Paper Group NANR 45
Video Prediction via Selective Sampling. NEUROSENT-PDI at SemEval-2018 Task 3: Understanding Irony in Social Networks Through a Multi-Domain Sentiment Model. Learning to Treat Sepsis with Multi-Output Gaussian Process Deep Recurrent Q-Networks. A Neural Local Coherence Model for Text Quality Assessment. ``Fingers in the Nose’': Evaluating Speakers’ …
Video Prediction via Selective Sampling
Title | Video Prediction via Selective Sampling |
Authors | Jingwei Xu, Bingbing Ni, Xiaokang Yang |
Abstract | Most adversarial learning based video prediction methods suffer from image blur, since the commonly used adversarial and regression loss pair work rather in a competitive way than collaboration, yielding compromised blur effect. In the meantime, as often relying on a single-pass architecture, the predictor is inadequate to explicitly capture the forthcoming uncertainty. Our work involves two key insights: (1) Video prediction can be approached as a stochastic process: we sample a collection of proposals conforming to possible frame distribution at following time stamp, and one can select the final prediction from it. (2) De-coupling combined loss functions into dedicatedly designed sub-networks encourages them to work in a collaborative way. Combining above two insights we propose a two-stage network called VPSS (\textbf{V}ideo \textbf{P}rediction via \textbf{S}elective \textbf{S}ampling). Specifically a \emph{Sampling} module produces a collection of high quality proposals, facilitated by a multiple choice adversarial learning scheme, yielding diverse frame proposal set. Subsequently a \emph{Selection} module selects high possibility candidates from proposals and combines them to produce final prediction. Extensive experiments on diverse challenging datasets demonstrate the effectiveness of proposed video prediction approach, i.e., yielding more diverse proposals and accurate prediction results. |
Tasks | Video Prediction |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7442-video-prediction-via-selective-sampling |
http://papers.nips.cc/paper/7442-video-prediction-via-selective-sampling.pdf | |
PWC | https://paperswithcode.com/paper/video-prediction-via-selective-sampling |
Repo | |
Framework | |
NEUROSENT-PDI at SemEval-2018 Task 3: Understanding Irony in Social Networks Through a Multi-Domain Sentiment Model
Title | NEUROSENT-PDI at SemEval-2018 Task 3: Understanding Irony in Social Networks Through a Multi-Domain Sentiment Model |
Authors | Mauro Dragoni |
Abstract | This paper describes the NeuroSent system that participated in SemEval 2018 Task 3. Our system takes a supervised approach that builds on neural networks and word embeddings. Word embeddings were built by starting from a repository of user generated reviews. Thus, they are specific for sentiment analysis tasks. Then, tweets are converted in the corresponding vector representation and given as input to the neural network with the aim of learning the different semantics contained in each emotion taken into account by the SemEval task. The output layer has been adapted based on the characteristics of each subtask. Preliminary results obtained on the provided training set are encouraging for pursuing the investigation into this direction. |
Tasks | Sentiment Analysis, Word Embeddings |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1083/ |
https://www.aclweb.org/anthology/S18-1083 | |
PWC | https://paperswithcode.com/paper/neurosent-pdi-at-semeval-2018-task-3 |
Repo | |
Framework | |
Learning to Treat Sepsis with Multi-Output Gaussian Process Deep Recurrent Q-Networks
Title | Learning to Treat Sepsis with Multi-Output Gaussian Process Deep Recurrent Q-Networks |
Authors | Joseph Futoma, Anthony Lin, Mark Sendak, Armando Bedoya, Meredith Clement, Cara O’Brien, Katherine Heller |
Abstract | Sepsis is a life-threatening complication from infection and a leading cause of mortality in hospitals. While early detection of sepsis improves patient outcomes, there is little consensus on exact treatment guidelines, and treating septic patients remains an open problem. In this work we present a new deep reinforcement learning method that we use to learn optimal personalized treatment policies for septic patients. We model patient continuous-valued physiological time series using multi-output Gaussian processes, a probabilistic model that easily handles missing values and irregularly spaced observation times while maintaining estimates of uncertainty. The Gaussian process is directly tied to a deep recurrent Q-network that learns clinically interpretable treatment policies, and both models are learned together end-to-end. We evaluate our approach on a heterogeneous dataset of septic spanning 15 months from our university health system, and find that our learned policy could reduce patient mortality by as much as 8.2% from an overall baseline mortality rate of 13.3%. Our algorithm could be used to make treatment recommendations to physicians as part of a decision support tool, and the framework readily applies to other reinforcement learning problems that rely on sparsely sampled and frequently missing multivariate time series data. |
Tasks | Gaussian Processes, Time Series |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=SyxCqGbRZ |
https://openreview.net/pdf?id=SyxCqGbRZ | |
PWC | https://paperswithcode.com/paper/learning-to-treat-sepsis-with-multi-output |
Repo | |
Framework | |
A Neural Local Coherence Model for Text Quality Assessment
Title | A Neural Local Coherence Model for Text Quality Assessment |
Authors | Mohsen Mesgar, Michael Strube |
Abstract | We propose a local coherence model that captures the flow of what semantically connects adjacent sentences in a text. We represent the semantics of a sentence by a vector and capture its state at each word of the sentence. We model what relates two adjacent sentences based on the two most similar semantic states, each of which is in one of the sentences. We encode the perceived coherence of a text by a vector, which represents patterns of changes in salient information that relates adjacent sentences. Our experiments demonstrate that our approach is beneficial for two downstream tasks: Readability assessment, in which our model achieves new state-of-the-art results; and essay scoring, in which the combination of our coherence vectors and other task-dependent features significantly improves the performance of a strong essay scorer. |
Tasks | Word Embeddings |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1464/ |
https://www.aclweb.org/anthology/D18-1464 | |
PWC | https://paperswithcode.com/paper/a-neural-local-coherence-model-for-text |
Repo | |
Framework | |
``Fingers in the Nose’': Evaluating Speakers’ Identification of Multi-Word Expressions Using a Slightly Gamified Crowdsourcing Platform
Title | ``Fingers in the Nose’': Evaluating Speakers’ Identification of Multi-Word Expressions Using a Slightly Gamified Crowdsourcing Platform | |
Authors | Kar{"e}n Fort, Bruno Guillaume, Matthieu Constant, Nicolas Lef{`e}bvre, Yann-Alan Pilatte |
Abstract | This article presents the results we obtained in crowdsourcing French speakers{'} intuition concerning multi-work expressions (MWEs). We developed a slightly gamified crowdsourcing platform, part of which is designed to test users{'} ability to identify MWEs with no prior training. The participants perform relatively well at the task, with a recall reaching 65{%} for MWEs that do not behave as function words. |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4923/ |
https://www.aclweb.org/anthology/W18-4923 | |
PWC | https://paperswithcode.com/paper/fingers-in-the-nose-evaluating-speakersa |
Repo | |
Framework | |
Interpreting Neural Network Hate Speech Classifiers
Title | Interpreting Neural Network Hate Speech Classifiers |
Authors | Cindy Wang |
Abstract | Deep neural networks have been applied to hate speech detection with apparent success, but they have limited practical applicability without transparency into the predictions they make. In this paper, we perform several experiments to visualize and understand a state-of-the-art neural network classifier for hate speech (Zhang et al., 2018). We adapt techniques from computer vision to visualize sensitive regions of the input stimuli and identify the features learned by individual neurons. We also introduce a method to discover the keywords that are most predictive of hate speech. Our analyses explain the aspects of neural networks that work well and point out areas for further improvement. |
Tasks | Hate Speech Detection, Text Classification |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/W18-5111/ |
https://www.aclweb.org/anthology/W18-5111 | |
PWC | https://paperswithcode.com/paper/interpreting-neural-network-hate-speech |
Repo | |
Framework | |
SciREL at SemEval-2018 Task 7: A System for Semantic Relation Extraction and Classification
Title | SciREL at SemEval-2018 Task 7: A System for Semantic Relation Extraction and Classification |
Authors | Darshini Mahendran, Chathurika Brahmana, Bridget McInnes |
Abstract | This paper describes our system, SciREL (Scientific abstract RELation extraction system), developed for the SemEval 2018 Task 7: Semantic Relation Extraction and Classification in Scientific Papers. We present a feature-vector based system to extract explicit semantic relation and classify them. Our system is trained in the ACL corpus (BIrd et al., 2008) that contains annotated abstracts given by the task organizers. When an abstract with annotated entities is given as the input into our system, it extracts the semantic relations through a set of defined features and classifies them into one of the given six categories of relations through feature engineering and a learned model. For the best combination of features, our system SciREL obtained an F-measure of 20.03 on the official test corpus which includes 150 abstracts in the relation classification Subtask 1.1. In this paper, we provide an in-depth error analysis of our results to prevent duplication of research efforts in the development of future systems |
Tasks | Feature Engineering, Relation Classification, Relation Extraction |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1137/ |
https://www.aclweb.org/anthology/S18-1137 | |
PWC | https://paperswithcode.com/paper/scirel-at-semeval-2018-task-7-a-system-for |
Repo | |
Framework | |
Semi-Automatic Construction of Word-Formation Networks (for Polish and Spanish)
Title | Semi-Automatic Construction of Word-Formation Networks (for Polish and Spanish) |
Authors | Mateusz Lango, Magda {\v{S}}ev{\v{c}}{'\i}kov{'a}, Zden{\v{e}}k {\v{Z}}abokrtsk{'y} |
Abstract | |
Tasks | Learning-To-Rank, Sequential Pattern Mining |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1291/ |
https://www.aclweb.org/anthology/L18-1291 | |
PWC | https://paperswithcode.com/paper/semi-automatic-construction-of-word-formation |
Repo | |
Framework | |
Book Review: Automatic Text Simplification by Horacio Saggion
Title | Book Review: Automatic Text Simplification by Horacio Saggion |
Authors | Xiaojun Wan |
Abstract | |
Tasks | Lexical Simplification, Text Generation, Text Simplification |
Published | 2018-12-01 |
URL | https://www.aclweb.org/anthology/J18-4005/ |
https://www.aclweb.org/anthology/J18-4005 | |
PWC | https://paperswithcode.com/paper/book-review-automatic-text-simplification-by |
Repo | |
Framework | |
Proceedings of the First Workshop on Economics and Natural Language Processing
Title | Proceedings of the First Workshop on Economics and Natural Language Processing |
Authors | |
Abstract | |
Tasks | |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-3100/ |
https://www.aclweb.org/anthology/W18-3100 | |
PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-3 |
Repo | |
Framework | |
Thwarting Adversarial Examples: An L_0-Robust Sparse Fourier Transform
Title | Thwarting Adversarial Examples: An L_0-Robust Sparse Fourier Transform |
Authors | Mitali Bafna, Jack Murtagh, Nikhil Vyas |
Abstract | We give a new algorithm for approximating the Discrete Fourier transform of an approximately sparse signal that is robust to worst-case $L_0$ corruptions, namely that some coordinates of the signal can be corrupt arbitrarily. Our techniques generalize to a wide range of linear transformations that are used in data analysis such as the Discrete Cosine and Sine transforms, the Hadamard transform, and their high-dimensional analogs. We use our algorithm to successfully defend against worst-case $L_0$ adversaries in the setting of image classification. We give experimental results on the Jacobian-based Saliency Map Attack (JSMA) and the CW $L_0$ attack on the MNIST and Fashion-MNIST datasets as well as the Adversarial Patch on the ImageNet dataset. |
Tasks | Image Classification |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8211-thwarting-adversarial-examples-an-l_0-robust-sparse-fourier-transform |
http://papers.nips.cc/paper/8211-thwarting-adversarial-examples-an-l_0-robust-sparse-fourier-transform.pdf | |
PWC | https://paperswithcode.com/paper/thwarting-adversarial-examples-an-l_0-robust |
Repo | |
Framework | |
Implicit and Explicit Aspect Extraction in Financial Microblogs
Title | Implicit and Explicit Aspect Extraction in Financial Microblogs |
Authors | Thomas Gaillat, Bernardo Stearns, Gopal Sridhar, Ross McDermott, Manel Zarrouk, Brian Davis |
Abstract | This paper focuses on aspect extraction which is a sub-task of Aspect-based Sentiment Analysis. The goal is to report an extraction method of financial aspects in microblog messages. Our approach uses a stock-investment taxonomy for the identification of explicit and implicit aspects. We compare supervised and unsupervised methods to assign predefined categories at message level. Results on 7 aspect classes show 0.71 accuracy, while the 32 class classification gives 0.82 accuracy for messages containing explicit aspects and 0.35 for implicit aspects. |
Tasks | Aspect-Based Sentiment Analysis, Aspect Extraction, Sentiment Analysis |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-3108/ |
https://www.aclweb.org/anthology/W18-3108 | |
PWC | https://paperswithcode.com/paper/implicit-and-explicit-aspect-extraction-in |
Repo | |
Framework | |
A Hybrid Approach for Automatic Extraction of Bilingual Multiword Expressions from Parallel Corpora
Title | A Hybrid Approach for Automatic Extraction of Bilingual Multiword Expressions from Parallel Corpora |
Authors | Nasredine Semmar |
Abstract | |
Tasks | Domain Adaptation, Information Retrieval, Machine Translation, Word Alignment |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1047/ |
https://www.aclweb.org/anthology/L18-1047 | |
PWC | https://paperswithcode.com/paper/a-hybrid-approach-for-automatic-extraction-of |
Repo | |
Framework | |
TOWARDS ROBOT VISION MODULE DEVELOPMENT WITH EXPERIENTIAL ROBOT LEARNING
Title | TOWARDS ROBOT VISION MODULE DEVELOPMENT WITH EXPERIENTIAL ROBOT LEARNING |
Authors | Ahmed A Aly, Joanne Bechta Dugan |
Abstract | n this paper we present a thrust in three directions of visual development us- ing supervised and semi-supervised techniques. The first is an implementation of semi-supervised object detection and recognition using the principles of Soft At- tention and Generative Adversarial Networks (GANs). The second and the third are supervised networks that learn basic concepts of spatial locality and quantity respectively using Convolutional Neural Networks (CNNs). The three thrusts to- gether are based on the approach of Experiential Robot Learning, introduced in previous publication. While the results are unripe for implementation, we believe they constitute a stepping stone towards autonomous development of robotic vi- sual modules. |
Tasks | Object Detection |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=H1BHbmWCZ |
https://openreview.net/pdf?id=H1BHbmWCZ | |
PWC | https://paperswithcode.com/paper/towards-robot-vision-module-development-with |
Repo | |
Framework | |
Temporal Deformable Residual Networks for Action Segmentation in Videos
Title | Temporal Deformable Residual Networks for Action Segmentation in Videos |
Authors | Peng Lei, Sinisa Todorovic |
Abstract | This paper is about temporal segmentation of human actions in videos. We introduce a new model – temporal deformable residual network (TDRN) – aimed at analyzing video intervals at multiple temporal scales for labeling video frames. Our TDRN computes two parallel temporal streams: i) Residual stream that analyzes video information at its full temporal resolution, and ii) Pooling/unpooling stream that captures long-range video information at different scales. The former facilitates local, fine-scale action segmentation, and the latter uses multiscale context for improving accuracy of frame classification. These two streams are computed by a set of temporal residual modules with deformable convolutions, and fused by temporal residuals at the full video resolution. Our evaluation on the University of Dundee 50 Salads, Georgia Tech Egocentric Activities, and JHU-ISI Gesture and Skill Assessment Working Set demonstrates that TDRN outperforms the state of the art in frame-wise segmentation accuracy, segmental edit score, and segmental overlap F1 score. |
Tasks | action segmentation |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Lei_Temporal_Deformable_Residual_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Lei_Temporal_Deformable_Residual_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/temporal-deformable-residual-networks-for |
Repo | |
Framework | |