Paper Group NANR 189
Handling missing values: A study of popular imputation packages in R. Variational Network Inference: Strong and Stable with Concrete Support. DiCE: The Infinitely Differentiable Monte Carlo Estimator. A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check. Leveraging Lexical Substitutes for Unsupervised Word Sense Induction. Im …
Handling missing values: A study of popular imputation packages in R
| Title | Handling missing values: A study of popular imputation packages in R |
| Authors | Madan Lal Yadav, Basav Roychoudhury |
| Abstract | In real world data are often plagued by missing values which adversely affects the final outcome of the analysis based on such data. The missing values can be handled using various techniques like deletion or imputation. Of late, R has become one of the most preferred platform for carrying out data analysis, and its popularity is growing further. R provides various packages for handling missing values through imputation. The presence of multiple packages however, calls for an analysis of their comparative performance and examine their suitability for handling a given set of data. The performance of different R packages may differ for different datasets and may depend on the size of the dataset and richness of the missing values in the datasets. In this paper, the authors perform comparative study of the performance of the common R packages, namely VIM, MICE, MissForest, and HMISC, used for missing value imputation. The authors measured the performances of the said packages in terms of their imputation time, imputation efficiency and the effect on the variance. The imputation efficiency was measured in terms of the difference in predictive performance of a model built using original dataset vis-à-vis a dataset with imputed values. Similarly, the variance of the variables in the original dataset was compared that of corresponding variables in the imputed dataset. A missing value imputation package can be considered to be better if it consumes less imputation time and provides high imputation accuracy. Also in terms of variance, one would like to have the imputation package maintain the original variance of the variables. On analysing the four imputation packages on two datasets over three predictive algorithms–Logistic Regression, Support Vector Machines, and Artificial Neural Networks–it was observed that the performances varies depending on the size of the dataset, and the missing values present in them. The study highlights that certain missing value package used in conjunction with a given predictive algorithm provides better performance, which is again a function of the dataset characteristics |
| Tasks | Imputation |
| Published | 2018-06-28 |
| URL | https://www.sciencedirect.com/science/article/abs/pii/S0950705118303381#abs0001 |
| https://doi.org/10.1016/j.knosys.2018.06.012 | |
| PWC | https://paperswithcode.com/paper/handling-missing-values-a-study-of-popular |
| Repo | |
| Framework | |
Variational Network Inference: Strong and Stable with Concrete Support
| Title | Variational Network Inference: Strong and Stable with Concrete Support |
| Authors | Amir Dezfouli, Edwin Bonilla, Richard Nock |
| Abstract | Traditional methods for the discovery of latent network structures are limited in two ways: they either assume that all the signal comes from the network (i.e. there is no source of signal outside the network) or they place constraints on the network parameters to ensure model or algorithmic stability. We address these limitations by proposing a model that incorporates a Gaussian process prior on a network-independent component and formally proving that we get algorithmic stability for free while providing a novel perspective on model stability as well as robustness results and precise intervals for key inference parameters. We show that, on three applications, our approach outperforms previous methods consistently. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1878 |
| http://proceedings.mlr.press/v80/dezfouli18a/dezfouli18a.pdf | |
| PWC | https://paperswithcode.com/paper/variational-network-inference-strong-and |
| Repo | |
| Framework | |
DiCE: The Infinitely Differentiable Monte Carlo Estimator
| Title | DiCE: The Infinitely Differentiable Monte Carlo Estimator |
| Authors | Jakob Foerster, Gregory Farquhar, Maruan Al-Shedivat, Tim Rocktäschel, Eric Xing, Shimon Whiteson |
| Abstract | The score function estimator is widely used for estimating gradients of stochastic objectives in stochastic computation graphs (SCG), eg., in reinforcement learning and meta-learning. While deriving the first-order gradient estimators by differentiating a surrogate loss (SL) objective is computationally and conceptually simple, using the same approach for higher-order derivatives is more challenging. Firstly, analytically deriving and implementing such estimators is laborious and not compliant with automatic differentiation. Secondly, repeatedly applying SL to construct new objectives for each order derivative involves increasingly cumbersome graph manipulations. Lastly, to match the first-order gradient under differentiation, SL treats part of the cost as a fixed sample, which we show leads to missing and wrong terms for estimators of higher-order derivatives. To address all these shortcomings in a unified way, we introduce DiCE, which provides a single objective that can be differentiated repeatedly, generating correct estimators of derivatives of any order in SCGs. Unlike SL, DiCE relies on automatic differentiation for performing the requisite graph manipulations. We verify the correctness of DiCE both through a proof and numerical evaluation of the DiCE derivative estimates. We also use DiCE to propose and evaluate a novel approach for multi-agent learning. Our code is available at https://github.com/alshedivat/lola. |
| Tasks | Meta-Learning |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2266 |
| http://proceedings.mlr.press/v80/foerster18a/foerster18a.pdf | |
| PWC | https://paperswithcode.com/paper/dice-the-infinitely-differentiable-monte-1 |
| Repo | |
| Framework | |
A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check
| Title | A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check |
| Authors | Dingmin Wang, Yan Song, Jing Li, Jialong Han, Haisong Zhang |
| Abstract | Chinese spelling check (CSC) is a challenging yet meaningful task, which not only serves as a preprocessing in many natural language processing(NLP) applications, but also facilitates reading and understanding of running texts in peoples{'} daily lives. However, to utilize data-driven approaches for CSC, there is one major limitation that annotated corpora are not enough in applying algorithms and building models. In this paper, we propose a novel approach of constructing CSC corpus with automatically generated spelling errors, which are either visually or phonologically resembled characters, corresponding to the OCR- and ASR-based methods, respectively. Upon the constructed corpus, different models are trained and evaluated for CSC with respect to three standard test sets. Experimental results demonstrate the effectiveness of the corpus, therefore confirm the validity of our approach. |
| Tasks | Language Modelling, Optical Character Recognition, Part-Of-Speech Tagging |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1273/ |
| https://www.aclweb.org/anthology/D18-1273 | |
| PWC | https://paperswithcode.com/paper/a-hybrid-approach-to-automatic-corpus |
| Repo | |
| Framework | |
Leveraging Lexical Substitutes for Unsupervised Word Sense Induction
| Title | Leveraging Lexical Substitutes for Unsupervised Word Sense Induction |
| Authors | Domagoj Alagić, Jan Šnajder, Sebastian Padó |
| Abstract | Word sense induction is the most prominent unsupervised approach to lexical disambiguation. It clusters word instances, typically represented by their bag-of-words contexts. Therefore, uninformative and ambiguous contexts present a major challenge. In this paper, we investigate the use of an alternative instance representation based on lexical substitutes, i.e., contextually suitable, meaning-preserving replacements. Using lexical substitutes predicted by a state-of-the-art automatic system and a simple clustering algorithm, we outperform bag-of-words instance representations and compete with much more complex structured probabilistic models. Furthermore, we show that an oracle based on manually-labeled lexical substitutes yields yet substantially higher performance. Taken together, this provides evidence for a complementarity between word sense induction and lexical substitution that has not been given much consideration before. |
| Tasks | Word Sense Induction |
| Published | 2018-04-27 |
| URL | https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17317 |
| https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17317/16780 | |
| PWC | https://paperswithcode.com/paper/leveraging-lexical-substitutes-for |
| Repo | |
| Framework | |
Imitation Learning from Visual Data with Multiple Intentions
| Title | Imitation Learning from Visual Data with Multiple Intentions |
| Authors | Aviv Tamar, Khashayar Rohanimanesh, Yinlam Chow, Chris Vigorito, Ben Goodrich, Michael Kahane, Derik Pridmore |
| Abstract | Recent advances in learning from demonstrations (LfD) with deep neural networks have enabled learning complex robot skills that involve high dimensional perception such as raw image inputs. LfD algorithms generally assume learning from single task demonstrations. In practice, however, it is more efficient for a teacher to demonstrate a multitude of tasks without careful task set up, labeling, and engineering. Unfortunately in such cases, traditional imitation learning techniques fail to represent the multi-modal nature of the data, and often result in sub-optimal behavior. In this paper we present an LfD approach for learning multiple modes of behavior from visual data. Our approach is based on a stochastic deep neural network (SNN), which represents the underlying intention in the demonstration as a stochastic activation in the network. We present an efficient algorithm for training SNNs, and for learning with vision inputs, we also propose an architecture that associates the intention with a stochastic attention module. We demonstrate our method on real robot visual object reaching tasks, and show that it can reliably learn the multiple behavior modes in the demonstration data. Video results are available at https://vimeo.com/240212286/fd401241b9. |
| Tasks | Imitation Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=Hk3ddfWRW |
| https://openreview.net/pdf?id=Hk3ddfWRW | |
| PWC | https://paperswithcode.com/paper/imitation-learning-from-visual-data-with |
| Repo | |
| Framework | |
Incorporating Syntactic Uncertainty in Neural Machine Translation with a Forest-to-Sequence Model
| Title | Incorporating Syntactic Uncertainty in Neural Machine Translation with a Forest-to-Sequence Model |
| Authors | Poorya Zaremoodi, Gholamreza Haffari |
| Abstract | Incorporating syntactic information in Neural Machine Translation (NMT) can lead to better reorderings, particularly useful when the language pairs are syntactically highly divergent or when the training bitext is not large. Previous work on using syntactic information, provided by top-1 parse trees generated by (inevitably error-prone) parsers, has been promising. In this paper, we propose a forest-to-sequence NMT model to make use of exponentially many parse trees of the source sentence to compensate for the parser errors. Our method represents the collection of parse trees as a packed forest, and learns a neural transducer to translate from the input forest to the target sentence. Experiments on English to German, Chinese and Farsi translation tasks show the superiority of our approach over the sequence-to-sequence and tree-to-sequence neural translation models. |
| Tasks | Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1120/ |
| https://www.aclweb.org/anthology/C18-1120 | |
| PWC | https://paperswithcode.com/paper/incorporating-syntactic-uncertainty-in-neural |
| Repo | |
| Framework | |
Proceedings of the 30th Conference on Computational Linguistics and Speech Processing (ROCLING 2018)
| Title | Proceedings of the 30th Conference on Computational Linguistics and Speech Processing (ROCLING 2018) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/O18-1000/ |
| https://www.aclweb.org/anthology/O18-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-30th-conference-on |
| Repo | |
| Framework | |
Mix & Match - Agent Curricula for Reinforcement Learning
| Title | Mix & Match - Agent Curricula for Reinforcement Learning |
| Authors | Wojciech Czarnecki, Siddhant Jayakumar, Max Jaderberg, Leonard Hasenclever, Yee Whye Teh, Nicolas Heess, Simon Osindero, Razvan Pascanu |
| Abstract | We introduce Mix and match (M&M) – a training framework designed to facilitate rapid and effective learning in RL agents that would be too slow or too challenging to train otherwise.The key innovation is a procedure that allows us to automatically form a curriculum over agents. Through such a curriculum we can progressively train more complex agents by, effectively, bootstrapping from solutions found by simpler agents.In contradistinction to typical curriculum learning approaches, we do not gradually modify the tasks or environments presented, but instead use a process to gradually alter how the policy is represented internally.We show the broad applicability of our method by demonstrating significant performance gains in three different experimental setups: (1) We train an agent able to control more than 700 actions in a challenging 3D first-person task; using our method to progress through an action-space curriculum we achieve both faster training and better final performance than one obtains using traditional methods.(2) We further show that M&M can be used successfully to progress through a curriculum of architectural variants defining an agents internal state. (3) Finally, we illustrate how a variant of our method can be used to improve agent performance in a multitask setting. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2187 |
| http://proceedings.mlr.press/v80/czarnecki18a/czarnecki18a.pdf | |
| PWC | https://paperswithcode.com/paper/mix-match-agent-curricula-for-reinforcement |
| Repo | |
| Framework | |
Coreference Resolution in FreeLing 4.0
| Title | Coreference Resolution in FreeLing 4.0 |
| Authors | Montserrat Marimon, Llu{'\i}s Padr{'o}, Jordi Turmo |
| Abstract | |
| Tasks | Constituency Parsing, Coreference Resolution, Dependency Parsing, Document Summarization, Language Identification, Lemmatization, Named Entity Recognition, Tokenization, Word Sense Disambiguation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1057/ |
| https://www.aclweb.org/anthology/L18-1057 | |
| PWC | https://paperswithcode.com/paper/coreference-resolution-in-freeling-40 |
| Repo | |
| Framework | |
A First South African Corpus of Multilingual Code-switched Soap Opera Speech
| Title | A First South African Corpus of Multilingual Code-switched Soap Opera Speech |
| Authors | Ewald van der Westhuizen, Thomas Niesler |
| Abstract | |
| Tasks | Language Modelling |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1451/ |
| https://www.aclweb.org/anthology/L18-1451 | |
| PWC | https://paperswithcode.com/paper/a-first-south-african-corpus-of-multilingual |
| Repo | |
| Framework | |
Annotating Abstract Meaning Representations for Spanish
| Title | Annotating Abstract Meaning Representations for Spanish |
| Authors | Noelia Migueles-Abraira, Rodrigo Agerri, Arantza Diaz de Ilarraza |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1486/ |
| https://www.aclweb.org/anthology/L18-1486 | |
| PWC | https://paperswithcode.com/paper/annotating-abstract-meaning-representations |
| Repo | |
| Framework | |
PoTion: Pose MoTion Representation for Action Recognition
| Title | PoTion: Pose MoTion Representation for Action Recognition |
| Authors | Vasileios Choutas, Philippe Weinzaepfel, Jérôme Revaud, Cordelia Schmid |
| Abstract | Most state-of-the-art methods for action recognition rely on a two-stream architecture that processes appearance and motion independently. In this paper, we claim that considering them jointly offers rich information for action recognition. We introduce a novel representation that gracefully encodes the movement of some semantic keypoints. We use the human joints as these keypoints and term our Pose moTion representation PoTion. Specifically, we first run a state-of-the-art human pose estimator and extract heatmaps for the human joints in each frame. We obtain our PoTion representation by temporally aggregating these probability maps. This is achieved by colorizing each of them depending on the relative time of the frames in the video clip and summing them. This fixed-size representation for an entire video clip is suitable to classify actions using a shallow convolutional neural network. Our experimental evaluation shows that PoTion outperforms other state-of-the-art pose representations. Furthermore, it is complementary to standard appearance and motion streams. When combining PoTion with the recent two-stream I3D approach [5], we obtain state-of-the-art performance on the JHMDB, HMDB and UCF101 datasets. |
| Tasks | Action Recognition In Videos, Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Choutas_PoTion_Pose_MoTion_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Choutas_PoTion_Pose_MoTion_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/potion-pose-motion-representation-for-action |
| Repo | |
| Framework | |
Crowdsourcing a Large Corpus of Clickbait on Twitter
| Title | Crowdsourcing a Large Corpus of Clickbait on Twitter |
| Authors | Martin Potthast, Tim Gollub, Kristof Komlossy, Sebastian Schuster, Matti Wiegmann, Garces Fern, Erika Patricia ez, Matthias Hagen, Benno Stein |
| Abstract | Clickbait has become a nuisance on social media. To address the urging task of clickbait detection, we constructed a new corpus of 38,517 annotated Twitter tweets, the Webis Clickbait Corpus 2017. To avoid biases in terms of publisher and topic, tweets were sampled from the top 27 most retweeted news publishers, covering a period of 150 days. Each tweet has been annotated on 4-point scale by five annotators recruited at Amazon{'}s Mechanical Turk. The corpus has been employed to evaluate 12 clickbait detectors submitted to the Clickbait Challenge 2017. Download: https://webis.de/data/webis-clickbait-17.html Challenge: https://clickbait-challenge.org |
| Tasks | Clickbait Detection |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1127/ |
| https://www.aclweb.org/anthology/C18-1127 | |
| PWC | https://paperswithcode.com/paper/crowdsourcing-a-large-corpus-of-clickbait-on |
| Repo | |
| Framework | |
Finding Tiny Faces in the Wild With Generative Adversarial Network
| Title | Finding Tiny Faces in the Wild With Generative Adversarial Network |
| Authors | Yancheng Bai, Yongqiang Zhang, Mingli Ding, Bernard Ghanem |
| Abstract | Face detection techniques have been developed for decades, and one of remaining open challenges is detecting small faces in unconstrained conditions. The reason is that tiny faces are often lacking detailed information and blurring. In this paper, we proposed an algorithm to directly generate a clear high-resolution face from a blurry small one by adopting a generative adversarial network (GAN). Toward this end, the basic GAN formulation achieves it by super-resolving and refining sequentially (e.g. SR-GAN and cycle-GAN). However, we design a novel network to address the problem of super-resolving and refining jointly. We also introduce new training losses to guide the generator network to recover fine details and to promote the discriminator network to distinguish real vs. fake and face vs. non-face simultaneously. Extensive experiments on the challenging dataset WIDER FACE demonstrate the effectiveness of our proposed method in restoring a clear high-resolution face from a blurry small one, and show that the detection performance outperforms other state-of-the-art methods. |
| Tasks | Face Detection |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Bai_Finding_Tiny_Faces_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Bai_Finding_Tiny_Faces_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/finding-tiny-faces-in-the-wild-with |
| Repo | |
| Framework | |
