN: Adversarial Training in Semi-Supervised Learning. Spatiotemporal Multi-Graph Convolution Networkfor Ride-hailing Demand Forecasting. Effective …
SemEval-2019 Task 10: Math Question Answering
| Title | SemEval-2019 Task 10: Math Question Answering |
| Authors | Mark Hopkins, Ronan Le Bras, Cristian Petrescu-Prahova, Gabriel Stanovsky, Hannaneh Hajishirzi, Rik Koncel-Kedziorski |
| Abstract | We report on the SemEval 2019 task on math question answering. We provided a question set derived from Math SAT practice exams, including 2778 training questions and 1082 test questions. For a significant subset of these questions, we also provided SMT-LIB logical form annotations and an interpreter that could solve these logical forms. Systems were evaluated based on the percentage of correctly answered questions. The top system correctly answered 45{%} of the test questions, a considerable improvement over the 17{%} random guessing baseline. |
| Tasks | Question Answering |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2153/ |
| https://www.aclweb.org/anthology/S19-2153 | |
| PWC | https://paperswithcode.com/paper/semeval-2019-task-10-math-question-answering |
| Repo | https://github.com/allenai/semeval-2019-task-10 |
| Framework | none |
ST-LSTM: A Deep Learning Approach Combined Spatio-Temporal Features for Short-Term
| Title | ST-LSTM: A Deep Learning Approach Combined Spatio-Temporal Features for Short-Term |
| Authors | Qicheng Tang, Mengning Yang, and Ying Yang |
| Abstract | The short-term forecast of rail transit is one of the most essential issues in urban intelligent transportation system (ITS). Accurate forecast result can provide support for the forewarning of flow outburst and enables passengers to make an appropriate travel plan. Therefore, it is significant to develop a more accurate forecast model. Long short-term memory (LSTM) network has been proved to be effective on data with temporal features. However, it cannot process the correlation between time and space in rail transit. As a result, a novel forecast model combining spatio-temporal features based on LSTM network (ST-LSTM) is proposed. Different from other forecast methods, ST-LSTM network uses a new method to extract spatio-temporal features from the data and combines them together as the input. Compared with other conventional models, ST-LSTM network can achieve a better performance in experiments. |
| Tasks | Time Series, Time Series Forecasting |
| Published | 2019-01-21 |
| URL | https://www.hindawi.com/journals/jat/2019/8392592/abs/ |
| https://www.hindawi.com/journals/jat/2019/8392592/abs/ | |
| PWC | https://paperswithcode.com/paper/st-lstm-a-deep-learning-approach-combined |
| Repo | https://github.com/QichengT/ST-LSTM |
| Framework | tf |
Memory-oriented Decoder for Light Field Salient Object Detection
| Title | Memory-oriented Decoder for Light Field Salient Object Detection |
| Authors | Miao Zhang, Jingjing Li, Ji Wei, Yongri Piao, Huchuan Lu |
| Abstract | Light field data have been demonstrated in favor of many tasks in computer vision, but existing works about light field saliency detection still rely on hand-crafted features. In this paper, we present a deep-learning-based method where a novel memory-oriented decoder is tailored for light field saliency detection. Our goal is to deeply explore and comprehensively exploit internal correlation of focal slices for accurate prediction by designing feature fusion and integration mechanisms. The success of our method is demonstrated by achieving the state of the art on three datasets. We present this problem in a way that is accessible to members of the community and provide a large-scale light field dataset that facilitates comparisons across algorithms. The code and dataset will be made publicly available. |
| Tasks | Object Detection, Saliency Detection, Salient Object Detection |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8376-memory-oriented-decoder-for-light-field-salient-object-detection |
| http://papers.nips.cc/paper/8376-memory-oriented-decoder-for-light-field-salient-object-detection.pdf | |
| PWC | https://paperswithcode.com/paper/memory-oriented-decoder-for-light-field |
| Repo | https://github.com/OIPLab-DUT/MoLF |
| Framework | none |
MarginGAN: Adversarial Training in Semi-Supervised Learning
| Title | MarginGAN: Adversarial Training in Semi-Supervised Learning |
| Authors | Jinhao Dong, Tong Lin |
| Abstract | A Margin Generative Adversarial Network (MarginGAN) is proposed for semi-supervised learning problems. Like Triple-GAN, the proposed MarginGAN consists of three components—a generator, a discriminator and a classifier, among which two forms of adversarial training arise. The discriminator is trained as usual to distinguish real examples from fake examples produced by the generator. The new feature is that the classifier attempts to increase the margin of real examples and to decrease the margin of fake examples. On the contrary, the purpose of the generator is yielding realistic and large-margin examples in order to fool the discriminator and the classifier simultaneously. Pseudo labels are used for generated and unlabeled examples in training. Our method is motivated by the success of large-margin classifiers and the recent viewpoint that good semi-supervised learning requires a ``bad’’ GAN. Experiments on benchmark datasets testify that MarginGAN is orthogonal to several state-of-the-art methods, offering improved error rates and shorter training time as well. | |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9231-margingan-adversarial-training-in-semi-supervised-learning |
| http://papers.nips.cc/paper/9231-margingan-adversarial-training-in-semi-supervised-learning.pdf | |
| PWC | https://paperswithcode.com/paper/margingan-adversarial-training-in-semi |
| Repo | https://github.com/xdu-DJhao/MarginGAN |
| Framework | pytorch |
Spatiotemporal Multi-Graph Convolution Networkfor Ride-hailing Demand Forecasting
| Title | Spatiotemporal Multi-Graph Convolution Networkfor Ride-hailing Demand Forecasting |
| Authors | Xu Geng, ∗1 Yaguang Li, ∗2 Leye Wang, 1, 3 Lingyu Zhang, 4 Qiang Yang, 1 Jieping Ye, 4 Yan Liu 2, 4 |
| Abstract | Region-level demand forecasting is an essential task in ridehailing services. Accurate ride-hailing demand forecasting can guide vehicle dispatching, improve vehicle utilization, reduce the wait-time, and mitigate traffic congestion. This task is challenging due to the complicated spatiotemporal dependencies among regions. Existing approaches mainly focus on modeling the Euclidean correlations among spatially adjacent regions while we observe that non-Euclidean pair-wise correlations among possibly distant regions are also critical for accurate forecasting. In this paper, we propose the spatiotemporal multi-graph convolution network (ST-MGCN), a novel deep learning model for ride-hailing demand forecasting. We first encode the non-Euclidean pair-wise correlations among regions into multiple graphs and then explicitly model these correlations using multi-graph convolution. To utilize the global contextual information in modeling the temporal correlation, we further propose contextual gated recurrent neural network which augments recurrent neural network with a contextual-aware gating mechanism to re-weights different historical observations. We evaluate the proposed model on two real-world large scale ride-hailing demand datasets and observe consistent improvement of more than 10% over stateof-the-art baselines. |
| Tasks | Spatio-Temporal Forecasting, Time Series |
| Published | 2019-01-20 |
| URL | http://202.119.24.249/cache/8/03/www-scf.usc.edu/59dc738bd683a198ef69fb39196799d7/aaai19_multi_graph_convolution.pdf |
| http://202.119.24.249/cache/8/03/www-scf.usc.edu/59dc738bd683a198ef69fb39196799d7/aaai19_multi_graph_convolution.pdf | |
| PWC | https://paperswithcode.com/paper/spatiotemporal-multi-graph-convolution |
| Repo | https://github.com/Knowledge-Precipitation-Tribe/ST-MGCN-keras |
| Framework | none |
Effective Dimensionality Reduction for Word Embeddings
| Title | Effective Dimensionality Reduction for Word Embeddings |
| Authors | Vikas Raunak, Vivek Gupta, Florian Metze |
| Abstract | Pre-trained word embeddings are used in several downstream applications as well as for constructing representations for sentences, paragraphs and documents. Recently, there has been an emphasis on improving the pretrained word vectors through post-processing algorithms. One improvement area is reducing the dimensionality of word embeddings. Reducing the size of word embeddings can improve their utility in memory constrained devices, benefiting several real world applications. In this work, we present a novel technique that efficiently combines PCA based dimensionality reduction with a recently proposed post-processing algorithm (Mu and Viswanath, 2018), to construct effective word embeddings of lower dimensions. Empirical evaluations on several benchmarks show that our algorithm efficiently reduces the embedding size while achieving similar or (more often) better performance than original embeddings. We have released the source code along with this paper. |
| Tasks | Dimensionality Reduction, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4328/ |
| https://www.aclweb.org/anthology/W19-4328 | |
| PWC | https://paperswithcode.com/paper/effective-dimensionality-reduction-for-word |
| Repo | https://github.com/vyraun/Half-Size |
| Framework | none |
Better Exploration with Optimistic Actor Critic
| Title | Better Exploration with Optimistic Actor Critic |
| Authors | Kamil Ciosek, Quan Vuong, Robert Loftin, Katja Hofmann |
| Abstract | Actor-critic methods, a type of model-free Reinforcement Learning, have been successfully applied to challenging tasks in continuous control, often achieving state-of-the art performance. However, wide-scale adoption of these methods in real-world domains is made difficult by their poor sample efficiency. We address this problem both theoretically and empirically. On the theoretical side, we identify two phenomena preventing efficient exploration in existing state-of-the-art algorithms such as Soft Actor Critic. First, combining a greedy actor update with a pessimistic estimate of the critic leads to the avoidance of actions that the agent does not know about, a phenomenon we call pessimistic underexploration. Second, current algorithms are directionally uninformed, sampling actions with equal probability in opposite directions from the current mean. This is wasteful, since we typically need actions taken along certain directions much more than others. To address both of these phenomena, we introduce a new algorithm, Optimistic Actor Critic, which approximates a lower and upper confidence bound on the state-action value function. This allows us to apply the principle of optimism in the face of uncertainty to perform directed exploration using the upper bound while still using the lower bound to avoid overestimation. We evaluate OAC in several challenging continuous control tasks, achieving state-of the art sample efficiency. |
| Tasks | Continuous Control, Efficient Exploration |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8455-better-exploration-with-optimistic-actor-critic |
| http://papers.nips.cc/paper/8455-better-exploration-with-optimistic-actor-critic.pdf | |
| PWC | https://paperswithcode.com/paper/better-exploration-with-optimistic-actor-1 |
| Repo | https://github.com/microsoft/oac-explore |
| Framework | pytorch |
