October 20, 2019

3277 words 16 mins read

Paper Group AWR 333

From POS tagging to dependency parsing for biomedical event extraction. Recurrent Deep Embedding Networks for Genotype Clustering and Ethnicity Prediction. Adversarial Logit Pairing. Stories for Images-in-Sequence by using Visual and Narrative Components. On Learning Intrinsic Rewards for Policy Gradient Methods. Pose Flow: Efficient Online Pose Tr …

From POS tagging to dependency parsing for biomedical event extraction


Title	From POS tagging to dependency parsing for biomedical event extraction
Authors	Dat Quoc Nguyen, Karin Verspoor
Abstract	Background: Given the importance of relation or event extraction from biomedical research publications to support knowledge capture and synthesis, and the strong dependency of approaches to this information extraction task on syntactic information, it is valuable to understand which approaches to syntactic processing of biomedical text have the highest performance. Results: We perform an empirical study comparing state-of-the-art traditional feature-based and neural network-based models for two core natural language processing tasks of part-of-speech (POS) tagging and dependency parsing on two benchmark biomedical corpora, GENIA and CRAFT. To the best of our knowledge, there is no recent work making such comparisons in the biomedical context; specifically no detailed analysis of neural models on this data is available. Experimental results show that in general, the neural models outperform the feature-based models on two benchmark biomedical corpora GENIA and CRAFT. We also perform a task-oriented evaluation to investigate the influences of these models in a downstream application on biomedical event extraction, and show that better intrinsic parsing performance does not always imply better extrinsic event extraction performance. Conclusion: We have presented a detailed empirical study comparing traditional feature-based and neural network-based models for POS tagging and dependency parsing in the biomedical context, and also investigated the influence of parser selection for a biomedical event extraction downstream task. Availability of data and material: We make the retrained models available at https://github.com/datquocnguyen/BioPosDep
Tasks	Dependency Parsing, Part-Of-Speech Tagging
Published	2018-08-11
URL	http://arxiv.org/abs/1808.03731v2
PDF	http://arxiv.org/pdf/1808.03731v2.pdf
PWC	https://paperswithcode.com/paper/from-pos-tagging-to-dependency-parsing-for
Repo	https://github.com/datquocnguyen/BioPosDep
Framework	tf

Recurrent Deep Embedding Networks for Genotype Clustering and Ethnicity Prediction


Title	Recurrent Deep Embedding Networks for Genotype Clustering and Ethnicity Prediction
Authors	Md. Rezaul Karim, Michael Cochez, Oya Deniz Beyan, Achille Zappa, Ratnesh Sahay, Stefan Decker, Dietrich-Rebholz Schuhmann
Abstract	The understanding of variations in genome sequences assists us in identifying people who are predisposed to common diseases, solving rare diseases, and finding the corresponding population group of the individuals from a larger population group. Although classical machine learning techniques allow researchers to identify groups (i.e. clusters) of related variables, the accuracy, and effectiveness of these methods diminish for large and high-dimensional datasets such as the whole human genome. On the other hand, deep neural network architectures (the core of deep learning) can better exploit large-scale datasets to build complex models. In this paper, we use the K-means clustering approach for scalable genomic data analysis aiming towards clustering genotypic variants at the population scale. Finally, we train a deep belief network (DBN) for predicting the geographic ethnicity. We used the genotype data from the 1000 Genomes Project, which covers the result of genome sequencing for 2504 individuals from 26 different ethnic origins and comprises 84 million variants. Our experimental results, with a focus on accuracy and scalability, show the effectiveness and superiority compared to the state-of-the-art.
Tasks
Published	2018-05-30
URL	http://arxiv.org/abs/1805.12218v1
PDF	http://arxiv.org/pdf/1805.12218v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-deep-embedding-networks-for
Repo	https://github.com/rezacsedu/Recurrent-Deep-Embedding-Networks
Framework	tf

Adversarial Logit Pairing


Title	Adversarial Logit Pairing
Authors	Harini Kannan, Alexey Kurakin, Ian Goodfellow
Abstract	In this paper, we develop improved techniques for defending against adversarial examples at scale. First, we implement the state of the art version of adversarial training at unprecedented scale on ImageNet and investigate whether it remains effective in this setting - an important open scientific question (Athalye et al., 2018). Next, we introduce enhanced defenses using a technique we call logit pairing, a method that encourages logits for pairs of examples to be similar. When applied to clean examples and their adversarial counterparts, logit pairing improves accuracy on adversarial examples over vanilla adversarial training; we also find that logit pairing on clean examples only is competitive with adversarial training in terms of accuracy on two datasets. Finally, we show that adversarial logit pairing achieves the state of the art defense on ImageNet against PGD white box attacks, with an accuracy improvement from 1.5% to 27.9%. Adversarial logit pairing also successfully damages the current state of the art defense against black box attacks on ImageNet (Tramer et al., 2018), dropping its accuracy from 66.6% to 47.1%. With this new accuracy drop, adversarial logit pairing ties with Tramer et al.(2018) for the state of the art on black box attacks on ImageNet.
Tasks
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06373v1
PDF	http://arxiv.org/pdf/1803.06373v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-logit-pairing
Repo	https://github.com/labsix/adversarial-logit-pairing-analysis
Framework	tf

Stories for Images-in-Sequence by using Visual and Narrative Components


Title	Stories for Images-in-Sequence by using Visual and Narrative Components
Authors	Marko Smilevski, Ilija Lalkovski, Gjorgji Madjarov
Abstract	Recent research in AI is focusing towards generating narrative stories about visual scenes. It has the potential to achieve more human-like understanding than just basic description generation of images- in-sequence. In this work, we propose a solution for generating stories for images-in-sequence that is based on the Sequence to Sequence model. As a novelty, our encoder model is composed of two separate encoders, one that models the behaviour of the image sequence and other that models the sentence-story generated for the previous image in the sequence of images. By using the image sequence encoder we capture the temporal dependencies between the image sequence and the sentence-story and by using the previous sentence-story encoder we achieve a better story flow. Our solution generates long human-like stories that not only describe the visual context of the image sequence but also contains narrative and evaluative language. The obtained results were confirmed by manual human evaluation.
Tasks
Published	2018-05-15
URL	http://arxiv.org/abs/1805.05622v3
PDF	http://arxiv.org/pdf/1805.05622v3.pdf
PWC	https://paperswithcode.com/paper/stories-for-images-in-sequence-by-using
Repo	https://github.com/Pendulibrium/ai-visual-storytelling-seq2seq
Framework	tf

On Learning Intrinsic Rewards for Policy Gradient Methods


Title	On Learning Intrinsic Rewards for Policy Gradient Methods
Authors	Zeyu Zheng, Junhyuk Oh, Satinder Singh
Abstract	In many sequential decision making tasks, it is challenging to design reward functions that help an RL agent efficiently learn behavior that is considered good by the agent designer. A number of different formulations of the reward-design problem, or close variants thereof, have been proposed in the literature. In this paper we build on the Optimal Rewards Framework of Singh et.al. that defines the optimal intrinsic reward function as one that when used by an RL agent achieves behavior that optimizes the task-specifying or extrinsic reward function. Previous work in this framework has shown how good intrinsic reward functions can be learned for lookahead search based planning agents. Whether it is possible to learn intrinsic reward functions for learning agents remains an open problem. In this paper we derive a novel algorithm for learning intrinsic rewards for policy-gradient based learning agents. We compare the performance of an augmented agent that uses our algorithm to provide additive intrinsic rewards to an A2C-based policy learner (for Atari games) and a PPO-based policy learner (for Mujoco domains) with a baseline agent that uses the same policy learners but with only extrinsic rewards. Our results show improved performance on most but not all of the domains.
Tasks	Atari Games, Decision Making, Policy Gradient Methods
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06459v2
PDF	http://arxiv.org/pdf/1804.06459v2.pdf
PWC	https://paperswithcode.com/paper/on-learning-intrinsic-rewards-for-policy
Repo	https://github.com/Hwhitetooth/lirpg
Framework	tf

Pose Flow: Efficient Online Pose Tracking


Title	Pose Flow: Efficient Online Pose Tracking
Authors	Yuliang Xiu, Jiefeng Li, Haoyu Wang, Yinghong Fang, Cewu Lu
Abstract	Multi-person articulated pose tracking in unconstrained videos is an important while challenging problem. In this paper, going along the road of top-down approaches, we propose a decent and efficient pose tracker based on pose flows. First, we design an online optimization framework to build the association of cross-frame poses and form pose flows (PF-Builder). Second, a novel pose flow non-maximum suppression (PF-NMS) is designed to robustly reduce redundant pose flows and re-link temporal disjoint ones. Extensive experiments show that our method significantly outperforms best-reported results on two standard Pose Tracking datasets by 13 mAP 25 MOTA and 6 mAP 3 MOTA respectively. Moreover, in the case of working on detected poses in individual frames, the extra computation of pose tracker is very minor, guaranteeing online 10FPS tracking. Our source codes are made publicly available(https://github.com/YuliangXiu/PoseFlow).
Tasks	Pose Tracking
Published	2018-02-03
URL	http://arxiv.org/abs/1802.00977v2
PDF	http://arxiv.org/pdf/1802.00977v2.pdf
PWC	https://paperswithcode.com/paper/pose-flow-efficient-online-pose-tracking
Repo	https://github.com/YuliangXiu/PoseFlow
Framework	pytorch

Learning to Compose Dynamic Tree Structures for Visual Contexts


Title	Learning to Compose Dynamic Tree Structures for Visual Contexts
Authors	Kaihua Tang, Hanwang Zhang, Baoyuan Wu, Wenhan Luo, Wei Liu
Abstract	We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A. Our visual context tree model, dubbed VCTree, has two key advantages over existing structured object representations including chains and fully-connected graphs: 1) The efficient and expressive binary tree encodes the inherent parallel/hierarchical relationships among objects, e.g., “clothes” and “pants” are usually co-occur and belong to “person”; 2) the dynamic structure varies from image to image and task to task, allowing more content-/task-specific message passing among objects. To construct a VCTree, we design a score function that calculates the task-dependent validity between each object pair, and the tree is the binary version of the maximum spanning tree from the score matrix. Then, visual contexts are encoded by bidirectional TreeLSTM and decoded by task-specific models. We develop a hybrid learning procedure which integrates end-task supervised learning and the tree structure reinforcement learning, where the former’s evaluation result serves as a self-critic for the latter’s structure exploration. Experimental results on two benchmarks, which require reasoning over contexts: Visual Genome for scene graph generation and VQA2.0 for visual Q&A, show that VCTree outperforms state-of-the-art results while discovering interpretable visual context structures.
Tasks	Graph Generation, Scene Graph Generation, Visual Question Answering, Visual Reasoning
Published	2018-12-05
URL	http://arxiv.org/abs/1812.01880v1
PDF	http://arxiv.org/pdf/1812.01880v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-compose-dynamic-tree-structures
Repo	https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch
Framework	pytorch

Environmental Sound Recognition using Masked Conditional Neural Networks


Title	Environmental Sound Recognition using Masked Conditional Neural Networks
Authors	Fady Medhat, David Chesmore, John Robinson
Abstract	Neural network based architectures used for sound recognition are usually adapted from other application domains, which may not harness sound related properties. The ConditionaL Neural Network (CLNN) is designed to consider the relational properties across frames in a temporal signal, and its extension the Masked ConditionaL Neural Network (MCLNN) embeds a filterbank behavior within the network, which enforces the network to learn in frequency bands rather than bins. Additionally, it automates the exploration of different feature combinations analogous to handcrafting the optimum combination of features for a recognition task. We applied the MCLNN to the environmental sounds of the ESC-10 dataset. The MCLNN achieved competitive accuracies compared to state-of-the-art convolutional neural networks and hand-crafted attempts.
Tasks
Published	2018-04-08
URL	http://arxiv.org/abs/1804.02665v2
PDF	http://arxiv.org/pdf/1804.02665v2.pdf
PWC	https://paperswithcode.com/paper/environmental-sound-recognition-using-masked
Repo	https://github.com/fadymedhat/MCLNN
Framework	tf

Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition


Title	Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
Authors	Geonmin Kim, Hwaran Lee, Bo-Kyeong Kim, Sang-Hoon Oh, Soo-Young Lee
Abstract	Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of this work is proposing an alternative learning algorithm, called acoustic and adversarial supervision (AAS). AAS makes the enhanced output both maximizing the likelihood of transcription on the pre-trained acoustic model and having general characteristics of clean speech, which improve generalization on unseen noisy speeches. We employ the connectionist temporal classification and the unpaired conditional boundary equilibrium generative adversarial network as the loss function of AAS. AAS is tested on two datasets including additive noise without and with reverberation, Librispeech + DEMAND and CHiME-4. By visualizing the enhanced speech with different loss combinations, we demonstrate the role of each supervision. AAS achieves a lower word error rate than other state-of-the-art methods using the clean speech target in both datasets.
Tasks	Speech Enhancement, Speech Recognition
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02182v1
PDF	http://arxiv.org/pdf/1811.02182v1.pdf
PWC	https://paperswithcode.com/paper/unpaired-speech-enhancement-by-acoustic-and
Repo	https://github.com/gmkim90/AAS_enhancement
Framework	pytorch

Emulating malware authors for proactive protection using GANs over a distributed image visualization of dynamic file behavior


Title	Emulating malware authors for proactive protection using GANs over a distributed image visualization of dynamic file behavior
Authors	Vineeth S. Bhaskara, Debanjan Bhattacharyya
Abstract	Malware authors have always been at an advantage of being able to adversarially test and augment their malicious code, before deploying the payload, using anti-malware products at their disposal. The anti-malware developers and threat experts, on the other hand, do not have such a privilege of tuning anti-malware products against zero-day attacks pro-actively. This allows the malware authors to being a step ahead of the anti-malware products, fundamentally biasing the cat and mouse game played by the two parties. In this paper, we propose a way that would enable machine learning based threat prevention models to bridge that gap by being able to tune against a deep generative adversarial network (GAN), which takes up the role of a malware author and generates new types of malware. The GAN is trained over a reversible distributed RGB image representation of known malware behaviors, encoding the sequence of API call ngrams and the corresponding term frequencies. The generated images represent synthetic malware that can be decoded back to the underlying API call sequence information. The image representation is not only demonstrated as a general technique of incorporating necessary priors for exploiting convolutional neural network architectures for generative or discriminative modeling, but also as a visualization method for easy manual software or malware categorization, by having individual API ngram information distributed across the image space. In addition, we also propose using smart-definitions for detecting malwares based on perceptual hashing of these images. Such hashes are potentially more effective than cryptographic hashes that do not carry any meaningful similarity metric, and hence, do not generalize well.
Tasks
Published	2018-07-19
URL	http://arxiv.org/abs/1807.07525v2
PDF	http://arxiv.org/pdf/1807.07525v2.pdf
PWC	https://paperswithcode.com/paper/emulating-malware-authors-for-proactive
Repo	https://github.com/bsvineethiitg/malwaregan
Framework	tf

Learning Role-based Graph Embeddings


Title	Learning Role-based Graph Embeddings
Authors	Nesreen K. Ahmed, Ryan Rossi, John Boaz Lee, Theodore L. Willke, Rong Zhou, Xiangnan Kong, Hoda Eldardiry
Abstract	Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to vertex identity. In this work, we introduce the Role2Vec framework which uses the flexible notion of attributed random walks, and serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many others that leverage random walks. Our proposed framework enables these methods to be more widely applicable for both transductive and inductive learning as well as for use on graphs with attributes (if available). This is achieved by learning functions that generalize to new nodes and graphs. We show that our proposed framework is effective with an average AUC improvement of 16.55% while requiring on average 853x less space than existing methods on a variety of graphs.
Tasks	Network Embedding
Published	2018-02-07
URL	http://arxiv.org/abs/1802.02896v2
PDF	http://arxiv.org/pdf/1802.02896v2.pdf
PWC	https://paperswithcode.com/paper/learning-role-based-graph-embeddings
Repo	https://github.com/benedekrozemberczki/karateclub
Framework	none

Exploring Author Gender in Book Rating and Recommendation


Title	Exploring Author Gender in Book Rating and Recommendation
Authors	Michael D. Ekstrand, Mucun Tian, Mohammed R. Imran Kazi, Hoda Mehrpouyan, Daniel Kluver
Abstract	Collaborative filtering algorithms find useful patterns in rating and consumption data and exploit these patterns to guide users to good items. Many of the patterns in rating datasets reflect important real-world differences between the various users and items in the data; other patterns may be irrelevant or possibly undesirable for social or ethical reasons, particularly if they reflect undesired discrimination, such as discrimination in publishing or purchasing against authors who are women or ethnic minorities. In this work, we examine the response of collaborative filtering recommender algorithms to the distribution of their input data with respect to a dimension of social concern, namely content creator gender. Using publicly-available book ratings data, we measure the distribution of the genders of the authors of books in user rating profiles and recommendation lists produced from this data. We find that common collaborative filtering algorithms differ in the gender distribution of their recommendation lists, and in the relationship of that output distribution to user profile distribution.
Tasks
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07586v1
PDF	http://arxiv.org/pdf/1808.07586v1.pdf
PWC	https://paperswithcode.com/paper/exploring-author-gender-in-book-rating-and
Repo	https://github.com/BoiseState/bookdata-tools
Framework	none

Off-Policy Deep Reinforcement Learning without Exploration


Title	Off-Policy Deep Reinforcement Learning without Exploration
Authors	Scott Fujimoto, David Meger, Doina Precup
Abstract	Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard off-policy deep reinforcement learning algorithms, such as DQN and DDPG, are incapable of learning with data uncorrelated to the distribution under the current policy, making them ineffective for this fixed batch setting. We introduce a novel class of off-policy algorithms, batch-constrained reinforcement learning, which restricts the action space in order to force the agent towards behaving close to on-policy with respect to a subset of the given data. We present the first continuous control deep reinforcement learning algorithm which can learn effectively from arbitrary, fixed batch data, and empirically demonstrate the quality of its behavior in several tasks.
Tasks	Continuous Control
Published	2018-12-07
URL	https://arxiv.org/abs/1812.02900v3
PDF	https://arxiv.org/pdf/1812.02900v3.pdf
PWC	https://paperswithcode.com/paper/off-policy-deep-reinforcement-learning
Repo	https://github.com/AurelianTactics/bcq_tensorflow
Framework	tf

Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation


Title	Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation
Authors	Francis Grégoire, Philippe Langlais
Abstract	Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora show that we can achieve promising results against a competitive baseline by removing the need of specific feature engineering or additional external resources. To justify the utility of our approach, we extract sentence pairs from Wikipedia articles to train machine translation systems and show significant improvements in translation performance.
Tasks	Feature Engineering, Machine Translation
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05559v2
PDF	http://arxiv.org/pdf/1806.05559v2.pdf
PWC	https://paperswithcode.com/paper/extracting-parallel-sentences-with
Repo	https://github.com/FrancisGregoire/parSentExtract
Framework	tf

RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems


Title	RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
Authors	Hongwei Wang, Fuzheng Zhang, Jialin Wang, Miao Zhao, Wenjie Li, Xing Xie, Minyi Guo
Abstract	To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph as the source of side information. To address the limitations of existing embedding-based and path-based methods for knowledge-graph-aware recommendation, we propose Ripple Network, an end-to-end framework that naturally incorporates the knowledge graph into recommender systems. Similar to actual ripples propagating on the surface of water, Ripple Network stimulates the propagation of user preferences over the set of knowledge entities by automatically and iteratively extending a user’s potential interests along links in the knowledge graph. The multiple “ripples” activated by a user’s historically clicked items are thus superposed to form the preference distribution of the user with respect to a candidate item, which could be used for predicting the final clicking probability. Through extensive experiments on real-world datasets, we demonstrate that Ripple Network achieves substantial gains in a variety of scenarios, including movie, book and news recommendation, over several state-of-the-art baselines.
Tasks	Click-Through Rate Prediction, Recommendation Systems
Published	2018-03-09
URL	http://arxiv.org/abs/1803.03467v4
PDF	http://arxiv.org/pdf/1803.03467v4.pdf
PWC	https://paperswithcode.com/paper/ripplenet-propagating-user-preferences-on-the
Repo	https://github.com/qibinc/RippleNet-PyTorch
Framework	pytorch