Paper Group NANR 166
Unlocking Fairness: a Trade-off Revisited. Meta-Learning Improves Lifelong Relation Extraction. Adversarial Category Alignment Network for Cross-domain Sentiment Classification. A Qualitative Evaluation Framework for Paraphrase Identification. Linguistically-Driven Strategy for Concept Prerequisites Learning on Italian. Deep Supervised Hashing With …
Unlocking Fairness: a Trade-off Revisited
| Title | Unlocking Fairness: a Trade-off Revisited |
| Authors | Michael Wick, Swetasudha Panda, Jean-Baptiste Tristan |
| Abstract | The prevailing wisdom is that a model’s fairness and its accuracy are in tension with one another. However, there is a pernicious {\em modeling-evaluating dualism} bedeviling fair machine learning in which phenomena such as label bias are appropriately acknowledged as a source of unfairness when designing fair models, only to be tacitly abandoned when evaluating them. We investigate fairness and accuracy, but this time under a variety of controlled conditions in which we vary the amount and type of bias. We find, under reasonable assumptions, that the tension between fairness and accuracy is illusive, and vanishes as soon as we account for these phenomena during evaluation. Moreover, our results are consistent with an opposing conclusion: fairness and accuracy are sometimes in accord. This raises the question, {\em might there be a way to harness fairness to improve accuracy after all?} Since most notions of fairness are with respect to the model’s predictions and not the ground truth labels, this provides an opportunity to see if we can improve accuracy by harnessing appropriate notions of fairness over large quantities of {\em unlabeled} data with techniques like posterior regularization and generalized expectation. Indeed, we find that semi-supervision not only improves fairness, but also accuracy and has advantages over existing in-processing methods that succumb to selection bias on the training set. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9082-unlocking-fairness-a-trade-off-revisited |
| http://papers.nips.cc/paper/9082-unlocking-fairness-a-trade-off-revisited.pdf | |
| PWC | https://paperswithcode.com/paper/unlocking-fairness-a-trade-off-revisited |
| Repo | |
| Framework | |
Meta-Learning Improves Lifelong Relation Extraction
| Title | Meta-Learning Improves Lifelong Relation Extraction |
| Authors | Abiola Obamuyide, Andreas Vlachos |
| Abstract | Most existing relation extraction models assume a fixed set of relations and are unable to adapt to exploit newly available supervision data to extract new relations. In order to alleviate such problems, there is the need to develop approaches that make relation extraction models capable of continuous adaptation and learning. We investigate and present results for such an approach, based on a combination of ideas from lifelong learning and optimization-based meta-learning. We evaluate the proposed approach on two recent lifelong relation extraction benchmarks, and demonstrate that it markedly outperforms current state-of-the-art approaches. |
| Tasks | Meta-Learning, Relation Extraction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4326/ |
| https://www.aclweb.org/anthology/W19-4326 | |
| PWC | https://paperswithcode.com/paper/meta-learning-improves-lifelong-relation |
| Repo | |
| Framework | |
Adversarial Category Alignment Network for Cross-domain Sentiment Classification
| Title | Adversarial Category Alignment Network for Cross-domain Sentiment Classification |
| Authors | Xiaoye Qu, Zhikang Zou, Yu Cheng, Yang Yang, Pan Zhou |
| Abstract | Cross-domain sentiment classification aims to predict sentiment polarity on a target domain utilizing a classifier learned from a source domain. Most existing adversarial learning methods focus on aligning the global marginal distribution by fooling a domain discriminator, without taking category-specific decision boundaries into consideration, which can lead to the mismatch of category-level features. In this work, we propose an adversarial category alignment network (ACAN), which attempts to enhance category consistency between the source domain and the target domain. Specifically, we increase the discrepancy of two polarity classifiers to provide diverse views, locating ambiguous features near the decision boundaries. Then the generator learns to create better features away from the category boundaries by minimizing this discrepancy. Experimental results on benchmark datasets show that the proposed method can achieve state-of-the-art performance and produce more discriminative features. |
| Tasks | Sentiment Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1258/ |
| https://www.aclweb.org/anthology/N19-1258 | |
| PWC | https://paperswithcode.com/paper/adversarial-category-alignment-network-for |
| Repo | |
| Framework | |
A Qualitative Evaluation Framework for Paraphrase Identification
| Title | A Qualitative Evaluation Framework for Paraphrase Identification |
| Authors | Venelin Kovatchev, M. Antonia Marti, Maria Salamo, Javier Beltran |
| Abstract | In this paper, we present a new approach for the evaluation, error analysis, and interpretation of supervised and unsupervised Paraphrase Identification (PI) systems. Our evaluation framework makes use of a PI corpus annotated with linguistic phenomena to provide a better understanding and interpretation of the performance of various PI systems. Our approach allows for a qualitative evaluation and comparison of the PI models using human interpretable categories. It does not require modification of the training objective of the systems and does not place additional burden on the developers. We replicate several popular supervised and unsupervised PI systems. Using our evaluation framework we show that: 1) Each system performs differently with respect to a set of linguistic phenomena and makes qualitatively different kinds of errors; 2) Some linguistic phenomena are more challenging than others across all systems. |
| Tasks | Paraphrase Identification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1067/ |
| https://www.aclweb.org/anthology/R19-1067 | |
| PWC | https://paperswithcode.com/paper/a-qualitative-evaluation-framework-for |
| Repo | |
| Framework | |
Linguistically-Driven Strategy for Concept Prerequisites Learning on Italian
| Title | Linguistically-Driven Strategy for Concept Prerequisites Learning on Italian |
| Authors | Alessio Miaschi, Chiara Alzetta, Franco Alberto Cardillo, Felice Dell{'}Orletta |
| Abstract | We present a new concept prerequisite learning method for Learning Object (LO) ordering that exploits only linguistic features extracted from textual educational resources. The method was tested in a cross- and in- domain scenario both for Italian and English. Additionally, we performed experiments based on a incremental training strategy to study the impact of the training set size on the classifier performances. The paper also introduces ITA-PREREQ, to the best of our knowledge the first Italian dataset annotated with prerequisite relations between pairs of educational concepts, and describe the automatic strategy devised to build it. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4430/ |
| https://www.aclweb.org/anthology/W19-4430 | |
| PWC | https://paperswithcode.com/paper/linguistically-driven-strategy-for-concept |
| Repo | |
| Framework | |
Deep Supervised Hashing With Anchor Graph
| Title | Deep Supervised Hashing With Anchor Graph |
| Authors | Yudong Chen, Zhihui Lai, Yujuan Ding, Kaiyi Lin, Wai Keung Wong |
| Abstract | Recently, a series of deep supervised hashing methods were proposed for binary code learning. However, due to the high computation cost and the limited hardware’s memory, these methods will first select a subset from the training set, and then form a mini-batch data to update the network in each iteration. Therefore, the remaining labeled data cannot be fully utilized and the model cannot directly obtain the binary codes of the entire training set for retrieval. To address these problems, this paper proposes an interesting regularized deep model to seamlessly integrate the advantages of deep hashing and efficient binary code learning by using the anchor graph. As such, the deep features and label matrix can be jointly used to optimize the binary codes, and the network can obtain more discriminative feedback from the linear combinations of the learned bits. Moreover, we also reveal the algorithm mechanism and its computation essence. Experiments on three large-scale datasets indicate that the proposed method achieves better retrieval performance with less training time compared to previous deep hashing methods. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Deep_Supervised_Hashing_With_Anchor_Graph_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Deep_Supervised_Hashing_With_Anchor_Graph_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-supervised-hashing-with-anchor-graph |
| Repo | |
| Framework | |
Predicting ICU transfers using text messages between nurses and doctors
| Title | Predicting ICU transfers using text messages between nurses and doctors |
| Authors | Faiza Khan Khattak, Chlo{'e} Pou-Prom, Robert Wu, Frank Rudzicz |
| Abstract | We explore the use of real-time clinical information, i.e., text messages sent between nurses and doctors regarding patient conditions in order to predict transfer to the intensive care unit(ICU). Preliminary results, in data from five hospitals, indicate that, despite being short and full of noise, text messages can augment other visit information to improve the performance of ICU transfer prediction. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1911/ |
| https://www.aclweb.org/anthology/W19-1911 | |
| PWC | https://paperswithcode.com/paper/predicting-icu-transfers-using-text-messages |
| Repo | |
| Framework | |
Coordination of Unlike Grammatical Functions
| Title | Coordination of Unlike Grammatical Functions |
| Authors | Agnieszka Patejuk, Adam Przepi{'o}rkowski |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7705/ |
| https://www.aclweb.org/anthology/W19-7705 | |
| PWC | https://paperswithcode.com/paper/coordination-of-unlike-grammatical-functions |
| Repo | |
| Framework | |
Statistical-Computational Tradeoff in Single Index Models
| Title | Statistical-Computational Tradeoff in Single Index Models |
| Authors | Lingxiao Wang, Zhuoran Yang, Zhaoran Wang |
| Abstract | We study the statistical-computational tradeoffs in a high dimensional single index model $Y=f(X^\top\beta^*) +\epsilon$, where $f$ is unknown, $X$ is a Gaussian vector and $\beta^*$ is $s$-sparse with unit norm. When $\cov(Y,X^\top\beta^*)\neq 0$, \cite{plan2016generalized} shows that the direction and support of $\beta^*$ can be recovered using a generalized version of Lasso. In this paper, we investigate the case when this critical assumption fails to hold, where the problem becomes considerably harder. Using the statistical query model to characterize the computational cost of an algorithm, we show that when $\cov(Y,X^\top\beta^*)=0$ and $\cov(Y,(X^\top\beta^*)^2)>0$, no computationally tractable algorithms can achieve the information-theoretic limit of the minimax risk. This implies that one must pay an extra computational cost for the nonlinearity involved in the model. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9229-statistical-computational-tradeoff-in-single-index-models |
| http://papers.nips.cc/paper/9229-statistical-computational-tradeoff-in-single-index-models.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-computational-tradeoff-in-single |
| Repo | |
| Framework | |
Doc2hash: Learning Discrete Latent variables for Documents Retrieval
| Title | Doc2hash: Learning Discrete Latent variables for Documents Retrieval |
| Authors | Yifei Zhang, Hao Zhu |
| Abstract | Learning to hash via generative model has become a powerful paradigm for fast similarity search in documents retrieval. To get binary representation (i.e., hash codes), the discrete distribution prior (i.e., Bernoulli Distribution) is applied to train the variational autoencoder (VAE). However, the discrete stochastic layer is usually incompatible with the backpropagation in the training stage, and thus causes a gradient flow problem because of non-differentiable operators. The reparameterization trick of sampling from a discrete distribution usually inc non-differentiable operators. In this paper, we propose a method, Doc2hash, that solves the gradient flow problem of the discrete stochastic layer by using continuous relaxation on priors, and trains the generative model in an end-to-end manner to generate hash codes. In qualitative and quantitative experiments, we show the proposed model outperforms other state-of-art methods. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1232/ |
| https://www.aclweb.org/anthology/N19-1232 | |
| PWC | https://paperswithcode.com/paper/doc2hash-learning-discrete-latent-variables |
| Repo | |
| Framework | |
PDE Acceleration for Active Contours
| Title | PDE Acceleration for Active Contours |
| Authors | Anthony Yezzi, Ganesh Sundaramoorthi, Minas Benyamin |
| Abstract | Following the seminal work of Nesterov, accelerated optimization methods have been used to powerfully boost the performance of first-order, gradient-based parameter estimation in scenarios where second-order optimization strategies are either inapplicable or impractical. Accelerated gradient descent converges faster and performs a more robust local search of the parameter space by initially overshooting then oscillating back into minimizers which have a basis of attraction large enough to contain the overshoot. Recent work has demonstrated how a broad class of accelerated schemes can be cast in a variational framework leading to continuum limit ODE’s. We extend their formulation to the PDE framework, specifically for the infinite dimensional manifold of continuous curves, to introduce acceleration, and its added robustness, into the broad range of PDE based active contours. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Yezzi_PDE_Acceleration_for_Active_Contours_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Yezzi_PDE_Acceleration_for_Active_Contours_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pde-acceleration-for-active-contours |
| Repo | |
| Framework | |
Rediscovering Greenberg’s Word Order Universals in UD
| Title | Rediscovering Greenberg’s Word Order Universals in UD |
| Authors | Kim Gerdes, Sylvain Kahane, Xinying Chen |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-8015/ |
| https://www.aclweb.org/anthology/W19-8015 | |
| PWC | https://paperswithcode.com/paper/rediscovering-greenbergs-word-order |
| Repo | |
| Framework | |
Unsupervised Domain Adaptation for ToF Data Denoising With Adversarial Learning
| Title | Unsupervised Domain Adaptation for ToF Data Denoising With Adversarial Learning |
| Authors | Gianluca Agresti, Henrik Schaefer, Piergiorgio Sartor, Pietro Zanuttigh |
| Abstract | Time-of-Flight data is typically affected by a high level of noise and by artifacts due to Multi-Path Interference (MPI). While various traditional approaches for ToF data improvement have been proposed, machine learning techniques have seldom been applied to this task, mostly due to the limited availability of real world training data with depth ground truth. In this paper, we avoid to rely on labeled real data in the learning framework. A Coarse-Fine CNN, able to exploit multi-frequency ToF data for MPI correction, is trained on synthetic data with ground truth in a supervised way. In parallel, an adversarial learning strategy, based on the Generative Adversarial Networks (GAN) framework, is used to perform an unsupervised pixel-level domain adaptation from synthetic to real world data, exploiting unlabeled real world acquisitions. Experimental results demonstrate that the proposed approach is able to effectively denoise real world data and to outperform state-of-the-art techniques. |
| Tasks | Denoising, Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Agresti_Unsupervised_Domain_Adaptation_for_ToF_Data_Denoising_With_Adversarial_Learning_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Agresti_Unsupervised_Domain_Adaptation_for_ToF_Data_Denoising_With_Adversarial_Learning_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-for-tof-data |
| Repo | |
| Framework | |
MAssistant: A Personal Knowledge Assistant for MOOC Learners
| Title | MAssistant: A Personal Knowledge Assistant for MOOC Learners |
| Authors | Lan Jiang, Shuhan Hu, Mingyu Huang, Zhichun Wang, Jinjian Yang, Xiaoju Ye, Wei Zheng |
| Abstract | Massive Open Online Courses (MOOCs) have developed rapidly and attracted large number of learners. In this work, we present MAssistant system, a personal knowledge assistant for MOOC learners. MAssistant helps users to trace the concepts they have learned in MOOCs, and to build their own concept graphs. There are three key components in MAssistant: (i) a large-scale concept graph built from open data sources, which contains concepts in various domains and relations among them; (ii) a browser extension which interacts with learners when they are watching video lectures, and presents important concepts to them; (iii) a web application allowing users to explore their personal concept graphs, which are built based on their learning activities on MOOCs. MAssistant will facilitate the knowledge management task for MOOC learners, and make the learning on MOOCs easier. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3023/ |
| https://www.aclweb.org/anthology/D19-3023 | |
| PWC | https://paperswithcode.com/paper/massistant-a-personal-knowledge-assistant-for |
| Repo | |
| Framework | |
Mazajak: An Online Arabic Sentiment Analyser
| Title | Mazajak: An Online Arabic Sentiment Analyser |
| Authors | Ibrahim Abu Farha, Walid Magdy |
| Abstract | Sentiment analysis (SA) is one of the most useful natural language processing applications. Literature is flooding with many papers and systems addressing this task, but most of the work is focused on English. In this paper, we present {``}Mazajak{''}, an online system for Arabic SA. The system is based on a deep learning model, which achieves state-of-the-art results on many Arabic dialect datasets including SemEval 2017 and ASTD. The availability of such system should assist various applications and research that rely on sentiment analysis as a tool. | |
| Tasks | Arabic Sentiment Analysis, Sentiment Analysis, Twitter Sentiment Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4621/ |
| https://www.aclweb.org/anthology/W19-4621 | |
| PWC | https://paperswithcode.com/paper/mazajak-an-online-arabic-sentiment-analyser |
| Repo | |
| Framework | |
