Paper Group NANR 210
Equality of Opportunity in Classification: A Causal Approach. DNN Model Compression Under Accuracy Constraints. Cross-lingual complex word identification with multitask learning. PARAMETRIZED DEEP Q-NETWORKS LEARNING: PLAYING ONLINE BATTLE ARENA WITH DISCRETE-CONTINUOUS HYBRID ACTION SPACE. Automatic Detection of Atrial Fibrillation Based on Contin …
Equality of Opportunity in Classification: A Causal Approach
| Title | Equality of Opportunity in Classification: A Causal Approach |
| Authors | Junzhe Zhang, Elias Bareinboim |
| Abstract | The Equalized Odds (for short, EO) is one of the most popular measures of discrimination used in the supervised learning setting. It ascertains fairness through the balance of the misclassification rates (false positive and negative) across the protected groups – e.g., in the context of law enforcement, an African-American defendant who would not commit a future crime will have an equal opportunity of being released, compared to a non-recidivating Caucasian defendant. Despite this noble goal, it has been acknowledged in the literature that statistical tests based on the EO are oblivious to the underlying causal mechanisms that generated the disparity in the first place (Hardt et al. 2016). This leads to a critical disconnect between statistical measures readable from the data and the meaning of discrimination in the legal system, where compelling evidence that the observed disparity is tied to a specific causal process deemed unfair by society is required to characterize discrimination. The goal of this paper is to develop a principled approach to connect the statistical disparities characterized by the EO and the underlying, elusive, and frequently unobserved, causal mechanisms that generated such inequality. We start by introducing a new family of counterfactual measures that allows one to explain the misclassification disparities in terms of the underlying mechanisms in an arbitrary, non-parametric structural causal model. This will, in turn, allow legal and data analysts to interpret currently deployed classifiers through causal lens, linking the statistical disparities found in the data to the corresponding causal processes. Leveraging the new family of counterfactual measures, we develop a learning procedure to construct a classifier that is statistically efficient, interpretable, and compatible with the basic human intuition of fairness. We demonstrate our results through experiments in both real (COMPAS) and synthetic datasets. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7625-equality-of-opportunity-in-classification-a-causal-approach |
| http://papers.nips.cc/paper/7625-equality-of-opportunity-in-classification-a-causal-approach.pdf | |
| PWC | https://paperswithcode.com/paper/equality-of-opportunity-in-classification-a |
| Repo | |
| Framework | |
DNN Model Compression Under Accuracy Constraints
| Title | DNN Model Compression Under Accuracy Constraints |
| Authors | Soroosh Khoram, Jing Li |
| Abstract | The growing interest to implement Deep Neural Networks (DNNs) on resource-bound hardware has motivated innovation of compression algorithms. Using these algorithms, DNN model sizes can be substantially reduced, with little to no accuracy degradation. This is achieved by either eliminating components from the model, or penalizing complexity during training. While both approaches demonstrate considerable compressions, the former often ignores the loss function during compression while the later produces unpredictable compressions. In this paper, we propose a technique that directly minimizes both the model complexity and the changes in the loss function. In this technique, we formulate compression as a constrained optimization problem, and then present a solution for it. We will show that using this technique, we can achieve competitive results. |
| Tasks | Model Compression |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=By0ANxbRW |
| https://openreview.net/pdf?id=By0ANxbRW | |
| PWC | https://paperswithcode.com/paper/dnn-model-compression-under-accuracy |
| Repo | |
| Framework | |
Cross-lingual complex word identification with multitask learning
| Title | Cross-lingual complex word identification with multitask learning |
| Authors | Joachim Bingel, Johannes Bjerva |
| Abstract | We approach the 2018 Shared Task on Complex Word Identification by leveraging a cross-lingual multitask learning approach. Our method is highly language agnostic, as evidenced by the ability of our system to generalize across languages, including languages for which we have no training data. In the shared task, this is the case for French, for which our system achieves the best performance. We further provide a qualitative and quantitative analysis of which words pose problems for our system. |
| Tasks | Complex Word Identification, Lexical Simplification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0518/ |
| https://www.aclweb.org/anthology/W18-0518 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-complex-word-identification |
| Repo | |
| Framework | |
PARAMETRIZED DEEP Q-NETWORKS LEARNING: PLAYING ONLINE BATTLE ARENA WITH DISCRETE-CONTINUOUS HYBRID ACTION SPACE
| Title | PARAMETRIZED DEEP Q-NETWORKS LEARNING: PLAYING ONLINE BATTLE ARENA WITH DISCRETE-CONTINUOUS HYBRID ACTION SPACE |
| Authors | Jiechao Xiong, Qing Wang, Zhuoran Yang, Peng Sun, Yang Zheng, Lei Han, Haobo Fu, Xiangru Lian, Carson Eisenach, Haichuan Yang, Emmanuel Ekwedike, Bei Peng, Haoyue Gao, Tong Zhang, Ji Liu, Han Liu |
| Abstract | Most existing deep reinforcement learning (DRL) frameworks consider action spaces that are either discrete or continuous space. Motivated by the project of design Game AI for King of Glory (KOG), one the world’s most popular mobile game, we consider the scenario with the discrete-continuous hybrid action space. To directly apply existing DLR frameworks, existing approaches either approximate the hybrid space by a discrete set or relaxing it into a continuous set, which is usually less efficient and robust. In this paper, we propose a parametrized deep Q-network (P-DQN) for the hybrid action space without approximation or relaxation. Our algorithm combines DQN and DDPG and can be viewed as an extension of the DQN to hybrid actions. The empirical study on the game KOG validates the efficiency and effectiveness of our method. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=Sy_MK3lAZ |
| https://openreview.net/pdf?id=Sy_MK3lAZ | |
| PWC | https://paperswithcode.com/paper/parametrized-deep-q-networks-learning-playing |
| Repo | |
| Framework | |
Automatic Detection of Atrial Fibrillation Based on Continuous Wavelet Transform and 2D Convolutional Neural Networks
| Title | Automatic Detection of Atrial Fibrillation Based on Continuous Wavelet Transform and 2D Convolutional Neural Networks |
| Authors | Runnan He, Kuanquan Wang, Na Zhao, Yang Liu, Yongfeng Yuan, Qince Li, Henggui Zhang |
| Abstract | Atrial fibrillation (AF) is the most common cardiac arrhythmias causing morbidity and mortality. AF may appear as episodes of very short (i.e., proximal AF) or sustained duration (i.e., persistent AF), either form of which causes irregular ventricular excitations that affect the global function of the heart. It is an unmet challenge for early and automatic detection of AF, limiting efficient treatment strategies for AF. In this study, we developed a new method based on continuous wavelet transform and 2D convolutional neural networks (CNNs) to detect AF episodes. The proposed method analyzed the time-frequency features of the electrocardiogram (ECG), thus being different to conventional AF detecting methods that implement isolating atrial or ventricular activities. Then a 2D CNN was trained to improve AF detection performance. The MIT-BIH Atrial Fibrillation Database was used for evaluating the algorithm. The efficacy of the proposed method was compared with those of some existing methods, most of which implemented the same dataset. The newly developed algorithm using CNNs achieved 99.41, 98.91, 99.39, and 99.23% for the sensitivity, specificity, positive predictive value, and overall accuracy (ACC) respectively. As the proposed algorithm targets the time-frequency feature of ECG signals rather than isolated atrial or ventricular activity, it has the ability to detect AF episodes for using just five beats, suggesting practical applications in the future. |
| Tasks | Atrial Fibrillation Detection, Electrocardiography (ECG) |
| Published | 2018-08-30 |
| URL | https://dx.doi.org/10.3389%2Ffphys.2018.01206 |
| https://www.frontiersin.org/articles/10.3389/fphys.2018.01206/pdf | |
| PWC | https://paperswithcode.com/paper/automatic-detection-of-atrial-fibrillation |
| Repo | |
| Framework | |
UNSUPERVISED METRIC LEARNING VIA NONLINEAR FEATURE SPACE TRANSFORMATIONS
| Title | UNSUPERVISED METRIC LEARNING VIA NONLINEAR FEATURE SPACE TRANSFORMATIONS |
| Authors | Pin Zhang, Bibo Shi, JundongLiu |
| Abstract | In this paper, we propose a nonlinear unsupervised metric learning framework to boost of the performance of clustering algorithms. Under our framework, nonlinear distance metric learning and manifold embedding are integrated and conducted simultaneously to increase the natural separations among data samples. The metric learning component is implemented through feature space transformations, regulated by a nonlinear deformable model called Coherent Point Drifting (CPD). Driven by CPD, data points can get to a higher level of linear separability, which is subsequently picked up by the manifold embedding component to generate well-separable sample projections for clustering. Experimental results on synthetic and benchmark datasets show the effectiveness of our proposed approach over the state-of-the-art solutions in unsupervised metric learning. |
| Tasks | Metric Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SJu63o10b |
| https://openreview.net/pdf?id=SJu63o10b | |
| PWC | https://paperswithcode.com/paper/unsupervised-metric-learning-via-nonlinear |
| Repo | |
| Framework | |
Multi-domain Causal Structure Learning in Linear Systems
| Title | Multi-domain Causal Structure Learning in Linear Systems |
| Authors | Amiremad Ghassami, Negar Kiyavash, Biwei Huang, Kun Zhang |
| Abstract | We study the problem of causal structure learning in linear systems from observational data given in multiple domains, across which the causal coefficients and/or the distribution of the exogenous noises may vary. The main tool used in our approach is the principle that in a causally sufficient system, the causal modules, as well as their included parameters, change independently across domains. We first introduce our approach for finding causal direction in a system comprising two variables and propose efficient methods for identifying causal direction. Then we generalize our methods to causal structure learning in networks of variables. Most of previous work in structure learning from multi-domain data assume that certain types of invariance are held in causal modules across domains. Our approach unifies the idea in those works and generalizes to the case that there is no such invariance across the domains. Our proposed methods are generally capable of identifying causal direction from fewer than ten domains. When the invariance property holds, two domains are generally sufficient. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7864-multi-domain-causal-structure-learning-in-linear-systems |
| http://papers.nips.cc/paper/7864-multi-domain-causal-structure-learning-in-linear-systems.pdf | |
| PWC | https://paperswithcode.com/paper/multi-domain-causal-structure-learning-in |
| Repo | |
| Framework | |
Using Wikipedia Edits in Low Resource Grammatical Error Correction
| Title | Using Wikipedia Edits in Low Resource Grammatical Error Correction |
| Authors | Adriane Boyd |
| Abstract | We develop a grammatical error correction (GEC) system for German using a small gold GEC corpus augmented with edits extracted from Wikipedia revision history. We extend the automatic error annotation tool ERRANT (Bryant et al., 2017) for German and use it to analyze both gold GEC corrections and Wikipedia edits (Grundkiewicz and Junczys-Dowmunt, 2014) in order to select as additional training data Wikipedia edits containing grammatical corrections similar to those in the gold corpus. Using a multilayer convolutional encoder-decoder neural network GEC approach (Chollampatt and Ng, 2018), we evaluate the contribution of Wikipedia edits and find that carefully selected Wikipedia edits increase performance by over 5{%}. |
| Tasks | Grammatical Error Correction, Machine Translation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6111/ |
| https://www.aclweb.org/anthology/W18-6111 | |
| PWC | https://paperswithcode.com/paper/using-wikipedia-edits-in-low-resource |
| Repo | |
| Framework | |
A Deep Neural Network based Approach for Entity Extraction in Code-Mixed Indian Social Media Text
| Title | A Deep Neural Network based Approach for Entity Extraction in Code-Mixed Indian Social Media Text |
| Authors | Deepak Gupta, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | |
| Tasks | Entity Extraction, Named Entity Recognition, Opinion Mining, Part-Of-Speech Tagging |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1278/ |
| https://www.aclweb.org/anthology/L18-1278 | |
| PWC | https://paperswithcode.com/paper/a-deep-neural-network-based-approach-for |
| Repo | |
| Framework | |
Quality Estimation with Force-Decoded Attention and Cross-lingual Embeddings
| Title | Quality Estimation with Force-Decoded Attention and Cross-lingual Embeddings |
| Authors | Elizaveta Yankovskaya, Andre T{"a}ttar, Mark Fishel |
| Abstract | This paper describes the submissions of the team from the University of Tartu for the sentence-level Quality Estimation shared task of WMT18. The proposed models use features based on attention weights of a neural machine translation system and cross-lingual phrase embeddings as input features of a regression model. Two of the proposed models require only a neural machine translation system with an attention mechanism with no additional resources. Results show that combining neural networks and baseline features leads to significant improvements over the baseline features alone. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6466/ |
| https://www.aclweb.org/anthology/W18-6466 | |
| PWC | https://paperswithcode.com/paper/quality-estimation-with-force-decoded |
| Repo | |
| Framework | |
The Speechmatics Parallel Corpus Filtering System for WMT18
| Title | The Speechmatics Parallel Corpus Filtering System for WMT18 |
| Authors | Tom Ash, Remi Francis, Will Williams |
| Abstract | Our entry to the parallel corpus filtering task uses a two-step strategy. The first step uses a series of pragmatic hard {`}rules{'} to remove the worst example sentences. This first step reduces the effective corpus size down from the initial 1 billion to 160 million tokens. The second step uses four different heuristics weighted to produce a score that is then used for further filtering down to 100 or 10 million tokens. Our final system produces competitive results without requiring excessive fine tuning to the exact task or language pair. The first step in isolation provides a very fast filter that gives most of the gains of the final system. | |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6472/ |
| https://www.aclweb.org/anthology/W18-6472 | |
| PWC | https://paperswithcode.com/paper/the-speechmatics-parallel-corpus-filtering |
| Repo | |
| Framework | |
MoNet: Deep Motion Exploitation for Video Object Segmentation
| Title | MoNet: Deep Motion Exploitation for Video Object Segmentation |
| Authors | Huaxin Xiao, Jiashi Feng, Guosheng Lin, Yu Liu, Maojun Zhang |
| Abstract | In this paper, we propose a novel MoNet model to deeply exploit motion cues for boosting video object segmentation performance from two aspects, i.e., frame representation learning and segmentation refinement. Concretely, MoNet exploits computed motion cue (i.e., optical flow) to reinforce the representation of the target frame by aligning and integrating representations from its neighbors. The new representation provides valuable temporal contexts for segmentation and improves robustness to various common contaminating factors, e.g., motion blur, appearance variation and deformation of video objects. Moreover, MoNet exploits motion inconsistency and transforms such motion cue into foreground/background prior to eliminate distraction from confusing instances and noisy regions. By introducing a distance transform layer, MoNet can effectively separate motion-inconstant instances/regions and thoroughly refine segmentation results. Integrating the proposed two motion exploitation components with a standard segmentation network, MoNet provides new state-of-the-art performance on three competitive benchmark datasets. |
| Tasks | Optical Flow Estimation, Representation Learning, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Xiao_MoNet_Deep_Motion_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Xiao_MoNet_Deep_Motion_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/monet-deep-motion-exploitation-for-video |
| Repo | |
| Framework | |
Motion-Guided Cascaded Refinement Network for Video Object Segmentation
| Title | Motion-Guided Cascaded Refinement Network for Video Object Segmentation |
| Authors | Ping Hu, Gang Wang, Xiangfei Kong, Jason Kuen, Yap-Peng Tan |
| Abstract | Deep CNNs have achieved superior performance in many tasks of computer vision and image understanding. However, it is still difficult to effectively apply deep CNNs to video object segmentation(VOS) since treating video frames as separate and static will lose the information hidden in motion. To tackle this problem, we propose a Motion-guided Cascaded Refinement Network for VOS. By assuming the object motion is normally different from the background motion, for a video frame we first apply an active contour model on optical flow to coarsely segment objects of interest. Then, the proposed Cascaded Refinement Network(CRN) takes the coarse segmentation as guidance to generate an accurate segmentation of full resolution. In this way, the motion information and the deep CNNs can well complement each other to accurately segment objects from video frames. Furthermore, in CRN we introduce a Single-channel Residual Attention Module to incorporate the coarse segmentation map as attention, making our network effective and efficient in both training and testing. We perform experiments on the popular benchmarks and the results show that our method achieves state-of-the-art performance at a much faster speed. |
| Tasks | Optical Flow Estimation, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Hu_Motion-Guided_Cascaded_Refinement_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Motion-Guided_Cascaded_Refinement_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/motion-guided-cascaded-refinement-network-for |
| Repo | |
| Framework | |
Tutorial: Corpora Quality Management for MT - Practices and Roles
| Title | Tutorial: Corpora Quality Management for MT - Practices and Roles |
| Authors | Silvio Picinini, Pete Smith, Nicola Ueffing |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1926/ |
| https://www.aclweb.org/anthology/W18-1926 | |
| PWC | https://paperswithcode.com/paper/tutorial-corpora-quality-management-for-mt |
| Repo | |
| Framework | |
Portable Speech-to-Speech Translation on an Android Smartphone: The MFLTS System
| Title | Portable Speech-to-Speech Translation on an Android Smartphone: The MFLTS System |
| Authors | Ralf Meermeier, Sean Colbath, Martha Lillie |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1923/ |
| https://www.aclweb.org/anthology/W18-1923 | |
| PWC | https://paperswithcode.com/paper/portable-speech-to-speech-translation-on-an |
| Repo | |
| Framework | |
