Paper Group NANR 163
Emotion Detection and Classification in a Multigenre Corpus with Joint Multi-Task Deep Learning. Aggression Identification Using Deep Learning and Data Augmentation. Towards Unsupervised Classification with Deep Generative Models. Cyber-aggression Detection using Cross Segment-and-Concatenate Multi-Task Learning from Text. The Nautilus Speaker Char …
Emotion Detection and Classification in a Multigenre Corpus with Joint Multi-Task Deep Learning
| Title | Emotion Detection and Classification in a Multigenre Corpus with Joint Multi-Task Deep Learning |
| Authors | Shabnam Tafreshi, Mona Diab |
| Abstract | Detection and classification of emotion categories expressed by a sentence is a challenging task due to subjectivity of emotion. To date, most of the models are trained and evaluated on single genre and when used to predict emotion in different genre their performance drops by a large margin. To address the issue of robustness, we model the problem within a joint multi-task learning framework. We train this model with a multigenre emotion corpus to predict emotions across various genre. Each genre is represented as a separate task, we use soft parameter shared layers across the various tasks. our experimental results show that this model improves the results across the various genres, compared to a single genre training in the same neural net architecture. |
| Tasks | Multi-Task Learning |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1246/ |
| https://www.aclweb.org/anthology/C18-1246 | |
| PWC | https://paperswithcode.com/paper/emotion-detection-and-classification-in-a |
| Repo | |
| Framework | |
Aggression Identification Using Deep Learning and Data Augmentation
| Title | Aggression Identification Using Deep Learning and Data Augmentation |
| Authors | Julian Risch, Ralf Krestel |
| Abstract | Social media platforms allow users to share and discuss their opinions online. However, a minority of user posts is aggressive, thereby hinders respectful discussion, and {—} at an extreme level {—} is liable to prosecution. The automatic identification of such harmful posts is important, because it can support the costly manual moderation of online discussions. Further, the automation allows unprecedented analyses of discussion datasets that contain millions of posts. This system description paper presents our submission to the First Shared Task on Aggression Identification. We propose to augment the provided dataset to increase the number of labeled comments from 15,000 to 60,000. Thereby, we introduce linguistic variety into the dataset. As a consequence of the larger amount of training data, we are able to train a special deep neural net, which generalizes especially well to unseen data. To further boost the performance, we combine this neural net with three logistic regression classifiers trained on character and word n-grams, and hand-picked syntactic features. This ensemble is more robust than the individual single models. Our team named {``}Julian{''} achieves an F1-score of 60{%} on both English datasets, 63{%} on the Hindi Facebook dataset, and 38{%} on the Hindi Twitter dataset. | |
| Tasks | Data Augmentation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4418/ |
| https://www.aclweb.org/anthology/W18-4418 | |
| PWC | https://paperswithcode.com/paper/aggression-identification-using-deep-learning |
| Repo | |
| Framework | |
Towards Unsupervised Classification with Deep Generative Models
| Title | Towards Unsupervised Classification with Deep Generative Models |
| Authors | Dimitris Kalatzis, Konstantia Kotta, Ilias Kalamaras, Anastasios Vafeiadis, Andrew Rawstron, Dimitris Tzovaras, Kostas Stamatopoulos |
| Abstract | Deep generative models have advanced the state-of-the-art in semi-supervised classification, however their capacity for deriving useful discriminative features in a completely unsupervised fashion for classification in difficult real-world data sets, where adequate manifold separation is required has not been adequately explored. Most methods rely on defining a pipeline of deriving features via generative modeling and then applying clustering algorithms, separating the modeling and discriminative processes. We propose a deep hierarchical generative model which uses a mixture of discrete and continuous distributions to learn to effectively separate the different data manifolds and is trainable end-to-end. We show that by specifying the form of the discrete variable distribution we are imposing a specific structure on the model’s latent representations. We test our model’s discriminative performance on the task of CLL diagnosis against baselines from the field of computational FC, as well as the Variational Autoencoder literature. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ryb83alCZ |
| https://openreview.net/pdf?id=ryb83alCZ | |
| PWC | https://paperswithcode.com/paper/towards-unsupervised-classification-with-deep |
| Repo | |
| Framework | |
Cyber-aggression Detection using Cross Segment-and-Concatenate Multi-Task Learning from Text
| Title | Cyber-aggression Detection using Cross Segment-and-Concatenate Multi-Task Learning from Text |
| Authors | Ahmed Husseini Orabi, Mahmoud Husseini Orabi, Qianjia Huang, Diana Inkpen, David Van Bruwaene |
| Abstract | In this paper, we propose a novel deep-learning architecture for text classification, named cross segment-and-concatenate multi-task learning (CSC-MTL). We use CSC-MTL to improve the performance of cyber-aggression detection from text. Our approach provides a robust shared feature representation for multi-task learning by detecting contrasts and similarities among polarity and neutral classes. We participated in the cyber-aggression shared task under the team name uOttawa. We report 59.74{%} F1 performance for the Facebook test set and 56.9{%} for the Twitter test set, for detecting aggression from text. |
| Tasks | Multi-Task Learning, Text Classification |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4419/ |
| https://www.aclweb.org/anthology/W18-4419 | |
| PWC | https://paperswithcode.com/paper/cyber-aggression-detection-using-cross |
| Repo | |
| Framework | |
The Nautilus Speaker Characterization Corpus: Speech Recordings and Labels of Speaker Characteristics and Voice Descriptions
| Title | The Nautilus Speaker Characterization Corpus: Speech Recordings and Labels of Speaker Characteristics and Voice Descriptions |
| Authors | Laura Fern{'a}ndez Gallardo, Benjamin Weiss |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1448/ |
| https://www.aclweb.org/anthology/L18-1448 | |
| PWC | https://paperswithcode.com/paper/the-nautilus-speaker-characterization-corpus |
| Repo | |
| Framework | |
Delete or not Delete? Semi-Automatic Comment Moderation for the Newsroom
| Title | Delete or not Delete? Semi-Automatic Comment Moderation for the Newsroom |
| Authors | Julian Risch, Ralf Krestel |
| Abstract | Comment sections of online news providers have enabled millions to share and discuss their opinions on news topics. Today, moderators ensure respectful and informative discussions by deleting not only insults, defamation, and hate speech, but also unverifiable facts. This process has to be transparent and comprehensive in order to keep the community engaged. Further, news providers have to make sure to not give the impression of censorship or dissemination of fake news. Yet manual moderation is very expensive and becomes more and more unfeasible with the increasing amount of comments. Hence, we propose a semi-automatic, holistic approach, which includes comment features but also their context, such as information about users and articles. For evaluation, we present experiments on a novel corpus of 3 million news comments annotated by a team of professional moderators. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4420/ |
| https://www.aclweb.org/anthology/W18-4420 | |
| PWC | https://paperswithcode.com/paper/delete-or-not-delete-semi-automatic-comment |
| Repo | |
| Framework | |
Constructing a Chinese Medical Conversation Corpus Annotated with Conversational Structures and Actions
| Title | Constructing a Chinese Medical Conversation Corpus Annotated with Conversational Structures and Actions |
| Authors | Nan Wang, Yan Song, Fei Xia |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1464/ |
| https://www.aclweb.org/anthology/L18-1464 | |
| PWC | https://paperswithcode.com/paper/constructing-a-chinese-medical-conversation |
| Repo | |
| Framework | |
Textual Aggression Detection through Deep Learning
| Title | Textual Aggression Detection through Deep Learning |
| Authors | Antonela Tommasel, Juan Manuel Rodriguez, Daniela Godoy |
| Abstract | Cyberbullying and cyberaggression are serious and widespread issues increasingly affecting Internet users. With the widespread of social media networks, bullying, once limited to particular places, can now occur anytime and anywhere. Cyberaggression refers to aggressive online behaviour that aims at harming other individuals, and involves rude, insulting, offensive, teasing or demoralising comments through online social media. Considering the dangerous consequences that cyberaggression has on its victims and its rapid spread amongst internet users (specially kids and teens), it is crucial to understand how cyberbullying occurs to prevent it from escalating. Given the massive information overload on the Web, there is an imperious need to develop intelligent techniques to automatically detect harmful content, which would allow the large-scale social media monitoring and early detection of undesired situations. This paper presents the Isistanitos{'}s approach for detecting aggressive content in multiple social media sites. The approach is based on combining Support Vector Machines and Recurrent Neural Network models for analysing a wide-range of character, word, word embeddings, sentiment and irony features. Results confirmed the difficulty of the task (particularly for detecting covert aggressions), showing the limitations of traditionally used features. |
| Tasks | Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4421/ |
| https://www.aclweb.org/anthology/W18-4421 | |
| PWC | https://paperswithcode.com/paper/textual-aggression-detection-through-deep |
| Repo | |
| Framework | |
A Semi-autonomous System for Creating a Human-Machine Interaction Corpus in Virtual Reality: Application to the ACORFORMed System for Training Doctors to Break Bad News
| Title | A Semi-autonomous System for Creating a Human-Machine Interaction Corpus in Virtual Reality: Application to the ACORFORMed System for Training Doctors to Break Bad News |
| Authors | Magalie Ochs, Philippe Blache, Gr{'e}goire de Montcheuil, Perg, Jean-Marie i, Jorane Saubesty, Daniel Francon, Daniel Mestre |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1467/ |
| https://www.aclweb.org/anthology/L18-1467 | |
| PWC | https://paperswithcode.com/paper/a-semi-autonomous-system-for-creating-a-human |
| Repo | |
| Framework | |
Datasets of Slovene and Croatian Moderated News Comments
| Title | Datasets of Slovene and Croatian Moderated News Comments |
| Authors | Nikola Ljube{\v{s}}i{'c}, Toma{\v{z}} Erjavec, Darja Fi{\v{s}}er |
| Abstract | This paper presents two large newly constructed datasets of moderated news comments from two highly popular online news portals in the respective countries: the Slovene RTV MCC and the Croatian 24sata. The datasets are analyzed by performing manual annotation of the types of the content which have been deleted by moderators and by investigating deletion trends among users and threads. Next, initial experiments on automatically detecting the deleted content in the datasets are presented. Both datasets are published in encrypted form, to enable others to perform experiments on detecting content to be deleted without revealing potentially inappropriate content. Finally, the baseline classification models trained on the non-encrypted datasets are disseminated as well to enable real-world use. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5116/ |
| https://www.aclweb.org/anthology/W18-5116 | |
| PWC | https://paperswithcode.com/paper/datasets-of-slovene-and-croatian-moderated |
| Repo | |
| Framework | |
GenDR: A Generic Deep Realizer with Complex Lexicalization
| Title | GenDR: A Generic Deep Realizer with Complex Lexicalization |
| Authors | Fran{\c{c}}ois Lareau, Florie Lambrey, Ieva Dubinskaite, Daniel Galarreta-Piquette, Maryam Nejat |
| Abstract | |
| Tasks | Text Generation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1478/ |
| https://www.aclweb.org/anthology/L18-1478 | |
| PWC | https://paperswithcode.com/paper/gendr-a-generic-deep-realizer-with-complex |
| Repo | |
| Framework | |
From Node Embedding to Graph Embedding: Scalable Global Graph Kernel via Random Features
| Title | From Node Embedding to Graph Embedding: Scalable Global Graph Kernel via Random Features |
| Authors | Lingfei Wu, Ian En-Hsu Yen, Kun Xu, Liang Zhao, Yinglong Xia, Michael Witbrock |
| Abstract | Graph kernels are one of the most important methods for graph data analysis and have been successfully applied in diverse applications. We can generally categorize existing graph kernels into two groups: kernels based on local sub-structures, and kernels based on global properties. The first line of research compares sub-structures of graphs such as random walks, shortest paths, and graphlets. Specifically, these kernels recursively decompose the graphs into small sub-structures, and then define a feature map over these sub-structures for the resulting graph kernel. However, the aforementioned approaches only consider local patterns rather than global properties, which may substantially limit effectiveness in some applications. Equally importantly, most of these graph kernels scale poorly to large graphs due to their at-least-quadratic complexity in the number of graphs and cubic complexity in the size of each graph. |
| Tasks | Graph Embedding |
| Published | 2018-12-01 |
| URL | https://www.semanticscholar.org/paper/From-Node-Embedding-to-Graph-Embedding-%3A-Scalable-Wu-Yen/022b9c8c518898b7677e1e7ad2243207c788330d |
| https://r2learning.github.io/assets/papers/RGE_NIPS18_RRL_Workshop.pdf | |
| PWC | https://paperswithcode.com/paper/from-node-embedding-to-graph-embedding |
| Repo | |
| Framework | |
End-to-end View Synthesis for Light Field Imaging with Pseudo 4DCNN
| Title | End-to-end View Synthesis for Light Field Imaging with Pseudo 4DCNN |
| Authors | Yunlong Wang, Fei Liu, Zilei Wang, Guangqi Hou, Zhenan Sun, Tieniu Tan |
| Abstract | Limited angular resolution has become the main bottleneck of microlens-based plenoptic cameras towards practical vision applications. Existing view synthesis methods mainly break the task into two steps, i.e. depth estimating and view warping, which are usually inefficient and produce artifacts over depth ambiguities. In this paper, an end-to-end deep learning framework is proposed to solve these problems by exploring Pseudo 4DCNN. Specifically, 2D strided convolutions operated on stacked EPIs and detail-restoration 3D CNNs connected with angular conversion are assembled to build the Pseudo 4DCNN. The key advantage is to efficiently synthesize dense 4D light fields from a sparse set of input views. The learning framework is well formulated as an entirely trainable problem, and all the weights can be recursively updated with standard backpropagation. The proposed framework is compared with state-of-the-art approaches on both genuine and synthetic light field databases, which achieves significant improvements of both image quality (+2dB higher) and computational efficiency (over 10X faster). Furthermore, the proposed framework shows good performances in real-world applications such as biometrics and depth estimation. |
| Tasks | Depth Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yunlong_Wang_End-to-end_View_Synthesis_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yunlong_Wang_End-to-end_View_Synthesis_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-view-synthesis-for-light-field |
| Repo | |
| Framework | |
Learning to navigate by distilling visual information and natural language instructions
| Title | Learning to navigate by distilling visual information and natural language instructions |
| Authors | Abhishek Sinha, Akilesh B, Mausoom Sarkar, Balaji Krishnamurthy |
| Abstract | In this work, we focus on the problem of grounding language by training an agent to follow a set of natural language instructions and navigate to a target object in a 2D grid environment. The agent receives visual information through raw pixels and a natural language instruction telling what task needs to be achieved. Other than these two sources of information, our model does not have any prior information of both the visual and textual modalities and is end-to-end trainable. We develop an attention mechanism for multi-modal fusion of visual and textual modalities that allows the agent to learn to complete the navigation tasks and also achieve language grounding. Our experimental results show that our attention mechanism outperforms the existing multi-modal fusion mechanisms proposed in order to solve the above mentioned navigation task. We demonstrate through the visualization of attention weights that our model learns to correlate attributes of the object referred in the instruction with visual representations and also show that the learnt textual representations are semantically meaningful as they follow vector arithmetic and are also consistent enough to induce translation between instructions in different natural languages. We also show that our model generalizes effectively to unseen scenarios and exhibit zero-shot generalization capabilities. In order to simulate the above described challenges, we introduce a new 2D environment for an agent to jointly learn visual and textual modalities |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HJPSN3gRW |
| https://openreview.net/pdf?id=HJPSN3gRW | |
| PWC | https://paperswithcode.com/paper/learning-to-navigate-by-distilling-visual |
| Repo | |
| Framework | |
Modeling Deliberative Argumentation Strategies on Wikipedia
| Title | Modeling Deliberative Argumentation Strategies on Wikipedia |
| Authors | Khalid Al-Khatib, Henning Wachsmuth, Kevin Lang, Jakob Herpel, Matthias Hagen, Benno Stein |
| Abstract | This paper studies how the argumentation strategies of participants in deliberative discussions can be supported computationally. Our ultimate goal is to predict the best next deliberative move of each participant. In this paper, we present a model for deliberative discussions and we illustrate its operationalization. Previous models have been built manually based on a small set of discussions, resulting in a level of abstraction that is not suitable for move recommendation. In contrast, we derive our model statistically from several types of metadata that can be used for move description. Applied to six million discussions from Wikipedia talk pages, our approach results in a model with 13 categories along three dimensions: discourse acts, argumentative relations, and frames. On this basis, we automatically generate a corpus with about 200,000 turns, labeled for the 13 categories. We then operationalize the model with three supervised classifiers and provide evidence that the proposed categories can be predicted. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1237/ |
| https://www.aclweb.org/anthology/P18-1237 | |
| PWC | https://paperswithcode.com/paper/modeling-deliberative-argumentation |
| Repo | |
| Framework | |
