Paper Group NANR 254
Fermi at SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media using Sentence Embeddings. Local Detection of Stereo Occlusion Boundaries. Neural Finite-State Transducers: Beyond Rational Relations. HAD-T"ubingen at SemEval-2019 Task 6: Deep Learning Analysis of Offensive Language on Twitter: Identification and Catego …
Fermi at SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media using Sentence Embeddings
| Title | Fermi at SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media using Sentence Embeddings |
| Authors | Vijayasaradhi Indurthi, Bakhtiyar Syed, Manish Shrivastava, Manish Gupta, Vasudeva Varma |
| Abstract | This paper describes our system (Fermi) for Task 6: OffensEval: Identifying and Categorizing Offensive Language in Social Media of SemEval-2019. We participated in all the three sub-tasks within Task 6. We evaluate multiple sentence embeddings in conjunction with various supervised machine learning algorithms and evaluate the performance of simple yet effective embedding-ML combination algorithms. Our team Fermi{'}s model achieved an F1-score of 64.40{%}, 62.00{%} and 62.60{%} for sub-task A, B and C respectively on the official leaderboard. Our model for sub-task C which uses pre-trained ELMo embeddings for transforming the input and uses SVM (RBF kernel) for training, scored third position on the official leaderboard. Through the paper we provide a detailed description of the approach, as well as the results obtained for the task. |
| Tasks | Sentence Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2109/ |
| https://www.aclweb.org/anthology/S19-2109 | |
| PWC | https://paperswithcode.com/paper/fermi-at-semeval-2019-task-6-identifying-and |
| Repo | |
| Framework | |
Local Detection of Stereo Occlusion Boundaries
| Title | Local Detection of Stereo Occlusion Boundaries |
| Authors | Jialiang Wang, Todd Zickler |
| Abstract | Stereo occlusion boundaries are one-dimensional structures in the visual field that separate foreground regions of a scene that are visible to both eyes (binocular regions) from background regions of a scene that are visible to only one eye (monocular regions). Stereo occlusion boundaries often coincide with object boundaries, and localizing them is useful for tasks like grasping, manipulation, and navigation. This paper describes the local signatures for stereo occlusion boundaries that exist in a stereo cost volume, and it introduces a local detector for them based on a simple feedforward network with relatively small receptive fields. The local detector produces better boundaries than many other stereo methods, even without incorporating explicit stereo matching, top-down contextual cues, or single-image boundary cues based on texture and intensity. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Local_Detection_of_Stereo_Occlusion_Boundaries_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Local_Detection_of_Stereo_Occlusion_Boundaries_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/local-detection-of-stereo-occlusion |
| Repo | |
| Framework | |
Neural Finite-State Transducers: Beyond Rational Relations
| Title | Neural Finite-State Transducers: Beyond Rational Relations |
| Authors | Chu-Cheng Lin, Hao Zhu, Matthew R. Gormley, Jason Eisner |
| Abstract | We introduce neural finite state transducers (NFSTs), a family of string transduction models defining joint and conditional probability distributions over pairs of strings. The probability of a string pair is obtained by marginalizing over all its accepting paths in a finite state transducer. In contrast to ordinary weighted FSTs, however, each path is scored using an arbitrary function such as a recurrent neural network, which breaks the usual conditional independence assumption (Markov property). NFSTs are more powerful than previous finite-state models with neural features (Rastogi et al., 2016.) We present training and inference algorithms for locally and globally normalized variants of NFSTs. In experiments on different transduction tasks, they compete favorably against seq2seq models while offering interpretable paths that correspond to hard monotonic alignments. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1024/ |
| https://www.aclweb.org/anthology/N19-1024 | |
| PWC | https://paperswithcode.com/paper/neural-finite-state-transducers-beyond |
| Repo | |
| Framework | |
HAD-T"ubingen at SemEval-2019 Task 6: Deep Learning Analysis of Offensive Language on Twitter: Identification and Categorization
| Title | HAD-T"ubingen at SemEval-2019 Task 6: Deep Learning Analysis of Offensive Language on Twitter: Identification and Categorization |
| Authors | Himanshu Bansal, Daniel Nagel, Anita Soloveva |
| Abstract | This paper describes the submissions of our team, HAD-T{"u}bingen, for the SemEval 2019 - Task 6: {}OffensEval: Identifying and Categorizing Offensive Language in Social Media{''}. We participated in all the three sub-tasks: Sub-task A - {}Offensive language identification{''}, sub-task B - {}Automatic categorization of offense types{''} and sub-task C - {}Offense target identification{''}. As a baseline model we used a Long short-term memory recurrent neural network (LSTM) to identify and categorize offensive tweets. For all the tasks we experimented with external databases in a postprocessing step to enhance the results made by our model. The best macro-average F1 scores obtained for the sub-tasks A, B and C are 0.73, 0.52, and 0.37, respectively. |
| Tasks | Language Identification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2111/ |
| https://www.aclweb.org/anthology/S19-2111 | |
| PWC | https://paperswithcode.com/paper/had-tubingen-at-semeval-2019-task-6-deep |
| Repo | |
| Framework | |
HHU at SemEval-2019 Task 6: Context Does Matter - Tackling Offensive Language Identification and Categorization with ELMo
| Title | HHU at SemEval-2019 Task 6: Context Does Matter - Tackling Offensive Language Identification and Categorization with ELMo |
| Authors | Alex Oberstrass, er, Julia Romberg, Anke Stoll, Stefan Conrad |
| Abstract | We present our results for OffensEval: Identifying and Categorizing Offensive Language in Social Media (SemEval 2019 - Task 6). Our results show that context embeddings are important features for the three different sub-tasks in connection with classical machine and with deep learning. Our best model reached place 3 of 75 in sub-task B with a macro $F_1$ of 0.719. Our approaches for sub-task A and C perform less well but could also deliver promising results. |
| Tasks | Language Identification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2112/ |
| https://www.aclweb.org/anthology/S19-2112 | |
| PWC | https://paperswithcode.com/paper/hhu-at-semeval-2019-task-6-context-does |
| Repo | |
| Framework | |
Automatic Question Answering for Medical MCQs: Can It go Further than Information Retrieval?
| Title | Automatic Question Answering for Medical MCQs: Can It go Further than Information Retrieval? |
| Authors | Le An Ha, Victoria Yaneva |
| Abstract | We present a novel approach to automatic question answering that does not depend on the performance of an information retrieval (IR) system and does not require that the training data come from the same source as the questions. We evaluate the system performance on a challenging set of university-level medical science multiple-choice questions. Best performance is achieved when combining a neural approach with an IR approach, both of which work independently. Unlike previous approaches, the system achieves statistically significant improvement over the random guess baseline even for questions that are labeled as challenging based on the performance of baseline solvers. |
| Tasks | Information Retrieval, Question Answering |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1049/ |
| https://www.aclweb.org/anthology/R19-1049 | |
| PWC | https://paperswithcode.com/paper/automatic-question-answering-for-medical-mcqs |
| Repo | |
| Framework | |
Wi-Fi Sensing: Applications and Challenges
| Title | Wi-Fi Sensing: Applications and Challenges |
| Authors | A. M. Khalili, Abdel-Hamid Soliman, Md Asaduzzaman, Alison Griffiths |
| Abstract | Wi-Fi technology has strong potentials in indoor and outdoor sensing applications, it has several important features which makes it an appealing option compared to other sensing technologies. This paper presents a survey on different applications of Wi-Fi based sensing systems such as elderly people monitoring, activity classification, gesture recognition, people counting, through the wall sensing, behind the corner sensing, and many other applications. The challenges and interesting future directions are also highlighted. |
| Tasks | Gesture Recognition, RF-based Action Recognition, RF-based Gesture Recognition, RF-based Pose Estimation |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1901.00715 |
| https://arxiv.org/pdf/1901.00715 | |
| PWC | https://paperswithcode.com/paper/wi-fi-sensing-applications-and-challenges |
| Repo | |
| Framework | |
Left-to-Right Dependency Parsing with Pointer Networks
| Title | Left-to-Right Dependency Parsing with Pointer Networks |
| Authors | Daniel Fern{'a}ndez-Gonz{'a}lez, Carlos G{'o}mez-Rodr{'\i}guez |
| Abstract | We propose a novel transition-based algorithm that straightforwardly parses sentences from left to right by building n attachments, with n being the length of the input sentence. Similarly to the recent stack-pointer parser by Ma et al. (2018), we use the pointer network framework that, given a word, can directly point to a position from the sentence. However, our left-to-right approach is simpler than the original top-down stack-pointer parser (not requiring a stack) and reduces transition sequence length in half, from 2n-1 actions to n. This results in a quadratic non-projective parser that runs twice as fast as the original while achieving the best accuracy to date on the English PTB dataset (96.04{%} UAS, 94.43{%} LAS) among fully-supervised single-model dependency parsers, and improves over the former top-down transition system in the majority of languages tested. |
| Tasks | Dependency Parsing |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1076/ |
| https://www.aclweb.org/anthology/N19-1076 | |
| PWC | https://paperswithcode.com/paper/left-to-right-dependency-parsing-with-pointer-1 |
| Repo | |
| Framework | |
jhan014 at SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media
| Title | jhan014 at SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media |
| Authors | Jiahui Han, Shengtan Wu, Xinyu Liu |
| Abstract | In this paper, we present two methods to identify and categorize the offensive language in Twitter. In the first method, we establish a probabilistic model to evaluate the sentence offensiveness level and target level according to different sub-tasks. In the second method, we develop a deep neural network consisting of bidirectional recurrent layers with Gated Recurrent Unit (GRU) cells and fully connected layers. In the comparison of two methods, we find both method has its own advantages and drawbacks while they have similar accuracy. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2116/ |
| https://www.aclweb.org/anthology/S19-2116 | |
| PWC | https://paperswithcode.com/paper/jhan014-at-semeval-2019-task-6-identifying |
| Repo | |
| Framework | |
Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection
| Title | Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection |
| Authors | Xuesong Niu, Hu Han, Songfan Yang, Yan Huang, Shiguang Shan |
| Abstract | Encoding individual facial expressions via action units (AUs) coded by the Facial Action Coding System (FACS) has been found to be an effective approach in resolving the ambiguity issue among different expressions. While a number of methods have been proposed for AU detection, robust AU detection in the wild remains a challenging problem because of the diverse baseline AU intensities across individual subjects, and the weakness of appearance signal of AUs. To resolve these issues, in this work, we propose a novel AU detection method by utilizing local information and the relationship of individual local face regions. Through such a local relationship learning, we expect to utilize rich local information to improve the AU detection robustness against the potential perceptual inconsistency of individual local regions. In addition, considering the diversity in the baseline AU intensities of individual subjects, we further regularize local relationship learning via person-specific face shape information, i.e., reducing the influence of person-specific shape information, and obtaining more AU discriminative features. The proposed approach outperforms the state-of-the-art methods on two widely used AU detection datasets in the public domain (BP4D and DISFA). |
| Tasks | Action Unit Detection, Facial Action Unit Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Niu_Local_Relationship_Learning_With_Person-Specific_Shape_Regularization_for_Facial_Action_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Niu_Local_Relationship_Learning_With_Person-Specific_Shape_Regularization_for_Facial_Action_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/local-relationship-learning-with-person |
| Repo | |
| Framework | |
Uncovering Surprising Behaviors in Reinforcement Learning via Worst-case Analysis
| Title | Uncovering Surprising Behaviors in Reinforcement Learning via Worst-case Analysis |
| Authors | Avraham Ruderman, Richard Everett, Bristy Sikder, Hubert Soyer, Jonathan Uesato, Ananya Kumar, Charlie Beattie, Pushmeet Kohli |
| Abstract | Reinforcement learning agents are typically trained and evaluated according to their performance averaged over some distribution of environment settings. But does the distribution over environment settings contain important biases, and do these lead to agents that fail in certain cases despite high average-case performance? In this work, we consider worst-case analysis of agents over environment settings in order to detect whether there are directions in which agents may have failed to generalize. Specifically, we consider a 3D first-person task where agents must navigate procedurally generated mazes, and where reinforcement learning agents have recently achieved human-level average-case performance. By optimizing over the structure of mazes, we find that agents can suffer from catastrophic failures, failing to find the goal even on surprisingly simple mazes, despite their impressive average-case performance. Additionally, we find that these failures transfer between different agents and even significantly different architectures. We believe our findings highlight an important role for worst-case analysis in identifying whether there are directions in which agents have failed to generalize. Our hope is that the ability to automatically identify failures of generalization will facilitate development of more general and robust agents. To this end, we report initial results on enriching training with settings causing failure. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SkgZNnR5tX |
| https://openreview.net/pdf?id=SkgZNnR5tX | |
| PWC | https://paperswithcode.com/paper/uncovering-surprising-behaviors-in |
| Repo | |
| Framework | |
CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation
| Title | CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation |
| Authors | Zhigang Li, Gu Wang, Xiangyang Ji |
| Abstract | 6-DoF object pose estimation from a single RGB image is a fundamental and long-standing problem in computer vision. Current leading approaches solve it by training deep networks to either regress both rotation and translation from image directly or to construct 2D-3D correspondences and further solve them via PnP indirectly. We argue that rotation and translation should be treated differently for their significant difference. In this work, we propose a novel 6-DoF pose estimation approach: Coordinates-based Disentangled Pose Network (CDPN), which disentangles the pose to predict rotation and translation separately to achieve highly accurate and robust pose estimation. Our method is flexible, efficient, highly accurate and can deal with texture-less and occluded objects. Extensive experiments on LINEMOD and Occlusion datasets are conducted and demonstrate the superiority of our approach. Concretely, our approach significantly exceeds the state-of-the- art RGB-based methods on commonly used metrics. |
| Tasks | 6D Pose Estimation using RGB, Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Li_CDPN_Coordinates-Based_Disentangled_Pose_Network_for_Real-Time_RGB-Based_6-DoF_Object_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_CDPN_Coordinates-Based_Disentangled_Pose_Network_for_Real-Time_RGB-Based_6-DoF_Object_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/cdpn-coordinates-based-disentangled-pose |
| Repo | |
| Framework | |
Content-based Dwell Time Engagement Prediction Model for News Articles
| Title | Content-based Dwell Time Engagement Prediction Model for News Articles |
| Authors | Heidar Davoudi, Aijun An, Gordon Edall |
| Abstract | The article dwell time (i.e., expected time that users spend on an article) is among the most important factors showing the article engagement. It is of great interest to predict the dwell time of an article before its release. This allows digital newspapers to make informed decisions and publish more engaging articles. In this paper, we propose a novel content-based approach based on a deep neural network architecture for predicting article dwell times. The proposed model extracts emotion, event and entity features from an article, learns interactions among them, and combines the interactions with the word-based features of the article to learn a model for predicting the dwell time. The experimental results on a real dataset from a major newspaper show that the proposed model outperforms other state-of-the-art baselines. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2028/ |
| https://www.aclweb.org/anthology/N19-2028 | |
| PWC | https://paperswithcode.com/paper/content-based-dwell-time-engagement |
| Repo | |
| Framework | |
Learning to Progressively Plan
| Title | Learning to Progressively Plan |
| Authors | Xinyun Chen, Yuandong Tian |
| Abstract | For problem solving, making reactive decisions based on problem description is fast but inaccurate, while search-based planning using heuristics gives better solutions but could be exponentially slow. In this paper, we propose a new approach that improves an existing solution by iteratively picking and rewriting its local components until convergence. The rewriting policy employs a neural network trained with reinforcement learning. We evaluate our approach in two domains: job scheduling and expression simplification. Compared to common effective heuristics, baseline deep models and search algorithms, our approach efficiently gives solutions with higher quality. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJgQB20qFQ |
| https://openreview.net/pdf?id=BJgQB20qFQ | |
| PWC | https://paperswithcode.com/paper/learning-to-progressively-plan |
| Repo | |
| Framework | |
Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection
| Title | Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection |
| Authors | Rui Shao, Xiangyuan Lan, Jiawei Li, Pong C. Yuen |
| Abstract | Face presentation attacks have become an increasingly critical issue in the face recognition community. Many face anti-spoofing methods have been proposed, but they cannot generalize well on “unseen” attacks. This work focuses on improving the generalization ability of face anti-spoofing methods from the perspective of the domain generalization. We propose to learn a generalized feature space via a novel multi-adversarial discriminative deep domain generalization framework. In this framework, a multi-adversarial deep domain generalization is performed under a dual-force triplet-mining constraint. This ensures that the learned feature space is discriminative and shared by multiple source domains, and thus is more generalized to new face presentation attacks. An auxiliary face depth supervision is incorporated to further enhance the generalization ability. Extensive experiments on four public datasets validate the effectiveness of the proposed method. |
| Tasks | Domain Generalization, Face Anti-Spoofing, Face Presentation Attack Detection, Face Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Shao_Multi-Adversarial_Discriminative_Deep_Domain_Generalization_for_Face_Presentation_Attack_Detection_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Shao_Multi-Adversarial_Discriminative_Deep_Domain_Generalization_for_Face_Presentation_Attack_Detection_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multi-adversarial-discriminative-deep-domain |
| Repo | |
| Framework | |
