Paper Group NAWR 27
Multi-view to Novel view: Synthesizing Novel Views with Self-Learned Confidence. Community Detection with Graph Neural Networks. Preparing Data from Psychotherapy for Natural Language Processing. Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection. Defining a Sandbox for Responsible AI. CogCompNLP: Your Swiss Army Knife f …
Multi-view to Novel view: Synthesizing Novel Views with Self-Learned Confidence
| Title | Multi-view to Novel view: Synthesizing Novel Views with Self-Learned Confidence |
| Authors | Shao-Hua Sun, Minyoung Huh, Yuan-Hong Liao, Ning Zhang, Joseph J. Lim |
| Abstract | We address the task of multi-view novel view synthesis, where we are interested in synthesizing a target image with an arbitrary camera pose from given source images. We propose an end-to-end trainable framework that learns to exploit multiple viewpoints to synthesize a novel view without any 3D supervision. Specifically, our model consists of a flow prediction module and a pixel generation module to directly leverage information presented in source views as well as hallucinate missing pixels from statistical priors. To merge the predictions produced by the two modules given multi-view source images, we introduce a self-learned confidence aggregation mechanism. We evaluate our model on images rendered from 3D object models as well as real and synthesized scenes. We demonstrate that our model is able to achieve state-of-the-art results as well as progressively improve its predictions when more source images are available. |
| Tasks | Novel View Synthesis |
| Published | 2018-10-05 |
| URL | https://shaohua0116.github.io/Multiview2Novelview/ |
| https://shaohua0116.github.io/Multiview2Novelview/sun2018multiview.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-to-novel-view-synthesizing-novel-1 |
| Repo | https://github.com/shaohua0116/Multiview2Novelview |
| Framework | tf |
Community Detection with Graph Neural Networks
| Title | Community Detection with Graph Neural Networks |
| Authors | Zhengdao Chen, Xiang Li, Joan Bruna |
| Abstract | We study data-driven methods for community detection on graphs, an inverse problem that is typically solved in terms of the spectrum of certain operators or via posterior inference under certain probabilistic graphical models. Focusing on random graph families such as the stochastic block model, recent research has unified both approaches and identified both statistical and computational signal-to-noise detection thresholds. This graph inference task can be recast as a node-wise graph classification problem, and, as such, computational detection thresholds can be translated in terms of learning within appropriate models. We present a novel family of Graph Neural Networks (GNNs) and show that they can reach those detection thresholds in a purely data-driven manner without access to the underlying generative models, and even improve upon current computational thresholds in hard regimes. For that purpose, we propose to augment GNNs with the non-backtracking operator, defined on the line graph of edge adjacencies. We also perform the first analysis of optimization landscape on using GNNs to solve community detection problems, demonstrating that under certain simplifications and assumptions, the loss value at the local minima is close to the loss value at the global minimum/minima. Finally, the resulting model is also tested on real datasets, performing significantly better than previous models. |
| Tasks | Community Detection, Graph Classification |
| Published | 2018-10-25 |
| URL | https://arxiv.org/abs/1705.08415 |
| https://arxiv.org/pdf/1705.08415.pdf | |
| PWC | https://paperswithcode.com/paper/community-detection-with-graph-neural |
| Repo | https://github.com/afansi/multiscalegnn |
| Framework | pytorch |
Preparing Data from Psychotherapy for Natural Language Processing
| Title | Preparing Data from Psychotherapy for Natural Language Processing |
| Authors | Margot Mieskes, Andreas Stiegelmayr |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1458/ |
| https://www.aclweb.org/anthology/L18-1458 | |
| PWC | https://paperswithcode.com/paper/preparing-data-from-psychotherapy-for-natural |
| Repo | https://github.com/mieskes/Paranoia |
| Framework | none |
Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection
| Title | Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection |
| Authors | Fanghua Ye, Chuan Chen, Zibin Zheng |
| Abstract | Community structure is ubiquitous in real-world complex networks. The task of community detection over these networks is of paramount importance in a variety of applications. Recently, nonnegative matrix factorization (NMF) has been widely adopted for community detection due to its great interpretability and its natural fitness for capturing the community membership of nodes. However, the existing NMF-based community detection approaches are shallow methods. They learn the community assignment by mapping the original network to the community membership space directly. Considering the complicated and diversified topology structures of real-world networks, it is highly possible that the mapping between the original network and the community membership space contains rather complex hierarchical information, which cannot be interpreted by classic shallow NMF-based approaches. Inspired by the unique feature representation learning capability of deep autoencoder, we propose a novel model, named Deep Autoencoder-like NMF (DANMF), for community detection. Similar to deep autoencoder, DANMF consists of an encoder component and a decoder component. This architecture empowers DANMF to learn the hierarchical mappings between the original network and the final community assignment with implicit low-to-high level hidden attributes of the original network learnt in the intermediate layers. Thus, DANMF should be better suited to the community detection task. Extensive experiments on benchmark datasets demonstrate that DANMF can achieve better performance than the state-of-the-art NMF-based community detection approaches. |
| Tasks | Community Detection, Local Community Detection, Network Community Partition, Node Classification, Representation Learning |
| Published | 2018-10-22 |
| URL | https://dl.acm.org/citation.cfm?id=3271697 |
| https://smartyfh.com/Documents/18DANMF.pdf | |
| PWC | https://paperswithcode.com/paper/deep-autoencoder-like-nonnegative-matrix |
| Repo | https://github.com/benedekrozemberczki/karateclub |
| Framework | none |
Defining a Sandbox for Responsible AI
| Title | Defining a Sandbox for Responsible AI |
| Authors | Shaun C. D’Souza, Bhavin Mehta |
| Abstract | Technology evolution present a unique set of challenges around the governance and ethics of the technology. These questions have dodged human civilization since the invention of the wheel. With every iteration of our journey we have to reevaluate our role in the larger planet. The human is a social animal. Technology is designed to augment our human lives and on occasion despite our best efforts can find its place in the wrong hands. This is no more real today with the advent of Artificial intelligence where we have given machines a cognition enabling them to function in more human centric roles. While this is not the first time that we have faced this future, it is important to take cognizance of the broader issues around the ethics and governance that are prevalent today in what are early days in an industry with a smaller number of large technology players. Like all our predecessor technologies through to today yet again we are dealing with a mortal creation that comes with an off switch and lesser divine origins. The human mind continues to question the singularity and what is to be the theory of everything. In this paper we explore some of the macro nuances centered around human actors. |
| Tasks | |
| Published | 2018-09-25 |
| URL | https://ssrn.com/abstract=3255075 |
| https://papers.ssrn.com/sol3/Delivery.cfm/SSRN_ID3255075_code3110456.pdf?abstractid=3255075&mirid=1 | |
| PWC | https://paperswithcode.com/paper/defining-a-sandbox-for-responsible-ai |
| Repo | https://github.com/shaundsouza/ai-ecosystems-enabling |
| Framework | none |
CogCompNLP: Your Swiss Army Knife for NLP
| Title | CogCompNLP: Your Swiss Army Knife for NLP |
| Authors | Daniel Khashabi, Mark Sammons, Ben Zhou, Tom Redman, Christos Christodoulopoulos, Vivek Srikumar, Nicholas Rizzolo, Lev Ratinov, Guanheng Luo, Quang Do, Chen-Tse Tsai, Subhro Roy, Stephen Mayhew, Zhili Feng, John Wieting, Xiaodong Yu, Yangqiu Song, Shashank Gupta, Shyam Upadhyay, Naveen Arivazhagan, Qiang Ning, Shaoshi Ling, Dan Roth |
| Abstract | |
| Tasks | Semantic Role Labeling |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1086/ |
| https://www.aclweb.org/anthology/L18-1086 | |
| PWC | https://paperswithcode.com/paper/cogcompnlp-your-swiss-army-knife-for-nlp |
| Repo | https://github.com/CogComp/cogcomp-nlp |
| Framework | none |
Surprisingly Easy Hard-Attention for Sequence to Sequence Learning
| Title | Surprisingly Easy Hard-Attention for Sequence to Sequence Learning |
| Authors | Shiv Shankar, Siddhant Garg, Sunita Sarawagi |
| Abstract | In this paper we show that a simple beam approximation of the joint distribution between attention and output is an easy, accurate, and efficient attention mechanism for sequence to sequence learning. The method combines the advantage of sharp focus in hard attention and the implementation ease of soft attention. On five translation tasks we show effortless and consistent gains in BLEU compared to existing attention mechanisms. |
| Tasks | Image Captioning, Morphological Inflection |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1065/ |
| https://www.aclweb.org/anthology/D18-1065 | |
| PWC | https://paperswithcode.com/paper/surprisingly-easy-hard-attention-for-sequence |
| Repo | https://github.com/sid7954/beam-joint-attention |
| Framework | tf |
Framing Named Entity Linking Error Types
| Title | Framing Named Entity Linking Error Types |
| Authors | Adrian Bra{\c{s}}oveanu, Giuseppe Rizzo, Philipp Kuntschik, Albert Weichselbraun, Lyndon J.B. Nixon |
| Abstract | |
| Tasks | Entity Linking, Knowledge Base Population, Named Entity Recognition, Relation Extraction |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1040/ |
| https://www.aclweb.org/anthology/L18-1040 | |
| PWC | https://paperswithcode.com/paper/framing-named-entity-linking-error-types |
| Repo | https://github.com/modultechnology/nel_errors |
| Framework | none |
Localization and Perception for Control and Decision Making of a Low Speed Autonomous Shuttle in a Campus Pilot Deployment
| Title | Localization and Perception for Control and Decision Making of a Low Speed Autonomous Shuttle in a Campus Pilot Deployment |
| Authors | Bowen Wen, Sukru Yaren Gelbal, Bilin Aksun Guvenc, Levent Guvenc |
| Abstract | Future SAE Level 4 and Level 5 autonomous vehicles will require novel applications of localization, perception, control and artificial intelligence technology in order to offer innovative and disruptive solutions to current mobility problems. This paper concentrates on low speed autonomous shuttles that are transitioning from being tested in limited traffic, dedicated routes to being deployed as SAE Level 4 automated driving vehicles in urban environments like college campuses and outdoor shopping centers within smart cities. The Ohio State University has designated a small segment in an underserved area of campus as an initial autonomous vehicle (AV) pilot test route for the deployment of low speed autonomous shuttles. This paper presents initial results of ongoing work on developing solutions to the localization and perception challenges of this planned pilot deployment. The paper treats autonomous driving with real time kinematics GPS (Global Positioning Systems) with an inertial measurement unit (IMU), combined with simultaneous localization and mapping (SLAM) with three-dimensional light detection and ranging (LIDAR) sensor, which provides solutions to scenarios where GPS is not available or a lower cost and hence lower accuracy GPS is desirable. Our in-house automated low speed electric vehicle is used in experimental evaluation and verification. In addition, the experimental vehicle has vehicle to everything (V2X) communication capability and utilizes a dedicated short-range communication (DSRC) modem. It is able to communicate with instrumented traffic lights and with pedestrians and bicyclists with DSRC enabled smartphones. Before real-world experiments, our connected and automated driving hardware in the loop (HiL) simulator with real DSRC modems is used for extensive testing of the algorithms and the low level longitudinal and lateral controllers. Real-world experiments that are reported here have been conducted in a small test area close to the Ohio State University AV pilot test route. Model-in-the-loop simulation, HiL simulation and experimental testing are used for demonstrating the feasibility and robustness of this approach to developing and evaluating low speed autonomous shuttle localization and perception algorithms for control and decision making. |
| Tasks | Autonomous Driving, Autonomous Vehicles, Decision Making, Self-Driving Cars, Simultaneous Localization and Mapping |
| Published | 2018-11-01 |
| URL | https://www.researchgate.net/publication/330110911_Localization_and_Perception_for_Control_and_Decision-Making_of_a_Low-Speed_Autonomous_Shuttle_in_a_Campus_Pilot_Deployment |
| https://www.researchgate.net/publication/330110911_Localization_and_Perception_for_Control_and_Decision-Making_of_a_Low-Speed_Autonomous_Shuttle_in_a_Campus_Pilot_Deployment | |
| PWC | https://paperswithcode.com/paper/localization-and-perception-for-control-and |
| Repo | https://github.com/wenbowen123/hector_slam_Ceres |
| Framework | none |
Aggressive Language Identification Using Word Embeddings and Sentiment Features
| Title | Aggressive Language Identification Using Word Embeddings and Sentiment Features |
| Authors | Constantin Or{\u{a}}san |
| Abstract | This paper describes our participation in the First Shared Task on Aggression Identification. The method proposed relies on machine learning to identify social media texts which contain aggression. The main features employed by our method are information extracted from word embeddings and the output of a sentiment analyser. Several machine learning methods and different combinations of features were tried. The official submissions used Support Vector Machines and Random Forests. The official evaluation showed that for texts similar to the ones in the training dataset Random Forests work best, whilst for texts which are different SVMs are a better choice. The evaluation also showed that despite its simplicity the method performs well when compared with more elaborated methods. |
| Tasks | Language Identification, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4414/ |
| https://www.aclweb.org/anthology/W18-4414 | |
| PWC | https://paperswithcode.com/paper/aggressive-language-identification-using-word |
| Repo | https://github.com/dinel/aggression_identification |
| Framework | none |
A Retrospective Analysis of the Fake News Challenge Stance-Detection Task
| Title | A Retrospective Analysis of the Fake News Challenge Stance-Detection Task |
| Authors | Andreas Hanselowski, Avinesh PVS, Benjamin Schiller, Felix Caspelherr, Debanjan Chaudhuri, Christian M. Meyer, Iryna Gurevych |
| Abstract | The 2017 Fake News Challenge Stage 1 (FNC-1) shared task addressed a stance classification task as a crucial first step towards detecting fake news. To date, there is no in-depth analysis paper to critically discuss FNC-1{'}s experimental setup, reproduce the results, and draw conclusions for next-generation stance classification methods. In this paper, we provide such an in-depth analysis for the three top-performing systems. We first find that FNC-1{'}s proposed evaluation metric favors the majority class, which can be easily classified, and thus overestimates the true discriminative power of the methods. Therefore, we propose a new F1-based metric yielding a changed system ranking. Next, we compare the features and architectures used, which leads to a novel feature-rich stacked LSTM model that performs on par with the best systems, but is superior in predicting minority classes. To understand the methods{'} ability to generalize, we derive a new dataset and perform both in-domain and cross-domain experiments. Our qualitative and quantitative study helps interpreting the original FNC-1 scores and understand which features help improving performance and why. Our new dataset and all source code used during the reproduction study are publicly available for future research. |
| Tasks | Stance Detection |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1158/ |
| https://www.aclweb.org/anthology/C18-1158 | |
| PWC | https://paperswithcode.com/paper/a-retrospective-analysis-of-the-fake-news |
| Repo | https://github.com/UKPLab/coling2018_fake-news-challenge |
| Framework | tf |
Statistically-motivated Second-order Pooling
| Title | Statistically-motivated Second-order Pooling |
| Authors | Kaicheng Yu, Mathieu Salzmann |
| Abstract | However, the nature of such operations is usually computationally expensive, and resulting vector representation orders of magnitude larger than first-order baselines. Here, by contrast, we introduce a statistically-motivated framework that projects the second-order descriptor into a compact vector while improving the representational power. To this end, we design a parametric vectorization layer, which maps a covariance matrix, known to follow a Wishart distribution, to a vector whose elements can be shown to follow a Chi-square distribution. We then propose to make use of a square-root normalization, which makes the distribution of the resulting representation converge to a Gaussian, with which most classifiers of recent first-order networks complying. As evidenced by our experiments, this lets us outperform the state-of-the-art first-order and second-order models on several benchmark recognition datasets. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Kaicheng_Yu_Statistically-motivated_Second-order_Pooling_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Kaicheng_Yu_Statistically-motivated_Second-order_Pooling_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/statistically-motivated-second-order-pooling |
| Repo | https://github.com/kcyu2014/smsop |
| Framework | tf |
Self-regulation: Employing a Generative Adversarial Network to Improve Event Detection
| Title | Self-regulation: Employing a Generative Adversarial Network to Improve Event Detection |
| Authors | Yu Hong, Wenxuan Zhou, Jingli Zhang, Guodong Zhou, Qiaoming Zhu |
| Abstract | Due to the ability of encoding and mapping semantic information into a high-dimensional latent feature space, neural networks have been successfully used for detecting events to a certain extent. However, such a feature space can be easily contaminated by spurious features inherent in event detection. In this paper, we propose a self-regulated learning approach by utilizing a generative adversarial network to generate spurious features. On the basis, we employ a recurrent network to eliminate the fakes. Detailed experiments on the ACE 2005 and TAC-KBP 2015 corpora show that our proposed method is highly effective and adaptable. |
| Tasks | Feature Engineering |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1048/ |
| https://www.aclweb.org/anthology/P18-1048 | |
| PWC | https://paperswithcode.com/paper/self-regulation-employing-a-generative |
| Repo | https://github.com/JoeZhouWenxuan/Self-regulation-Employing-a-Generative-Adversarial-Network-to-Improve-Event-Detection |
| Framework | tf |
Using Language Learner Data for Metaphor Detection
| Title | Using Language Learner Data for Metaphor Detection |
| Authors | Egon Stemle, Alex Onysko, er |
| Abstract | This article describes the system that participated in the shared task on metaphor detection on the Vrije University Amsterdam Metaphor Corpus (VUA). The ST was part of the workshop on processing figurative language at the 16th annual conference of the North American Chapter of the Association for Computational Linguistics (NAACL2018). The system combines a small assertion of trending techniques, which implement matured methods from NLP and ML; in particular, the system uses word embeddings from standard corpora and from corpora representing different proficiency levels of language learners in a LSTM BiRNN architecture. The system is available under the APLv2 open-source license. |
| Tasks | Language Identification, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0918/ |
| https://www.aclweb.org/anthology/W18-0918 | |
| PWC | https://paperswithcode.com/paper/using-language-learner-data-for-metaphor |
| Repo | https://github.com/bot-zen/naacl_flp_st |
| Framework | none |
Development of an Open Source Natural Language Generation Tool for Finnish
| Title | Development of an Open Source Natural Language Generation Tool for Finnish |
| Authors | Mika H{"a}m{"a}l{"a}inen, Jack Rueter |
| Abstract | |
| Tasks | Text Generation |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0205/ |
| https://www.aclweb.org/anthology/W18-0205 | |
| PWC | https://paperswithcode.com/paper/development-of-an-open-source-natural |
| Repo | https://github.com/mikahama/syntaxmaker |
| Framework | none |
