Paper Group NANR 6
IoT Data Analytics Using Deep Learning. The Effect of Error Rate in Artificially Generated Data for Automatic Preposition and Determiner Correction. Nearly Optimal Robust Matrix Completion. Deep Learning in Semantic Kernel Spaces. Extraction of Gene-Environment Interaction from the Biomedical Literature. Non-Deterministic Segmentation for Chinese L …
IoT Data Analytics Using Deep Learning
| Title | IoT Data Analytics Using Deep Learning |
| Authors | Xiaofeng Xie, Di Wu, Siping Liu, Renfa Li |
| Abstract | Deep learning is a popular machine learning approach which has achieved a lot of progress in all traditional machine learning areas. Internet of thing (IoT) and Smart City deployments are generating large amounts of time-series sensor data in need of analysis. Applying deep learning to these domains has been an important topic of research. The Long-Short Term Memory (LSTM) network has been proven to be well suited for dealing with and predicting important events with long intervals and delays in the time series. LTSM networks have the ability to maintain long-term memory. In an LTSM network, a stacked LSTM hidden layer also makes it possible to learn a high level temporal feature without the need of any fine tuning and preprocessing which would be required by other techniques. In this paper, we construct a long-short term memory (LSTM) recurrent neural network structure, use the normal time series training set to build the prediction model. And then we use the predicted error from the prediction model to construct a Gaussian naive Bayes model to detect whether the original sample is abnormal. This method is called LSTM-Gauss-NBayes for short. We use three real-world data sets, each of which involve long-term time-dependence or short-term time-dependence, even very weak time dependence. The experimental results show that LSTM-Gauss-NBayes is an effective and robust model. |
| Tasks | Time Series |
| Published | 2017-08-13 |
| URL | https://arxiv.org/abs/1708.03854 |
| https://arxiv.org/ftp/arxiv/papers/1708/1708.03854.pdf | |
| PWC | https://paperswithcode.com/paper/iot-data-analytics-using-deep-learning |
| Repo | |
| Framework | |
The Effect of Error Rate in Artificially Generated Data for Automatic Preposition and Determiner Correction
| Title | The Effect of Error Rate in Artificially Generated Data for Automatic Preposition and Determiner Correction |
| Authors | Fraser Bowen, Jon Dehdari, Josef van Genabith |
| Abstract | In this research we investigate the impact of mismatches in the density and type of error between training and test data on a neural system correcting preposition and determiner errors. We use synthetically produced training data to control error density and type, and {``}real{''} error data for testing. Our results show it is possible to combine error types, although prepositions and determiners behave differently in terms of how much error should be artificially introduced into the training data in order to get the best results. | |
| Tasks | Grammatical Error Correction, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4410/ |
| https://www.aclweb.org/anthology/W17-4410 | |
| PWC | https://paperswithcode.com/paper/the-effect-of-error-rate-in-artificially |
| Repo | |
| Framework | |
Nearly Optimal Robust Matrix Completion
| Title | Nearly Optimal Robust Matrix Completion |
| Authors | Yeshwanth Cherapanamjeri, Kartik Gupta, Prateek Jain |
| Abstract | In this paper, we consider the problem of Robust Matrix Completion (RMC) where the goal is to recover a low-rank matrix by observing a small number of its entries out of which a few can be arbitrarily corrupted. We propose a simple projected gradient descent-based method to estimate the low-rank matrix that alternately performs a projected gradient descent step and cleans up a few of the corrupted entries using hard-thresholding. Our algorithm solves RMC using nearly optimal number of observations while tolerating a nearly optimal number of corruptions. Our result also implies significant improvement over the existing time complexity bounds for the low-rank matrix completion problem. Finally, an application of our result to the robust PCA problem (low-rank+sparse matrix separation) leads to nearly linear time (in matrix dimensions) algorithm for the same; existing state-of-the-art methods require quadratic time. Our empirical results corroborate our theoretical results and show that even for moderate sized problems, our method for robust PCA is an order of magnitude faster than the existing methods. |
| Tasks | Low-Rank Matrix Completion, Matrix Completion |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=772 |
| http://proceedings.mlr.press/v70/cherapanamjeri17a/cherapanamjeri17a.pdf | |
| PWC | https://paperswithcode.com/paper/nearly-optimal-robust-matrix-completion-1 |
| Repo | |
| Framework | |
Deep Learning in Semantic Kernel Spaces
| Title | Deep Learning in Semantic Kernel Spaces |
| Authors | Danilo Croce, Simone Filice, Giuseppe Castellucci, Roberto Basili |
| Abstract | Kernel methods enable the direct usage of structured representations of textual data during language learning and inference tasks. Expressive kernels, such as Tree Kernels, achieve excellent performance in NLP. On the other side, deep neural networks have been demonstrated effective in automatically learning feature representations during training. However, their input is tensor data, i.e., they can not manage rich structured information. In this paper, we show that expressive kernels and deep neural networks can be combined in a common framework in order to (i) explicitly model structured information and (ii) learn non-linear decision functions. We show that the input layer of a deep architecture can be pre-trained through the application of the Nystrom low-rank approximation of kernel spaces. The resulting {``}kernelized{''} neural network achieves state-of-the-art accuracy in three different tasks. | |
| Tasks | Feature Engineering, Information Retrieval, Question Answering |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1032/ |
| https://www.aclweb.org/anthology/P17-1032 | |
| PWC | https://paperswithcode.com/paper/deep-learning-in-semantic-kernel-spaces |
| Repo | |
| Framework | |
Extraction of Gene-Environment Interaction from the Biomedical Literature
| Title | Extraction of Gene-Environment Interaction from the Biomedical Literature |
| Authors | Jinseon You, Jin-Woo Chung, Wonsuk Yang, Jong C. Park |
| Abstract | Genetic information in the literature has been extensively looked into for the purpose of discovering the etiology of a disease. As the gene-disease relation is sensitive to external factors, their identification is important to study a disease. Environmental influences, which are usually called Gene-Environment interaction (GxE), have been considered as important factors and have extensively been researched in biology. Nevertheless, there is still a lack of systems for automatic GxE extraction from the biomedical literature due to new challenges: (1) there are no preprocessing tools and corpora for GxE, (2) expressions of GxE are often quite implicit, and (3) document-level comprehension is usually required. We propose to overcome these challenges with neural network models and show that a modified sequence-to-sequence model with a static RNN decoder produces a good performance in GxE recognition. |
| Tasks | Named Entity Recognition |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1087/ |
| https://www.aclweb.org/anthology/I17-1087 | |
| PWC | https://paperswithcode.com/paper/extraction-of-gene-environment-interaction |
| Repo | |
| Framework | |
Non-Deterministic Segmentation for Chinese Lattice Parsing
| Title | Non-Deterministic Segmentation for Chinese Lattice Parsing |
| Authors | Hai Hu, Daniel Dakota, S K{"u}bler, ra |
| Abstract | Parsing Chinese critically depends on correct word segmentation for the parser since incorrect segmentation inevitably causes incorrect parses. We investigate a pipeline approach to segmentation and parsing using word lattices as parser input. We compare CRF-based and lexicon-based approaches to word segmentation. Our results show that the lattice parser is capable of selecting the correction segmentation from thousands of options, thus drastically reducing the number of unparsed sentence. Lexicon-based parsing models have a better coverage than the CRF-based approach, but the many options are more difficult to handle. We reach our best result by using a lexicon from the n-best CRF analyses, combined with highly probable words. |
| Tasks | Morphological Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1043/ |
| https://doi.org/10.26615/978-954-452-049-6_043 | |
| PWC | https://paperswithcode.com/paper/non-deterministic-segmentation-for-chinese |
| Repo | |
| Framework | |
Supervised Attention for Sequence-to-Sequence Constituency Parsing
| Title | Supervised Attention for Sequence-to-Sequence Constituency Parsing |
| Authors | Hidetaka Kamigaito, Katsuhiko Hayashi, Tsutomu Hirao, Hiroya Takamura, Manabu Okumura, Masaaki Nagata |
| Abstract | The sequence-to-sequence (Seq2Seq) model has been successfully applied to machine translation (MT). Recently, MT performances were improved by incorporating supervised attention into the model. In this paper, we introduce supervised attention to constituency parsing that can be regarded as another translation task. Evaluation results on the PTB corpus showed that the bracketing F-measure was improved by supervised attention. |
| Tasks | Constituency Parsing, Machine Translation, Text Generation, Text Summarization |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2002/ |
| https://www.aclweb.org/anthology/I17-2002 | |
| PWC | https://paperswithcode.com/paper/supervised-attention-for-sequence-to-sequence |
| Repo | |
| Framework | |
Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery
| Title | Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery |
| Authors | Mostafa Rahmani, George Atia |
| Abstract | This paper presents a remarkably simple, yet powerful, algorithm for robust Principal Component Analysis (PCA). In the proposed approach, an outlier is set apart from an inlier by comparing their coherence with the rest of the data points. As inliers lie on a low dimensional subspace, they are likely to have strong mutual coherence provided there are enough inliers. By contrast, outliers do not typically admit low dimensional structures, wherefore an outlier is unlikely to bear strong resemblance with a large number of data points. The mutual coherences are computed by forming the Gram matrix of normalized data points. Subsequently, the subspace is recovered from the span of a small subset of the data points that exhibit strong coherence with the rest of the data. As coherence pursuit only involves one simple matrix multiplication, it is significantly faster than the state of-the-art robust PCA algorithms. We provide a mathematical analysis of the proposed algorithm under a random model for the distribution of the inliers and outliers. It is shown that the proposed method can recover the correct subspace even if the data is predominantly outliers. To the best of our knowledge, this is the first provable robust PCA algorithm that is simultaneously non-iterative, can tolerate a large number of outliers and is robust to linearly dependent outliers. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=527 |
| http://proceedings.mlr.press/v70/rahmani17a/rahmani17a.pdf | |
| PWC | https://paperswithcode.com/paper/coherence-pursuit-fast-simple-and-robust |
| Repo | |
| Framework | |
Toward a Comparable Corpus of Latvian, Russian and English Tweets
| Title | Toward a Comparable Corpus of Latvian, Russian and English Tweets |
| Authors | Dmitrijs Milajevs |
| Abstract | Twitter has become a rich source for linguistic data. Here, a possibility of building a trilingual Latvian-Russian-English corpus of tweets from Riga, Latvia is investigated. Such a corpus, once constructed, might be of great use for multiple purposes including training machine translation models, examining cross-lingual phenomena and studying the population of Riga. This pilot study shows that it is feasible to build such a resource by collecting and analysing a pilot corpus, which is made publicly available and can be used to construct a large comparable corpus. |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2505/ |
| https://www.aclweb.org/anthology/W17-2505 | |
| PWC | https://paperswithcode.com/paper/toward-a-comparable-corpus-of-latvian-russian |
| Repo | |
| Framework | |
Deception detection in Russian texts
| Title | Deception detection in Russian texts |
| Authors | Olga Litvinova, Pavel Seredin, Tatiana Litvinova, John Lyell |
| Abstract | Humans are known to detect deception in speech randomly and it is therefore important to develop tools to enable them to detect deception. The problem of deception detection has been studied for a significant amount of time, however the last 10-15 years have seen methods of computational linguistics being employed. Texts are processed using different NLP tools and then classified as deceptive/truthful using machine learning methods. While most research has been performed for English, Slavic languages have never been a focus of detection deception studies. The paper deals with deception detection in Russian narratives. It employs a specially designed corpus of truthful and deceptive texts on the same topic from each respondent, N = 113. The texts were processed using Linguistic Inquiry and Word Count software that is used in most studies of text-based deception detection. The list of parameters computed using the software was expanded due to the designed users{'} dictionaries. A variety of text classification methods was employed. The accuracy of the model was found to depend on the author{'}s gender and text type (deceptive/truthful). |
| Tasks | Deception Detection, Text Classification |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-4005/ |
| https://www.aclweb.org/anthology/E17-4005 | |
| PWC | https://paperswithcode.com/paper/deception-detection-in-russian-texts |
| Repo | |
| Framework | |
MT/IE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models
| Title | MT/IE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models |
| Authors | Sheng Zhang, Kevin Duh, Benjamin Van Durme |
| Abstract | Cross-lingual information extraction is the task of distilling facts from foreign language (e.g. Chinese text) into representations in another language that is preferred by the user (e.g. English tuples). Conventional pipeline solutions decompose the task as machine translation followed by information extraction (or vice versa). We propose a joint solution with a neural sequence model, and show that it outperforms the pipeline in a cross-lingual open information extraction setting by 1-4 BLEU and 0.5-0.8 F1. |
| Tasks | Machine Translation, Open Information Extraction, Question Answering, Semantic Parsing |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2011/ |
| https://www.aclweb.org/anthology/E17-2011 | |
| PWC | https://paperswithcode.com/paper/mtie-cross-lingual-open-information |
| Repo | |
| Framework | |
Exploring Properties of Intralingual and Interlingual Association Measures Visually
| Title | Exploring Properties of Intralingual and Interlingual Association Measures Visually |
| Authors | Johannes Gra{"e}n, Christof Bless |
| Abstract | |
| Tasks | Language Modelling, Lemmatization, Word Alignment |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0245/ |
| https://www.aclweb.org/anthology/W17-0245 | |
| PWC | https://paperswithcode.com/paper/exploring-properties-of-intralingual-and |
| Repo | |
| Framework | |
Proceedings of the Linguistic Resources for Automatic Natural Language Generation - LiRA@NLG
| Title | Proceedings of the Linguistic Resources for Automatic Natural Language Generation - LiRA@NLG |
| Authors | |
| Abstract | |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3800/ |
| https://www.aclweb.org/anthology/W17-3800 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-linguistic-resources-for |
| Repo | |
| Framework | |
A Framework for Software Defect Prediction and Metric Selection
| Title | A Framework for Software Defect Prediction and Metric Selection |
| Authors | SHAMSUL HUDA 1, SULTAN ALYAHYA2, MD MOHSIN ALI3, SHAFIQ AHMAD 4, JEMAL ABAWAJY1, HMOOD AL-DOSSARI2, AND JOHN YEARWOOD1 |
| Abstract | ABSTRACT Automated software defect prediction is an important and fundamental activity in the domain of software development. However, modern software systems are inherently large and complex with numerous correlated metrics that capture different aspects of the software components. This large number of correlated metrics makes building a software defect prediction model very complex. Thus, identifying and selecting a subset of metrics that enhance the software defect prediction method’s performance are an important but challenging problem that has received little attention in the literature. The main objective of this paper is to identify significant software metrics, to build and evaluate an automated software defect prediction model. We propose two novel hybrid software defect prediction models to identify the significant attributes (metrics) using a combination of wrapper and filter techniques. The novelty of our approach is that it embeds the metric selection and training processes of software defect prediction as a single process while reducing the measurement overhead significantly. Different wrapper approaches were combined, including SVM and ANN, with a maximum relevance filter approach to find the significant metrics. A filter score was injected into the wrapper selection process in the proposed approaches to direct the search process efficiently to identify significant metrics. Experimental results with real defect-prone software data sets show that the proposed hybrid approaches achieve significantly compact metrics (i.e., selecting the most significant metrics) with high prediction accuracy compared with conventional wrapper or filter approaches. The performance of the proposed framework has also been verified using a statistical multivariate quality control process using multivariate exponentially weighted moving average. The proposed framework demonstrates that the hybrid heuristic can guide the metric selection process in a computationally efficient way by integrating the intrinsic characteristics from the filters into the wrapper and using the advantages of both the filter and wrapper approaches. |
| Tasks | |
| Published | 2017-12-27 |
| URL | https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8240899 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8240899 | |
| PWC | https://paperswithcode.com/paper/a-framework-for-software-defect-prediction |
| Repo | |
| Framework | |
Bregman Divergence for Stochastic Variance Reduction: Saddle-Point and Adversarial Prediction
| Title | Bregman Divergence for Stochastic Variance Reduction: Saddle-Point and Adversarial Prediction |
| Authors | Zhan Shi, Xinhua Zhang, Yaoliang Yu |
| Abstract | Adversarial machines, where a learner competes against an adversary, have regained much recent interest in machine learning. They are naturally in the form of saddle-point optimization, often with separable structure but sometimes also with unmanageably large dimension. In this work we show that adversarial prediction under multivariate losses can be solved much faster than they used to be. We first reduce the problem size exponentially by using appropriate sufficient statistics, and then we adapt the new stochastic variance-reduced algorithm of Balamurugan & Bach (2016) to allow any Bregman divergence. We prove that the same linear rate of convergence is retained and we show that for adversarial prediction using KL-divergence we can further achieve a speedup of #example times compared with the Euclidean alternative. We verify the theoretical findings through extensive experiments on two example applications: adversarial prediction and LPboosting. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7184-bregman-divergence-for-stochastic-variance-reduction-saddle-point-and-adversarial-prediction |
| http://papers.nips.cc/paper/7184-bregman-divergence-for-stochastic-variance-reduction-saddle-point-and-adversarial-prediction.pdf | |
| PWC | https://paperswithcode.com/paper/bregman-divergence-for-stochastic-variance |
| Repo | |
| Framework | |
