Paper Group NANR 36
Contextualized Word Representations from Distant Supervision with and for NER. A deep-learning-based approach for fast and robust steel surface defects classification. Self-Supervised 3D Hand Pose Estimation Through Training by Fitting. Crowdsourced Hedge Term Disambiguation. Multilingual Multimodal Machine Translation for Dravidian Languages utili …
Contextualized Word Representations from Distant Supervision with and for NER
| Title | Contextualized Word Representations from Distant Supervision with and for NER |
| Authors | Abbas Ghaddar, Phillippe Langlais |
| Abstract | We describe a special type of deep contextualized word representation that is learned from distant supervision annotations and dedicated to named entity recognition. Our extensive experiments on 7 datasets show systematic gains across all domains over strong baselines, and demonstrate that our representation is complementary to previously proposed embeddings. We report new state-of-the-art results on CONLL and ONTONOTES datasets. |
| Tasks | Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5513/ |
| https://www.aclweb.org/anthology/D19-5513 | |
| PWC | https://paperswithcode.com/paper/contextualized-word-representations-from |
| Repo | |
| Framework | |
A deep-learning-based approach for fast and robust steel surface defects classification
| Title | A deep-learning-based approach for fast and robust steel surface defects classification |
| Authors | Guizhong Fu, Peize Sun a, Wenbin Zhu, Jiangxin Yang, Yanlong Cao, Michael Ying Yang, Yanpeng Cao |
| Abstract | Automatic visual recognition of steel surface defects provides critical functionality to facilitate quality control of steel strip production. In this paper, we present a compact yet effective convolutional neural network (CNN) model, which emphasizes the training of low-level features and incorporates multiple receptive fields, to achieve fast and accurate steel surface defect classification. Our proposed method adopts the pre-trained SqueezeNet as the backbone architecture. It only requires a small amount of defect-specific training samples to achieve high- accuracy recognition on a diversity-enhanced testing dataset of steel surface defects which contains severe non- uniform illumination, camera noise, and motion blur. Moreover, our proposed light-weight CNN model can meet the requirement of real-time online inspection, running over 100 fps on a computer equipped with a single NVIDIA TITAN X Graphics Processing Unit (12G memory). Codes and a diversity-enhanced testing dataset will be made publicly available. |
| Tasks | |
| Published | 2019-05-15 |
| URL | https://doi.org/10.1016/j.optlaseng.2019.05.005 |
| https://reader.elsevier.com/reader/sd/pii/S0143816619301678?token=55C51B01EE82794EBAB609DE04AB86C09BD2FA1B79CF4A1EC3AA3F3A1D36BAE8C08ABF50F8EC88DD1D709446A2A57A86 | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-based-approach-for-fast-and |
| Repo | |
| Framework | |
Self-Supervised 3D Hand Pose Estimation Through Training by Fitting
| Title | Self-Supervised 3D Hand Pose Estimation Through Training by Fitting |
| Authors | Chengde Wan, Thomas Probst, Luc Van Gool, Angela Yao |
| Abstract | We present a self-supervision method for 3D hand pose estimation from depth maps. We begin with a neural network initialized with synthesized data and fine-tune it on real but unlabelled depth maps by minimizing a set of data-fitting terms. By approximating the hand surface with a set of spheres, we design a differentiable hand renderer to align estimates by comparing the rendered and input depth maps. In addition, we place a set of priors including a data-driven term to further regulate the estimate’s kinematic feasibility. Our method makes highly accurate estimates comparable to current supervised methods which require large amounts of labelled training samples, thereby advancing state-of-the-art in unsupervised learning for hand pose estimation. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wan_Self-Supervised_3D_Hand_Pose_Estimation_Through_Training_by_Fitting_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wan_Self-Supervised_3D_Hand_Pose_Estimation_Through_Training_by_Fitting_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-3d-hand-pose-estimation |
| Repo | |
| Framework | |
Crowdsourced Hedge Term Disambiguation
| Title | Crowdsourced Hedge Term Disambiguation |
| Authors | Morgan Ulinski, Julia Hirschberg |
| Abstract | We address the issue of acquiring quality annotations of hedging words and phrases, linguistic phenomenona in which words, sounds, or other constructions are used to express ambiguity or uncertainty. Due to the limited availability of existing corpora annotated for hedging, linguists and other language scientists have been constrained as to the extent they can study this phenomenon. In this paper, we introduce a new method of acquiring hedging annotations via crowdsourcing, based on reformulating the task of labeling hedges as a simple word sense disambiguation task. We also introduce a new hedging corpus we have constructed by applying this method, a collection of forum posts annotated using Amazon Mechanical Turk. We found that the crowdsourced judgments we obtained had an inter-annotator agreement of 92.89{%} (Fleiss{'} Kappa=0.751) and, when comparing a subset of these annotations to an expert-annotated gold standard, an accuracy of 96.65{%}. |
| Tasks | Word Sense Disambiguation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4001/ |
| https://www.aclweb.org/anthology/W19-4001 | |
| PWC | https://paperswithcode.com/paper/crowdsourced-hedge-term-disambiguation |
| Repo | |
| Framework | |
Multilingual Multimodal Machine Translation for Dravidian Languages utilizing Phonetic Transcription
| Title | Multilingual Multimodal Machine Translation for Dravidian Languages utilizing Phonetic Transcription |
| Authors | Bharathi Raja Chakravarthi, Ruba Priyadharshini, Bernardo Stearns, Arun Jayapal, Sridevy S, Mihael Arcan, Manel Zarrouk, John P McCrae |
| Abstract | |
| Tasks | Machine Translation, Multimodal Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6809/ |
| https://www.aclweb.org/anthology/W19-6809 | |
| PWC | https://paperswithcode.com/paper/multilingual-multimodal-machine-translation |
| Repo | |
| Framework | |
Mental Fatigue Monitoring using Brain Dynamics Preferences
| Title | Mental Fatigue Monitoring using Brain Dynamics Preferences |
| Authors | Yuangang Pan, Avinash K Singh, Ivor W. Tsang, Chin-teng Lin |
| Abstract | Driver’s cognitive state of mental fatigue significantly affects driving performance and more importantly public safety. Previous studies leverage the response time (RT) as the metric for mental fatigue and aim at estimating the exact value of RT using electroencephalogram (EEG) signals within a regression model. However, due to the easily corrupted EEG signals and also non-smooth RTs during data collection, regular regression methods generally suffer from poor generalization performance. Considering that human response time is the reflection of brain dynamics preference rather than a single value, a novel model called Brain Dynamic ranking (BDrank) has been proposed. BDrank could learn from brain dynamics preferences using EEG data robustly and preserve the ordering corresponding to RTs. BDrank model is based on the regularized alternative ordinal classification comparing to regular regression based practices. Furthermore, a transition matrix is introduced to characterize the reliability of each channel used in EEG data, which helps in learning brain dynamics preferences only from informative EEG channels. In order to handle large-scale EEG signals~and obtain higher generalization, an online-generalized Expectation Maximum (OnlineGEM) algorithm also has been proposed to update BDrank in an online fashion. Comprehensive empirical analysis on EEG signals from 44 participants shows that BDrank together with OnlineGEM achieves substantial improvements in reliability while simultaneously detecting possible less informative and noisy EEG channels. |
| Tasks | EEG |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1l9qsA5KQ |
| https://openreview.net/pdf?id=B1l9qsA5KQ | |
| PWC | https://paperswithcode.com/paper/mental-fatigue-monitoring-using-brain |
| Repo | |
| Framework | |
UniMelb at SemEval-2019 Task 12: Multi-model combination for toponym resolution
| Title | UniMelb at SemEval-2019 Task 12: Multi-model combination for toponym resolution |
| Authors | Haonan Li, Minghan Wang, Timothy Baldwin, Martin Tomko, Maria Vasardani |
| Abstract | This paper describes our submission to SemEval-2019 Task 12 on toponym resolution over scientific articles. We train separate NER models for toponym detection over text extracted from tables vs. text from the body of the paper, and train another auxiliary model to eliminate misdetected toponyms. For toponym disambiguation, we use an SVM classifier with hand-engineered features. The best setting achieved a strict micro-F1 score of 80.92{%} and overlap micro-F1 score of 86.88{%} in the toponym detection subtask, ranking 2nd out of 8 teams on F1 score. For toponym disambiguation and end-to-end resolution, we officially ranked 2nd and 3rd, respectively. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2231/ |
| https://www.aclweb.org/anthology/S19-2231 | |
| PWC | https://paperswithcode.com/paper/unimelb-at-semeval-2019-task-12-multi-model |
| Repo | |
| Framework | |
Subversive Toxicity Detection using Sentiment Information
| Title | Subversive Toxicity Detection using Sentiment Information |
| Authors | Eloi Brassard-Gourdeau, Richard Khoury |
| Abstract | The presence of toxic content has become a major problem for many online communities. Moderators try to limit this problem by implementing more and more refined comment filters, but toxic users are constantly finding new ways to circumvent them. Our hypothesis is that while modifying toxic content and keywords to fool filters can be easy, hiding sentiment is harder. In this paper, we explore various aspects of sentiment detection and their correlation to toxicity, and use our results to implement a toxicity detection tool. We then test how adding the sentiment information helps detect toxicity in three different real-world datasets, and incorporate subversion to these datasets to simulate a user trying to circumvent the system. Our results show sentiment information has a positive impact on toxicity detection. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3501/ |
| https://www.aclweb.org/anthology/W19-3501 | |
| PWC | https://paperswithcode.com/paper/subversive-toxicity-detection-using-sentiment |
| Repo | |
| Framework | |
Proceedings of the First International Workshop on Designing Meaning Representations
| Title | Proceedings of the First International Workshop on Designing Meaning Representations |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3300/ |
| https://www.aclweb.org/anthology/W19-3300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-international-5 |
| Repo | |
| Framework | |
GL at SemEval-2019 Task 5: Identifying hateful tweets with a deep learning approach.
| Title | GL at SemEval-2019 Task 5: Identifying hateful tweets with a deep learning approach. |
| Authors | Gretel Liz De la Pe{~n}a |
| Abstract | This paper describes the system we developed for SemEval 2019 on Multilingual detection of hate speech against immigrants and women in Twitter (HatEval - Task 5). We use an approach based on an Attention-based Long Short-Term Memory Recurrent Neural Network. In particular, we build a Bidirectional LSTM to extract information from the word embeddings over the sentence, then apply attention over the hidden states to estimate the importance of each word and finally feed this context vector to another LSTM model to get a representation. Then, the output obtained with this model is used to get the prediction of each of the sub-tasks. |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2073/ |
| https://www.aclweb.org/anthology/S19-2073 | |
| PWC | https://paperswithcode.com/paper/gl-at-semeval-2019-task-5-identifying-hateful |
| Repo | |
| Framework | |
LT3 at SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter (hatEval)
| Title | LT3 at SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter (hatEval) |
| Authors | Nina Bauwelinck, Gilles Jacobs, V{'e}ronique Hoste, Els Lefever |
| Abstract | This paper describes our contribution to the SemEval-2019 Task 5 on the detection of hate speech against immigrants and women in Twitter (hatEval). We considered a supervised classification-based approach to detect hate speech in English tweets, which combines a variety of standard lexical and syntactic features with specific features for capturing offensive language. Our experimental results show good classification performance on the training data, but a considerable drop in recall on the held-out test set. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2077/ |
| https://www.aclweb.org/anthology/S19-2077 | |
| PWC | https://paperswithcode.com/paper/lt3-at-semeval-2019-task-5-multilingual |
| Repo | |
| Framework | |
Semantics-Enhanced Adversarial Nets for Text-to-Image Synthesis
| Title | Semantics-Enhanced Adversarial Nets for Text-to-Image Synthesis |
| Authors | Hongchen Tan, Xiuping Liu, Xin Li, Yi Zhang, Baocai Yin |
| Abstract | This paper presents a new model, Semantics-enhanced Generative Adversarial Network (SEGAN), for fine-grained text-to-image generation. We introduce two modules, a Semantic Consistency Module (SCM) and an Attention Competition Module (ACM), to our SEGAN. The SCM incorporates image-level semantic consistency into the training of the Generative Adversarial Network (GAN), and can diversify the generated images and improve their structural coherence. A Siamese network and two types of semantic similarities are designed to map the synthesized image and the groundtruth image to nearby points in the latent semantic feature space. The ACM constructs adaptive attention weights to differentiate keywords from unimportant words, and improves the stability and accuracy of SEGAN. Extensive experiments demonstrate that our SEGAN significantly outperforms existing state-of-the-art methods in generating photo-realistic images. All source codes and models will be released for comparative study. |
| Tasks | Image Generation, Text-to-Image Generation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Tan_Semantics-Enhanced_Adversarial_Nets_for_Text-to-Image_Synthesis_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Tan_Semantics-Enhanced_Adversarial_Nets_for_Text-to-Image_Synthesis_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/semantics-enhanced-adversarial-nets-for-text |
| Repo | |
| Framework | |
Polynomial Representation for Persistence Diagram
| Title | Polynomial Representation for Persistence Diagram |
| Authors | Zhichao Wang, Qian Li, Gang Li, Guandong Xu |
| Abstract | Persistence diagram (PD) has been considered as a compact descriptor for topological data analysis (TDA). Unfortunately, PD cannot be directly used in machine learning methods since it is a multiset of points. Recent efforts have been devoted to transforming PDs into vectors to accommodate machine learning methods. However, they share one common shortcoming: the mapping of PDs to a feature representation depends on a pre-defined polynomial. To address this limitation, this paper proposes an algebraic representation for PDs, i.e., polynomial representation. In this work, we discover a set of general polynomials that vanish on vectorized PDs and extract the task-adapted feature representation from these polynomials. We also prove two attractive properties of the proposed polynomial representation, i.e., stability and linear separability. Experiments also show that our method compares favorably with state-of-the-art TDA methods. |
| Tasks | Topological Data Analysis |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Polynomial_Representation_for_Persistence_Diagram_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Polynomial_Representation_for_Persistence_Diagram_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/polynomial-representation-for-persistence |
| Repo | |
| Framework | |
Scalable Verified Training for Provably Robust Image Classification
| Title | Scalable Verified Training for Provably Robust Image Classification |
| Authors | Sven Gowal, Krishnamurthy (Dj) Dvijotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato, Relja Arandjelovic, Timothy Mann, Pushmeet Kohli |
| Abstract | Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minimizing an upper bound on the worst-case loss over all possible adversarial perturbations. While these techniques show promise, they often result in difficult optimization procedures that remain hard to scale to larger networks. Through a comprehensive analysis, we show how a simple bounding technique, interval bound propagation (IBP), can be exploited to train large provably robust neural networks that beat the state-of-the-art in verified accuracy. While the upper bound computed by IBP can be quite weak for general networks, we demonstrate that an appropriate loss and clever hyper-parameter schedule allow the network to adapt such that the IBP bound is tight. This results in a fast and stable learning algorithm that outperforms more sophisticated methods and achieves state-of-the-art results on MNIST, CIFAR-10 and SVHN. It also allows us to train the largest model to be verified beyond vacuous bounds on a downscaled version of IMAGENET. |
| Tasks | Image Classification |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Gowal_Scalable_Verified_Training_for_Provably_Robust_Image_Classification_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Gowal_Scalable_Verified_Training_for_Provably_Robust_Image_Classification_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-verified-training-for-provably |
| Repo | |
| Framework | |
HoloPose: Holistic 3D Human Reconstruction In-The-Wild
| Title | HoloPose: Holistic 3D Human Reconstruction In-The-Wild |
| Authors | Riza Alp Guler, Iasonas Kokkinos |
| Abstract | We introduce HoloPose, a method for holistic monocular 3D human body reconstruction. We first introduce a part-based model for 3D model parameter regression that allows our method to operate in-the-wild, gracefully handling severe occlusions and large pose variation. We further train a multi-task network comprising 2D, 3D and Dense Pose estimation to drive the 3D reconstruction task. For this we introduce an iterative refinement method that aligns the model-based 3D estimates of 2D/3D joint positions and DensePose with their image-based counterparts delivered by CNNs, achieving both model-based, global consistency and high spatial accuracy thanks to the bottom-up CNN processing. We validate our contributions on challenging benchmarks, showing that our method allows us to get both accurate joint and 3D surface estimates while operating at more than 10fps in-the-wild. More information about our approach, including videos and demos is available at http://arielai.com/holopose. |
| Tasks | 3D Reconstruction, Pose Estimation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Guler_HoloPose_Holistic_3D_Human_Reconstruction_In-The-Wild_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Guler_HoloPose_Holistic_3D_Human_Reconstruction_In-The-Wild_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/holopose-holistic-3d-human-reconstruction-in |
| Repo | |
| Framework | |
