Paper Group NANR 240
StrokeNet: A Neural Painting Environment. Sample Efficient Imitation Learning for Continuous Control. Amplifying the Neural Power Spectrum. Exploring Graph-Algebraic CCG Combinators for Syntactic-Semantic AMR Parsing. What a difference a pixel makes: An empirical examination of features used by CNNs for categorisation. Joint extraction of entities …
StrokeNet: A Neural Painting Environment
| Title | StrokeNet: A Neural Painting Environment |
| Authors | Ningyuan Zheng, Yifan Jiang, Dingjiang Huang |
| Abstract | We’ve seen tremendous success of image generating models these years. Generating images through a neural network is usually pixel-based, which is fundamentally different from how humans create artwork using brushes. To imitate human drawing, interactions between the environment and the agent is required to allow trials. However, the environment is usually non-differentiable, leading to slow convergence and massive computation. In this paper we try to address the discrete nature of software environment with an intermediate, differentiable simulation. We present StrokeNet, a novel model where the agent is trained upon a well-crafted neural approximation of the painting environment. With this approach, our agent was able to learn to write characters such as MNIST digits faster than reinforcement learning approaches in an unsupervised manner. Our primary contribution is the neural simulation of a real-world environment. Furthermore, the agent trained with the emulated environment is able to directly transfer its skills to real-world software. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJxwDiActX |
| https://openreview.net/pdf?id=HJxwDiActX | |
| PWC | https://paperswithcode.com/paper/strokenet-a-neural-painting-environment |
| Repo | |
| Framework | |
Sample Efficient Imitation Learning for Continuous Control
| Title | Sample Efficient Imitation Learning for Continuous Control |
| Authors | Fumihiro Sasaki, Tetsuya Yohira, Atsuo Kawaguchi |
| Abstract | The goal of imitation learning (IL) is to enable a learner to imitate expert behavior given expert demonstrations. Recently, generative adversarial imitation learning (GAIL) has shown significant progress on IL for complex continuous tasks. However, GAIL and its extensions require a large number of environment interactions during training. In real-world environments, the more an IL method requires the learner to interact with the environment for better imitation, the more training time it requires, and the more damage it causes to the environments and the learner itself. We believe that IL algorithms could be more applicable to real-world problems if the number of interactions could be reduced. In this paper, we propose a model-free IL algorithm for continuous control. Our algorithm is made up mainly three changes to the existing adversarial imitation learning (AIL) methods – (a) adopting off-policy actor-critic (Off-PAC) algorithm to optimize the learner policy, (b) estimating the state-action value using off-policy samples without learning reward functions, and (c) representing the stochastic policy function so that its outputs are bounded. Experimental results show that our algorithm achieves competitive results with GAIL while significantly reducing the environment interactions. |
| Tasks | Continuous Control, Imitation Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BkN5UoAqF7 |
| https://openreview.net/pdf?id=BkN5UoAqF7 | |
| PWC | https://paperswithcode.com/paper/sample-efficient-imitation-learning-for |
| Repo | |
| Framework | |
Amplifying the Neural Power Spectrum
| Title | Amplifying the Neural Power Spectrum |
| Authors | J. Andrew Doyle, Paule-Joanne Toussaint, Alan C. Evans |
| Abstract | We introduce a novel method that employs a parametric model of human electroen-cephalographic (EEG) brain signal power spectra to evaluate cognitive science experiments and test scientific hypotheses. We develop the Neural Power Amplifier (NPA), a data-driven approach to EEG pre-processing that can replace current filtering strategies with a principled method based on combining filters with log-arithmic and Gaussian magnitude responses. Presenting the first time domain evidence to validate an increasingly popular model for neural power spectra, we show that filtering out the 1/f background signal and selecting peaks improves a time-domain decoding experiment for visual stimulus of human faces versus random noise. |
| Tasks | EEG |
| Published | 2019-06-04 |
| URL | https://doi.org/10.1101/659268 |
| https://www.biorxiv.org/content/biorxiv/early/2019/06/04/659268.full.pdf | |
| PWC | https://paperswithcode.com/paper/amplifying-the-neural-power-spectrum |
| Repo | |
| Framework | |
Exploring Graph-Algebraic CCG Combinators for Syntactic-Semantic AMR Parsing
| Title | Exploring Graph-Algebraic CCG Combinators for Syntactic-Semantic AMR Parsing |
| Authors | Sebastian Beschke |
| Abstract | We describe a new approach to semantic parsing based on Combinatory Categorial Grammar (CCG). The grammar{'}s semantic construction operators are defined in terms of a graph algebra, which allows our system to induce a compact CCG lexicon. We introduce an expectation maximisation algorithm which we use to filter our lexicon down to 2500 lexical templates. Our system achieves a semantic triple (Smatch) precision that is competitive with other CCG-based AMR parsing approaches. |
| Tasks | Amr Parsing, Semantic Parsing |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1014/ |
| https://www.aclweb.org/anthology/R19-1014 | |
| PWC | https://paperswithcode.com/paper/exploring-graph-algebraic-ccg-combinators-for |
| Repo | |
| Framework | |
What a difference a pixel makes: An empirical examination of features used by CNNs for categorisation
| Title | What a difference a pixel makes: An empirical examination of features used by CNNs for categorisation |
| Authors | Gaurav Malhotra, Jeffrey Bowers |
| Abstract | Convolutional neural networks (CNNs) were inspired by human vision and, in some settings, achieve a performance comparable to human object recognition. This has lead to the speculation that both systems use similar mechanisms to perform recognition. In this study, we conducted a series of simulations that indicate that there is a fundamental difference between human vision and CNNs: while object recognition in humans relies on analysing shape, CNNs do not have such a shape-bias. We teased apart the type of features selected by the model by modifying the CIFAR-10 dataset so that, in addition to containing objects with shape, the images concurrently contained non-shape features, such as a noise-like mask. When trained on these modified set of images, the model did not show any bias towards selecting shapes as features. Instead it relied on whichever feature allowed it to perform the best prediction – even when this feature was a noise-like mask or a single predictive pixel amongst 50176 pixels. We also found that regularisation methods, such as batch normalisation or Dropout, did not change this behaviour and neither did past or concurrent experience with images from other datasets. |
| Tasks | Object Recognition |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ByePUo05K7 |
| https://openreview.net/pdf?id=ByePUo05K7 | |
| PWC | https://paperswithcode.com/paper/what-a-difference-a-pixel-makes-an-empirical |
| Repo | |
| Framework | |
Joint extraction of entities and overlapping relations using position-attentive sequence labeling
| Title | Joint extraction of entities and overlapping relations using position-attentive sequence labeling |
| Authors | Dai Dai, Xinyan Xiao, Yajuan Lyu, Shan Dou, Qiaoqiao She, Haifeng Wang |
| Abstract | Joint entity and relation extraction is to detect entity and relation using a single model. In this paper, we present a novel unified joint extraction model which directly tags entity and relation labels according to a query word position p, i.e., detecting entity at p, and identifying entities at other positions that have relationship with the former. To this end, we first design a tagging scheme to generate n tag sequences for an n-word sentence. Then a position-attention mechanism is introduced to produce different sentence representations for every query position to model these n tag sequences. In this way, our method can simultaneously extract all entities and their type, as well as all overlapping relations. Experiment results show that our framework performances significantly better on extracting overlapping relations as well as detecting long-range relation, and thus we achieve state-of-the-art performance on two public datasets. |
| Tasks | Joint Entity and Relation Extraction, Relation Extraction |
| Published | 2019-07-17 |
| URL | https://www.aaai.org/ojs/index.php/AAAI/article/view/4591 |
| https://www.aaai.org/ojs/index.php/AAAI/article/view/4591/4469 | |
| PWC | https://paperswithcode.com/paper/joint-extraction-of-entities-and-overlapping |
| Repo | |
| Framework | |
Improving Robustness of Neural Machine Translation with Multi-task Learning
| Title | Improving Robustness of Neural Machine Translation with Multi-task Learning |
| Authors | Shuyan Zhou, Xiangkai Zeng, Yingqi Zhou, Antonios Anastasopoulos, Graham Neubig |
| Abstract | While neural machine translation (NMT) achieves remarkable performance on clean, in-domain text, performance is known to degrade drastically when facing text which is full of typos, grammatical errors and other varieties of noise. In this work, we propose a multi-task learning algorithm for transformer-based MT systems that is more resilient to this noise. We describe our submission to the WMT 2019 Robustness shared task based on this method. Our model achieves a BLEU score of 32.8 on the shared task French to English dataset, which is 7.1 BLEU points higher than the baseline vanilla transformer trained with clean text. |
| Tasks | Machine Translation, Multi-Task Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5368/ |
| https://www.aclweb.org/anthology/W19-5368 | |
| PWC | https://paperswithcode.com/paper/improving-robustness-of-neural-machine |
| Repo | |
| Framework | |
Nuclearity in RST and signals of coherence relations
| Title | Nuclearity in RST and signals of coherence relations |
| Authors | Debopam Das |
| Abstract | We investigate the relationship between the notion of nuclearity as proposed in Rhetorical Structure Theory (RST) and the signalling of coherence relations. RST relations are categorized as either mononuclear (comprising a nucleus and a satellite span) or multinuclear (comprising two or more nuclei spans). We examine how mononuclear relations (e.g., Antithesis, Condition) and multinuclear relations (e.g., Contrast, List) are indicated by relational signals, more particularly by discourse markers (e.g., because, however, if, therefore). We conduct a corpus study, examining the distribution of either type of relations in the RST Discourse Treebank (Carlson et al., 2002) and the distribution of discourse markers for those relations in the RST Signalling Corpus (Das et al., 2015). Our results show that discourse markers are used more often to signal multinuclear relations than mononuclear relations. The findings also suggest a complex relationship between the relation types and syntactic categories of discourse markers (subordinating and coordinating conjunctions). |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2705/ |
| https://www.aclweb.org/anthology/W19-2705 | |
| PWC | https://paperswithcode.com/paper/nuclearity-in-rst-and-signals-of-coherence |
| Repo | |
| Framework | |
A Semantic Cover Approach for Topic Modeling
| Title | A Semantic Cover Approach for Topic Modeling |
| Authors | Rajagopal Venkatesaramani, Doug Downey, Bradley Malin, Yevgeniy Vorobeychik |
| Abstract | We introduce a novel topic modeling approach based on constructing a semantic set cover for clusters of similar documents. Specifically, our approach first clusters documents using their Tf-Idf representation, and then covers each cluster with a set of topic words based on semantic similarity, defined in terms of a word embedding. Computing a topic cover amounts to solving a minimum set cover problem. Our evaluation compares our topic modeling approach to Latent Dirichlet Allocation (LDA) on three metrics: 1) qualitative topic match, measured using evaluations by Amazon Mechanical Turk (MTurk) workers, 2) performance on classification tasks using each topic model as a sparse feature representation, and 3) topic coherence. We find that qualitative judgments significantly favor our approach, the method outperforms LDA on topic coherence, and is comparable to LDA on document classification tasks. |
| Tasks | Document Classification, Semantic Similarity, Semantic Textual Similarity |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1011/ |
| https://www.aclweb.org/anthology/S19-1011 | |
| PWC | https://paperswithcode.com/paper/a-semantic-cover-approach-for-topic-modeling |
| Repo | |
| Framework | |
R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition
| Title | R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition |
| Authors | Quanle Liu, Xiangjiu Che, Mei Bie |
| Abstract | Two-stream network architecture has the ability to capture temporal and spatial features from videos simultaneously and has achieved excellent performance on video action recognition tasks. However, there is a fair amount of redundant information in both temporal and spatial dimensions in videos, which increases the complexity of network learning. To solve this problem, we propose residual spatial-temporal attention network (R-STAN), a feed-forward convolutional neural network using residual learning and spatial-temporal attention mechanism for video action recognition, which makes the network focus more on discriminative temporal and spatial features. In our R-STAN, each stream is constructed by stacking residual spatial-temporal attention blocks (R-STAB), the spatial-temporal attention modules integrated in the residual blocks have the ability to generate attention-aware features along temporal and spatial dimensions, which largely reduce the redundant information. Together with the specific characteristic of residual learning, we are able to construct a very deep network for learning spatial-temporal information in videos. With the layers going deeper, the attention-aware features from the different R-STABs can change adaptively. We validate our R-STAN through a large number of experiments on UCF101 and HMDB51 datasets. Our experiments show that our proposed network combined with residual learning and spatial-temporal attention mechanism contributes substantially to the performance of video action recognition. |
| Tasks | Action Recognition In Videos, Temporal Action Localization |
| Published | 2019-06-19 |
| URL | https://doi.org/10.1109/ACCESS.2019.2923651 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8740848 | |
| PWC | https://paperswithcode.com/paper/r-stan-residual-spatial-temporal-attention |
| Repo | |
| Framework | |
Event Detection with Multi-Order Graph Convolution and Aggregated Attention
| Title | Event Detection with Multi-Order Graph Convolution and Aggregated Attention |
| Authors | Haoran Yan, Xiaolong Jin, Xiangbin Meng, Jiafeng Guo, Xueqi Cheng |
| Abstract | Syntactic relations are broadly used in many NLP tasks. For event detection, syntactic relation representations based on dependency tree can better capture the interrelations between candidate trigger words and related entities than sentence representations. But, existing studies only use first-order syntactic relations (i.e., the arcs) in dependency trees to identify trigger words. For this reason, this paper proposes a new method for event detection, which uses a dependency tree based graph convolution network with aggregative attention to explicitly model and aggregate multi-order syntactic representations in sentences. Experimental comparison with state-of-the-art baselines shows the superiority of the proposed method. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1582/ |
| https://www.aclweb.org/anthology/D19-1582 | |
| PWC | https://paperswithcode.com/paper/event-detection-with-multi-order-graph |
| Repo | |
| Framework | |
MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition
| Title | MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition |
| Authors | Ahmed Mazari, Hichem Sahbi |
| Abstract | Convolutional neural networks are nowadays witnessing a major success in different pattern recognition problems. These learning models were basically designed to handle vectorial data such as images but their extension to non-vectorial and semi-structured data (namely graphs with variable sizes, topology, etc.) remains a major challenge, though a few interesting solutions are currently emerging. In this paper, we introduce MLGCN; a novel spectral Multi-Laplacian Graph Convolutional Network. The main ontribution of this method resides in a new design principle that learns graph-laplacians as convex combinations of other elementary laplacians – each one dedicated to a particular topology of the input graphs. We also introduce a novel pooling operator, on graphs, that proceeds in two steps: context-dependent node expansion is achieved, followed by a global average pooling; the strength of this two-step process resides in its ability to preserve the discrimination power of nodes while achieving permutation invariance. Experiments conducted on SBU and UCF-101 datasets, show the validity of our method for the challenging task of action recognition. Supplementary : https://bit.ly/2ku2lYv |
| Tasks | Action Recognition In Videos, Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2019-09-11 |
| URL | https://bmvc2019.org/wp-content/uploads/papers/1103-paper.pdf |
| https://bmvc2019.org/wp-content/uploads/papers/1103-paper.pdf | |
| PWC | https://paperswithcode.com/paper/mlgcn-multi-laplacian-graph-convolutional |
| Repo | |
| Framework | |
Cross-lingual Transfer Learning for Japanese Named Entity Recognition
| Title | Cross-lingual Transfer Learning for Japanese Named Entity Recognition |
| Authors | Andrew Johnson, Penny Karanasou, Judith Gaspers, Dietrich Klakow |
| Abstract | This work explores cross-lingual transfer learning (TL) for named entity recognition, focusing on bootstrapping Japanese from English. A deep neural network model is adopted and the best combination of weights to transfer is extensively investigated. Moreover, a novel approach is presented that overcomes linguistic differences between this language pair by romanizing a portion of the Japanese input. Experiments are conducted on external datasets, as well as internal large-scale real-world ones. Gains with TL are achieved for all evaluated cases. Finally, the influence on TL of the target dataset size and of the target tagset distribution is further investigated. |
| Tasks | Cross-Lingual Transfer, Named Entity Recognition, Transfer Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2023/ |
| https://www.aclweb.org/anthology/N19-2023 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-transfer-learning-for-japanese |
| Repo | |
| Framework | |
Synthesizing Environment-Aware Activities via Activity Sketches
| Title | Synthesizing Environment-Aware Activities via Activity Sketches |
| Authors | Yuan-Hong Liao, Xavier Puig, Marko Boben, Antonio Torralba, Sanja Fidler |
| Abstract | In order to learn to perform activities from demonstrations or descriptions, agents need to distill what the essence of the given activity is, and how it can be adapted to new environments. In this work, we address the problem: environment-aware program generation. Given a visual demonstration or a description of an activity, we generate program sketches representing the essential instructions and propose a model to flesh these into full programs representing the actions needed to perform the activity under the presented environmental constraints. To this end, we build upon VirtualHome, to create a new dataset VirtualHome-Env, where we collect program sketches to represent activities and match programs with environments that can afford them. Furthermore, we construct a knowledge base to sample realistic environments and another knowledge base to seek out the programs under the sampled environments. Finally, we propose RNN-ResActGraph, a network that generates a program from a given sketch and an environment graph and tracks the changes in the environment induced by the program. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Liao_Synthesizing_Environment-Aware_Activities_via_Activity_Sketches_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Liao_Synthesizing_Environment-Aware_Activities_via_Activity_Sketches_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/synthesizing-environment-aware-activities-via |
| Repo | |
| Framework | |
Learning Actionable Representations with Goal Conditioned Policies
| Title | Learning Actionable Representations with Goal Conditioned Policies |
| Authors | Dibya Ghosh, Abhishek Gupta, Sergey Levine |
| Abstract | Representation learning is a central challenge across a range of machine learning areas. In reinforcement learning, effective and functional representations have the potential to tremendously accelerate learning progress and solve more challenging problems. Most prior work on representation learning has focused on generative approaches, learning representations that capture all the underlying factors of variation in the observation space in a more disentangled or well-ordered manner. In this paper, we instead aim to learn functionally salient representations: representations that are not necessarily complete in terms of capturing all factors of variation in the observation space, but rather aim to capture those factors of variation that are important for decision making – that are “actionable”. These representations are aware of the dynamics of the environment, and capture only the elements of the observation that are necessary for decision making rather than all factors of variation, eliminating the need for explicit reconstruction. We show how these learned representations can be useful to improve exploration for sparse reward problems, to enable long horizon hierarchical reinforcement learning, and as a state representation for learning policies for downstream tasks. We evaluate our method on a number of simulated environments, and compare it to prior methods for representation learning, exploration, and hierarchical reinforcement learning. |
| Tasks | Decision Making, Hierarchical Reinforcement Learning, Representation Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Hye9lnCct7 |
| https://openreview.net/pdf?id=Hye9lnCct7 | |
| PWC | https://paperswithcode.com/paper/learning-actionable-representations-with-goal-1 |
| Repo | |
| Framework | |
