Paper Group ANR 545
Proceedings of the twelfth Workshop on Answer Set Programming and Other Computing Paradigms 2019. Perspective Taking in Deep Reinforcement Learning Agents. Unsupervised Context Rewriting for Open Domain Conversation. Deep Learning For Experimental Hybrid Terrestrial and Satellite Interference Management. A^2-Net: Molecular Structure Estimation from …
Proceedings of the twelfth Workshop on Answer Set Programming and Other Computing Paradigms 2019
| Title | Proceedings of the twelfth Workshop on Answer Set Programming and Other Computing Paradigms 2019 |
| Authors | Jorge Fandinno, Johannes Fichte |
| Abstract | This is the Proceedings of the twelfth Workshop on Answer Set Programming and Other Computing Paradigms (ASPOCP) 2019, which was held in Philadelphia, USA, June 3rd , 2019. |
| Tasks | |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1912.09211v1 |
| https://arxiv.org/pdf/1912.09211v1.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-twelfth-workshop-on-answer |
| Repo | |
| Framework | |
Perspective Taking in Deep Reinforcement Learning Agents
| Title | Perspective Taking in Deep Reinforcement Learning Agents |
| Authors | Aqeel Labash, Jaan Aru, Tambet Matiisen, Ardi Tampuu, Raul Vicente |
| Abstract | Perspective taking is the ability to take the point of view of another agent. This skill is not unique to humans as it is also displayed by other animals like chimpanzees. It is an essential ability for efficient social interactions, including cooperation, competition, and communication. In this work, we present our progress toward building artificial agents with such abilities. To this end we implemented a perspective taking task that was inspired by experiments done with chimpanzees. We show that agents controlled by artificial neural networks can learn via reinforcement learning to pass simple tests that require perspective taking capabilities. In particular, this ability is more readily learned when the agent has allocentric information about the objects in the environment. Building artificial agents with perspective taking ability will help to reverse engineer how computations underlying theory of mind might be accomplished in our brains. |
| Tasks | |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01851v1 |
| https://arxiv.org/pdf/1907.01851v1.pdf | |
| PWC | https://paperswithcode.com/paper/perspective-taking-in-deep-reinforcement |
| Repo | |
| Framework | |
Unsupervised Context Rewriting for Open Domain Conversation
| Title | Unsupervised Context Rewriting for Open Domain Conversation |
| Authors | Kun Zhou, Kai Zhang, Yu Wu, Shujie Liu, Jingsong Yu |
| Abstract | Context modeling has a pivotal role in open domain conversation. Existing works either use heuristic methods or jointly learn context modeling and response generation with an encoder-decoder framework. This paper proposes an explicit context rewriting method, which rewrites the last utterance by considering context history. We leverage pseudo-parallel data and elaborate a context rewriting network, which is built upon the CopyNet with the reinforcement learning method. The rewritten utterance is beneficial to candidate retrieval, explainable context modeling, as well as enabling to employ a single-turn framework to the multi-turn scenario. The empirical results show that our model outperforms baselines in terms of the rewriting quality, the multi-turn response generation, and the end-to-end retrieval-based chatbots. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08282v2 |
| https://arxiv.org/pdf/1910.08282v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-context-rewriting-for-open |
| Repo | |
| Framework | |
Deep Learning For Experimental Hybrid Terrestrial and Satellite Interference Management
| Title | Deep Learning For Experimental Hybrid Terrestrial and Satellite Interference Management |
| Authors | Pol Henarejos, Miguel Ángel Vázquez, Ana Isabel Pérez-Neira |
| Abstract | Interference Management is a vast topic present in many disciplines. The majority of wireless standards suffer the drawback of interference intrusion and the network efficiency drop due to that. Traditionally, interference management has been addressed by proposing signal processing techniques that minimize their effects locally. However, the fast evolution of future communications makes difficult to adapt to new era. In this paper we propose the use of Deep Learning techniques to present a compact system for interference management. In particular, we describe two subsystems capable to detect the presence of interference, even in high Signal to Interference Ratio (SIR), and interference classification in several radio standards. Finally, we present results based on real signals captured from terrestrial and satellite networks and the conclusions unveil the courageous future of AI and wireless communications. |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.03012v1 |
| https://arxiv.org/pdf/1906.03012v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-experimental-hybrid |
| Repo | |
| Framework | |
A^2-Net: Molecular Structure Estimation from Cryo-EM Density Volumes
| Title | A^2-Net: Molecular Structure Estimation from Cryo-EM Density Volumes |
| Authors | Kui Xu, Zhe Wang, Jiangping Shi, Hongsheng Li, Qiangfeng Cliff Zhang |
| Abstract | Constructing of molecular structural models from Cryo-Electron Microscopy (Cryo-EM) density volumes is the critical last step of structure determination by Cryo-EM technologies. Methods have evolved from manual construction by structural biologists to perform 6D translation-rotation searching, which is extremely compute-intensive. In this paper, we propose a learning-based method and formulate this problem as a vision-inspired 3D detection and pose estimation task. We develop a deep learning framework for amino acid determination in a 3D Cryo-EM density volume. We also design a sequence-guided Monte Carlo Tree Search (MCTS) to thread over the candidate amino acids to form the molecular structure. This framework achieves 91% coverage on our newly proposed dataset and takes only a few minutes for a typical structure with a thousand amino acids. Our method is hundreds of times faster and several times more accurate than existing automated solutions without any human intervention. |
| Tasks | Pose Estimation |
| Published | 2019-01-03 |
| URL | http://arxiv.org/abs/1901.00785v3 |
| http://arxiv.org/pdf/1901.00785v3.pdf | |
| PWC | https://paperswithcode.com/paper/a2-net-molecular-structure-estimation-from |
| Repo | |
| Framework | |
Localizing Adverts in Outdoor Scenes
| Title | Localizing Adverts in Outdoor Scenes |
| Authors | Soumyabrata Dev, Murhaf Hossari, Matthew Nicholson, Killian McCabe, Atul Nautiyal, Clare Conran, Jian Tang, Wei Xu, François Pitié |
| Abstract | Online videos have witnessed an unprecedented growth over the last decade, owing to wide range of content creation. This provides the advertisement and marketing agencies plethora of opportunities for targeted advertisements. Such techniques involve replacing an existing advertisement in a video frame, with a new advertisement. However, such post-processing of online videos is mostly done manually by video editors. This is cumbersome and time-consuming. In this paper, we propose DeepAds – a deep neural network, based on the simple encoder-decoder architecture, that can accurately localize the position of an advert in a video frame. Our approach of localizing billboards in outdoor scenes using neural nets, is the first of its kind, and achieves the best performance. We benchmark our proposed method with other semantic segmentation algorithms, on a public dataset of outdoor scenes with manually annotated billboard binary maps. |
| Tasks | Semantic Segmentation |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02106v1 |
| https://arxiv.org/pdf/1905.02106v1.pdf | |
| PWC | https://paperswithcode.com/paper/localizing-adverts-in-outdoor-scenes |
| Repo | |
| Framework | |
FetusMap: Fetal Pose Estimation in 3D Ultrasound
| Title | FetusMap: Fetal Pose Estimation in 3D Ultrasound |
| Authors | Xin Yang, Wenlong Shi, Haoran Dou, Jikuan Qian, Yi Wang, Wufeng Xue, Shengli Li, Dong Ni, Pheng-Ann Heng |
| Abstract | The 3D ultrasound (US) entrance inspires a multitude of automated prenatal examinations. However, studies about the structuralized description of the whole fetus in 3D US are still rare. In this paper, we propose to estimate the 3D pose of fetus in US volumes to facilitate its quantitative analyses in global and local scales. Given the great challenges in 3D US, including the high volume dimension, poor image quality, symmetric ambiguity in anatomical structures and large variations of fetal pose, our contribution is three-fold. (i) This is the first work about 3D pose estimation of fetus in the literature. We aim to extract the skeleton of whole fetus and assign different segments/joints with correct torso/limb labels. (ii) We propose a self-supervised learning (SSL) framework to finetune the deep network to form visually plausible pose predictions. Specifically, we leverage the landmark-based registration to effectively encode case-adaptive anatomical priors and generate evolving label proxy for supervision. (iii) To enable our 3D network perceive better contextual cues with higher resolution input under limited computing resource, we further adopt the gradient check-pointing (GCP) strategy to save GPU memory and improve the prediction. Extensively validated on a large 3D US dataset, our method tackles varying fetal poses and achieves promising results. 3D pose estimation of fetus has potentials in serving as a map to provide navigation for many advanced studies. |
| Tasks | 3D Pose Estimation, Pose Estimation |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.04935v1 |
| https://arxiv.org/pdf/1910.04935v1.pdf | |
| PWC | https://paperswithcode.com/paper/fetusmap-fetal-pose-estimation-in-3d |
| Repo | |
| Framework | |
Low-cost LIDAR based Vehicle Pose Estimation and Tracking
| Title | Low-cost LIDAR based Vehicle Pose Estimation and Tracking |
| Authors | Chen Fu, Chiyu Dong, Xiao Zhang, John M. Dolan |
| Abstract | Detecting surrounding vehicles by low-cost LIDAR has been drawing enormous attention. In low-cost LIDAR, vehicles present a multi-layer L-Shape. Based on our previous optimization/criteria-based L-Shape fitting algorithm, we here propose a data-driven and model-based method for robust vehicle segmentation and tracking. The new method uses T-linkage RANSAC to take a limited amount of noisy data and performs a robust segmentation for a moving car against noise. Compared with our previous method, T-Linkage RANSAC is more tolerant of observation uncertainties, i.e., the number of sides of the target being observed, and gets rid of the L-Shape assumption. In addition, a vehicle tracking system with Multi-Model Association (MMA) is built upon the segmentation result, which provides smooth trajectories of tracked objects. A manually labeled dataset from low-cost multi-layer LIDARs for validation will also be released with the paper. Experiments on the dataset show that the new approach outperforms previous ones based on multiple criteria. The new algorithm can also run in real-time. |
| Tasks | Pose Estimation |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01701v1 |
| https://arxiv.org/pdf/1910.01701v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-cost-lidar-based-vehicle-pose-estimation |
| Repo | |
| Framework | |
TFCheck : A TensorFlow Library for Detecting Training Issues in Neural Network Programs
| Title | TFCheck : A TensorFlow Library for Detecting Training Issues in Neural Network Programs |
| Authors | Houssem Ben Braiek, Foutse Khomh |
| Abstract | The increasing inclusion of Machine Learning (ML) models in safety critical systems like autonomous cars have led to the development of multiple model-based ML testing techniques. One common denominator of these testing techniques is their assumption that training programs are adequate and bug-free. These techniques only focus on assessing the performance of the constructed model using manually labeled data or automatically generated data. However, their assumptions about the training program are not always true as training programs can contain inconsistencies and bugs. In this paper, we examine training issues in ML programs and propose a catalog of verification routines that can be used to detect the identified issues, automatically. We implemented the routines in a Tensorflow-based library named TFCheck. Using TFCheck, practitioners can detect the aforementioned issues automatically. To assess the effectiveness of TFCheck, we conducted a case study with real-world, mutants, and synthetic training programs. Results show that TFCheck can successfully detect training issues in ML code implementations. |
| Tasks | |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02562v1 |
| https://arxiv.org/pdf/1909.02562v1.pdf | |
| PWC | https://paperswithcode.com/paper/tfcheck-a-tensorflow-library-for-detecting |
| Repo | |
| Framework | |
Online Learning and Planning in Partially Observable Domains without Prior Knowledge
| Title | Online Learning and Planning in Partially Observable Domains without Prior Knowledge |
| Authors | Yunlong Liu, Jianyang Zheng |
| Abstract | How an agent can act optimally in stochastic, partially observable domains is a challenge problem, the standard approach to address this issue is to learn the domain model firstly and then based on the learned model to find the (near) optimal policy. However, offline learning the model often needs to store the entire training data and cannot utilize the data generated in the planning phase. Furthermore, current research usually assumes the learned model is accurate or presupposes knowledge of the nature of the unobservable part of the world. In this paper, for systems with discrete settings, with the benefits of Predictive State Representations~(PSRs), a model-based planning approach is proposed where the learning and planning phases can both be executed online and no prior knowledge of the underlying system is required. Experimental results show compared to the state-of-the-art approaches, our algorithm achieved a high level of performance with no prior knowledge provided, along with theoretical advantages of PSRs. Source code is available at https://github.com/DMU-XMU/PSR-MCTS-Online. |
| Tasks | |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.05130v1 |
| https://arxiv.org/pdf/1906.05130v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-learning-and-planning-in-partially |
| Repo | |
| Framework | |
Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-Play
| Title | Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-Play |
| Authors | Sourabh Majumdar, Serra Sinem Tekiroglu, Marco Guerini |
| Abstract | End-to-end neural approaches are becoming increasingly common in conversational scenarios due to their promising performances when provided with sufficient amount of data. In this paper, we present a novel methodology to address the interpretability of neural approaches in such scenarios by creating challenge datasets using dialogue self-play over multiple tasks/intents. Dialogue self-play allows generating large amount of synthetic data; by taking advantage of the complete control over the generation process, we show how neural approaches can be evaluated in terms of unseen dialogue patterns. We propose several out-of-pattern test cases each of which introduces a natural and unexpected user utterance phenomenon. As a proof of concept, we built a single and a multiple memory network, and show that these two architectures have diverse performances depending on the peculiar dialogue patterns. |
| Tasks | |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07357v1 |
| https://arxiv.org/pdf/1910.07357v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-challenge-datasets-for-task |
| Repo | |
| Framework | |
Agent Prioritization for Autonomous Navigation
| Title | Agent Prioritization for Autonomous Navigation |
| Authors | Khaled S. Refaat, Kai Ding, Natalia Ponomareva, Stéphane Ross |
| Abstract | In autonomous navigation, a planning system reasons about other agents to plan a safe and plausible trajectory. Before planning starts, agents are typically processed with computationally intensive models for recognition, tracking, motion estimation and prediction. With limited computational resources and a large number of agents to process in real time, it becomes important to efficiently rank agents according to their impact on the decision making process. This allows spending more time processing the most important agents. We propose a system to rank agents around an autonomous vehicle (AV) in real time. We automatically generate a ranking data set by running the planner in simulation on real-world logged data, where we can afford to run more accurate and expensive models on all the agents. The causes of various planner actions are logged and used for assigning ground truth importance scores. The generated data set can be used to learn ranking models. In particular, we show the utility of combining learned features, via a convolutional neural network, with engineered features designed to capture domain knowledge. We show the benefits of various design choices experimentally. When tested on real AVs, our system demonstrates the capability of understanding complex driving situations. |
| Tasks | Autonomous Navigation, Decision Making, Motion Estimation |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08792v1 |
| https://arxiv.org/pdf/1909.08792v1.pdf | |
| PWC | https://paperswithcode.com/paper/agent-prioritization-for-autonomous |
| Repo | |
| Framework | |
Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise
| Title | Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise |
| Authors | Chris Larson, Tarek Lahlou, Diana Mingels, Zachary Kulis, Erik Mueller |
| Abstract | Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT) and Text-to-Speech (TTS) systems, the question remains how to best leverage state-of-the-art language models (which capture rich semantic features, but are trained on only written text) on inputs with ASR errors. In this paper, we present Telephonetic, a data augmentation framework that helps robustify language model features to ASR corrupted inputs. To capture phonetic alterations, we employ a character-level language model trained using probabilistic masking. Phonetic augmentations are generated in two stages: a TTS encoder (Tacotron 2, WaveGlow) and a STT decoder (DeepSpeech). Similarly, semantic perturbations are produced by sampling from nearby words in an embedding space, which is computed using the BERT language model. Words are selected for augmentation according to a hierarchical grammar sampling strategy. Telephonetic is evaluated on the Penn Treebank (PTB) corpus, and demonstrates its effectiveness as a bootstrapping technique for transferring neural language models to the speech domain. Notably, our language model achieves a test perplexity of 37.49 on PTB, which to our knowledge is state-of-the-art among models trained only on PTB. |
| Tasks | Data Augmentation, Language Modelling |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05678v1 |
| https://arxiv.org/pdf/1906.05678v1.pdf | |
| PWC | https://paperswithcode.com/paper/telephonetic-making-neural-language-models |
| Repo | |
| Framework | |
Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning
| Title | Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning |
| Authors | Daniele Bonadiman, Anjishnu Kumar, Arpit Mittal |
| Abstract | The goal of a Question Paraphrase Retrieval (QPR) system is to retrieve equivalent questions that result in the same answer as the original question. Such a system can be used to understand and answer rare and noisy reformulations of common questions by mapping them to a set of canonical forms. This has large-scale applications for community Question Answering (cQA) and open-domain spoken language question answering systems. In this paper we describe a new QPR system implemented as a Neural Information Retrieval (NIR) system consisting of a neural network sentence encoder and an approximate k-Nearest Neighbour index for efficient vector retrieval. We also describe our mechanism to generate an annotated dataset for question paraphrase retrieval experiments automatically from question-answer logs via distant supervision. We show that the standard loss function in NIR, triplet loss, does not perform well with noisy labels. We propose smoothed deep metric loss (SDML) and with our experiments on two QPR datasets we show that it significantly outperforms triplet loss in the noisy label setting. |
| Tasks | Community Question Answering, Information Retrieval, Metric Learning, Question Answering |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12786v1 |
| https://arxiv.org/pdf/1905.12786v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-question-paraphrase-retrieval |
| Repo | |
| Framework | |
Non-Autoregressive Video Captioning with Iterative Refinement
| Title | Non-Autoregressive Video Captioning with Iterative Refinement |
| Authors | Bang Yang, Fenglin Liu, Yuexian Zou |
| Abstract | Existing state-of-the-art autoregressive video captioning methods (ARVC) generate captions sequentially, which leads to low inference efficiency. Moreover, the word-by-word generation process does not fit human intuition of comprehending video contents (i.e., first capturing the salient visual information and then generating well-organized descriptions), resulting in unsatisfied caption diversity. In order to press close to the human manner of comprehending video contents and writing captions, this paper proposes a non-autoregressive video captioning (NAVC) model with iterative refinement. We then further propose to exploit external auxiliary scoring information to assist the iterative refinement process, which can help the model focus on the inappropriate words more accurately. Experimental results on two mainstream benchmarks, i.e., MSVD and MSR-VTT, show that our proposed method generates more felicitous and diverse captions with a generally faster decoding speed, at the cost of up to 5% caption quality compared with the autoregressive counterpart. In particular, the proposal of using auxiliary scoring information not only improves non-autoregressive performance by a large margin, but is also beneficial for the caption diversity. |
| Tasks | Video Captioning |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.12018v3 |
| https://arxiv.org/pdf/1911.12018v3.pdf | |
| PWC | https://paperswithcode.com/paper/non-autoregressive-video-captioning-with |
| Repo | |
| Framework | |
