Paper Group NANR 199
Variance Reduction in Stochastic Gradient Langevin Dynamics. A Comparison of Event Representations in DEFT. Arabic Dialect Identification in Speech Transcripts. Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization. Attention-based LSTM Network for Cross-Lingual Sentiment Classification. 基於深層類神經網路之音訊事件偵測系統(Deep Neural Networks …
Variance Reduction in Stochastic Gradient Langevin Dynamics
| Title | Variance Reduction in Stochastic Gradient Langevin Dynamics |
| Authors | Kumar Avinava Dubey, Sashank J. Reddi, Sinead A. Williamson, Barnabas Poczos, Alexander J. Smola, Eric P. Xing |
| Abstract | Stochastic gradient-based Monte Carlo methods such as stochastic gradient Langevin dynamics are useful tools for posterior inference on large scale datasets in many machine learning applications. These methods scale to large datasets by using noisy gradients calculated using a mini-batch or subset of the dataset. However, the high variance inherent in these noisy gradients degrades performance and leads to slower mixing. In this paper, we present techniques for reducing variance in stochastic gradient Langevin dynamics, yielding novel stochastic Monte Carlo methods that improve performance by reducing the variance in the stochastic gradient. We show that our proposed method has better theoretical guarantees on convergence rate than stochastic Langevin dynamics. This is complemented by impressive empirical results obtained on a variety of real world datasets, and on four different machine learning tasks (regression, classification, independent component analysis and mixture modeling). These theoretical and empirical contributions combine to make a compelling case for using variance reduction in stochastic Monte Carlo methods. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6293-variance-reduction-in-stochastic-gradient-langevin-dynamics |
| http://papers.nips.cc/paper/6293-variance-reduction-in-stochastic-gradient-langevin-dynamics.pdf | |
| PWC | https://paperswithcode.com/paper/variance-reduction-in-stochastic-gradient |
| Repo | |
| Framework | |
A Comparison of Event Representations in DEFT
| Title | A Comparison of Event Representations in DEFT |
| Authors | Ann Bies, Zhiyi Song, Jeremy Getman, Joe Ellis, Justin Mott, Stephanie Strassel, Martha Palmer, Teruko Mitamura, Marjorie Freedman, Heng Ji, Tim O{'}Gorman |
| Abstract | |
| Tasks | Anomaly Detection |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1004/ |
| https://www.aclweb.org/anthology/W16-1004 | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-event-representations-in-deft |
| Repo | |
| Framework | |
Arabic Dialect Identification in Speech Transcripts
| Title | Arabic Dialect Identification in Speech Transcripts |
| Authors | Shervin Malmasi, Marcos Zampieri |
| Abstract | In this paper we describe a system developed to identify a set of four regional Arabic dialects (Egyptian, Gulf, Levantine, North African) and Modern Standard Arabic (MSA) in a transcribed speech corpus. We competed under the team name MAZA in the Arabic Dialect Identification sub-task of the 2016 Discriminating between Similar Languages (DSL) shared task. Our system achieved an F1-score of 0.51 in the closed training track, ranking first among the 18 teams that participated in the sub-task. Our system utilizes a classifier ensemble with a set of linear models as base classifiers. We experimented with three different ensemble fusion strategies, with the mean probability approach providing the best performance. |
| Tasks | Machine Translation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4814/ |
| https://www.aclweb.org/anthology/W16-4814 | |
| PWC | https://paperswithcode.com/paper/arabic-dialect-identification-in-speech |
| Repo | |
| Framework | |
Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization
| Title | Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization |
| Authors | Sashank J. Reddi, Suvrit Sra, Barnabas Poczos, Alexander J. Smola |
| Abstract | We analyze stochastic algorithms for optimizing nonconvex, nonsmooth finite-sum problems, where the nonsmooth part is convex. Surprisingly, unlike the smooth case, our knowledge of this fundamental problem is very limited. For example, it is not known whether the proximal stochastic gradient method with constant minibatch converges to a stationary point. To tackle this issue, we develop fast stochastic algorithms that provably converge to a stationary point for constant minibatches. Furthermore, using a variant of these algorithms, we obtain provably faster convergence than batch proximal gradient descent. Our results are based on the recent variance reduction techniques for convex optimization but with a novel analysis for handling nonconvex and nonsmooth functions. We also prove global linear convergence rate for an interesting subclass of nonsmooth nonconvex functions, which subsumes several recent works. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6116-proximal-stochastic-methods-for-nonsmooth-nonconvex-finite-sum-optimization |
| http://papers.nips.cc/paper/6116-proximal-stochastic-methods-for-nonsmooth-nonconvex-finite-sum-optimization.pdf | |
| PWC | https://paperswithcode.com/paper/proximal-stochastic-methods-for-nonsmooth |
| Repo | |
| Framework | |
Attention-based LSTM Network for Cross-Lingual Sentiment Classification
| Title | Attention-based LSTM Network for Cross-Lingual Sentiment Classification |
| Authors | Xinjie Zhou, Xiaojun Wan, Jianguo Xiao |
| Abstract | |
| Tasks | Machine Translation, Representation Learning, Sentiment Analysis, Text Classification |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1024/ |
| https://www.aclweb.org/anthology/D16-1024 | |
| PWC | https://paperswithcode.com/paper/attention-based-lstm-network-for-cross |
| Repo | |
| Framework | |
基於深層類神經網路之音訊事件偵測系統(Deep Neural Networks for Audio Event Detection)[In Chinese]
| Title | 基於深層類神經網路之音訊事件偵測系統(Deep Neural Networks for Audio Event Detection)[In Chinese] |
| Authors | Jhih-wei Chen, Chia-Hsin Liu, Yuan-Fu Liao |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/O16-1028/ |
| https://www.aclweb.org/anthology/O16-1028 | |
| PWC | https://paperswithcode.com/paper/ao14aeccc2e-a1e3e-aoaa-c3cdeep-neural |
| Repo | |
| Framework | |
A Generalized Framework for Hierarchical Word Sequence Language Model
| Title | A Generalized Framework for Hierarchical Word Sequence Language Model |
| Authors | Xiaoyi Wu, Kevin Duh, Yuji Matsumoto |
| Abstract | |
| Tasks | Language Modelling, Machine Translation, Speech Recognition, Spelling Correction |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-2004/ |
| https://www.aclweb.org/anthology/Y16-2004 | |
| PWC | https://paperswithcode.com/paper/a-generalized-framework-for-hierarchical-word |
| Repo | |
| Framework | |
Variational Bayes on Monte Carlo Steroids
| Title | Variational Bayes on Monte Carlo Steroids |
| Authors | Aditya Grover, Stefano Ermon |
| Abstract | Variational approaches are often used to approximate intractable posteriors or normalization constants in hierarchical latent variable models. While often effective in practice, it is known that the approximation error can be arbitrarily large. We propose a new class of bounds on the marginal log-likelihood of directed latent variable models. Our approach relies on random projections to simplify the posterior. In contrast to standard variational methods, our bounds are guaranteed to be tight with high probability. We provide a new approach for learning latent variable models based on optimizing our new bounds on the log-likelihood. We demonstrate empirical improvements on benchmark datasets in vision and language for sigmoid belief networks, where a neural network is used to approximate the posterior. |
| Tasks | Latent Variable Models |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6259-variational-bayes-on-monte-carlo-steroids |
| http://papers.nips.cc/paper/6259-variational-bayes-on-monte-carlo-steroids.pdf | |
| PWC | https://paperswithcode.com/paper/variational-bayes-on-monte-carlo-steroids |
| Repo | |
| Framework | |
Computing Sentiment Scores of Verb Phrases for Vietnamese
| Title | Computing Sentiment Scores of Verb Phrases for Vietnamese |
| Authors | Thien Khai Tran, Tuoi Thi Phan |
| Abstract | |
| Tasks | Common Sense Reasoning, Machine Translation, Opinion Mining, Sentiment Analysis |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/O16-1020/ |
| https://www.aclweb.org/anthology/O16-1020 | |
| PWC | https://paperswithcode.com/paper/computing-sentiment-scores-of-verb-phrases |
| Repo | |
| Framework | |
A Machine Learning Approach to Clinical Terms Normalization
| Title | A Machine Learning Approach to Clinical Terms Normalization |
| Authors | Jos{'e} Casta{~n}o, Mar{'\i}a Laura Gambarte, Hee Joon Park, Maria del Pilar Avila Williams, David P{'e}rez, Fern Campos, o, Daniel Luna, Sonia Ben{'\i}tez, Hern{'a}n Berinsky, Sof{'\i}a Zanetti |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2901/ |
| https://www.aclweb.org/anthology/W16-2901 | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-approach-to-clinical-terms |
| Repo | |
| Framework | |
Feature Derivation for Exploitation of Distant Annotation via Pattern Induction against Dependency Parses
| Title | Feature Derivation for Exploitation of Distant Annotation via Pattern Induction against Dependency Parses |
| Authors | Dayne Freitag, John Niekrasz |
| Abstract | |
| Tasks | Relation Extraction |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2905/ |
| https://www.aclweb.org/anthology/W16-2905 | |
| PWC | https://paperswithcode.com/paper/feature-derivation-for-exploitation-of |
| Repo | |
| Framework | |
A Practical Guide to Sentiment Annotation: Challenges and Solutions
| Title | A Practical Guide to Sentiment Annotation: Challenges and Solutions |
| Authors | Saif Mohammad |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0429/ |
| https://www.aclweb.org/anthology/W16-0429 | |
| PWC | https://paperswithcode.com/paper/a-practical-guide-to-sentiment-annotation |
| Repo | |
| Framework | |
How to Train good Word Embeddings for Biomedical NLP
| Title | How to Train good Word Embeddings for Biomedical NLP |
| Authors | Billy Chiu, Gamal Crichton, Anna Korhonen, Sampo Pyysalo |
| Abstract | |
| Tasks | Learning Word Embeddings, Named Entity Recognition, Sentiment Analysis, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2922/ |
| https://www.aclweb.org/anthology/W16-2922 | |
| PWC | https://paperswithcode.com/paper/how-to-train-good-word-embeddings-for |
| Repo | |
| Framework | |
Construction of a Personal Experience Tweet Corpus for Health Surveillance
| Title | Construction of a Personal Experience Tweet Corpus for Health Surveillance |
| Authors | Keyuan Jiang, Ricardo Calix, Matrika Gupta |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2917/ |
| https://www.aclweb.org/anthology/W16-2917 | |
| PWC | https://paperswithcode.com/paper/construction-of-a-personal-experience-tweet |
| Repo | |
| Framework | |
GTI at SemEval-2016 Task 4: Training a Naive Bayes Classifier using Features of an Unsupervised System
| Title | GTI at SemEval-2016 Task 4: Training a Naive Bayes Classifier using Features of an Unsupervised System |
| Authors | Jonathan Juncal-Mart{'\i}nez, Tamara {'A}lvarez-L{'o}pez, Milagros Fern{'a}ndez-Gavilanes, Enrique Costa-Montenegro, Francisco Javier Gonz{'a}lez-Casta{~n}o |
| Abstract | |
| Tasks | Dependency Parsing, Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1016/ |
| https://www.aclweb.org/anthology/S16-1016 | |
| PWC | https://paperswithcode.com/paper/gti-at-semeval-2016-task-4-training-a-naive |
| Repo | |
| Framework | |
