October 15, 2019

2138 words 11 mins read

Paper Group NANR 192

Paper Group NANR 192

A Very Low Resource Language Speech Corpus for Computational Language Documentation Experiments. Similarity Measures for the Detection of Clinical Conditions with Verbal Fluency Tasks. Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees. The SSIX Corpora: Three Gold Standard Corpora for Sentiment Analysis in English, Spanish a …

A Very Low Resource Language Speech Corpus for Computational Language Documentation Experiments

Title A Very Low Resource Language Speech Corpus for Computational Language Documentation Experiments
Authors Pierre Godard, Gilles Adda, Martine Adda-Decker, Juan Benjumea, Laurent Besacier, Jamison Cooper-Leavitt, Guy-Noel Kouarata, Lori Lamel, Hélène Maynard, Markus Mueller, Annie Rialland, Sebastian Stueker, François Yvon, Marcely Zanon Boito
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/papers/L18-1531/l18-1531
PDF https://www.aclweb.org/anthology/L18-1531
PWC https://paperswithcode.com/paper/a-very-low-resource-language-speech-corpus-1
Repo
Framework

Similarity Measures for the Detection of Clinical Conditions with Verbal Fluency Tasks

Title Similarity Measures for the Detection of Clinical Conditions with Verbal Fluency Tasks
Authors Felipe Paula, Rodrigo Wilkens, Marco Idiart, Aline Villavicencio
Abstract Semantic Verbal Fluency tests have been used in the detection of certain clinical conditions, like Dementia. In particular, given a sequence of semantically related words, a large number of switches from one semantic class to another has been linked to clinical conditions. In this work, we investigate three similarity measures for automatically identifying switches in semantic chains: semantic similarity from a manually constructed resource, and word association strength and semantic relatedness, both calculated from corpora. This information is used for building classifiers to distinguish healthy controls from clinical cases with early stages of Alzheimer{'}s Disease and Mild Cognitive Deficits. The overall results indicate that for clinical conditions the classifiers that use these similarity measures outperform those that use a gold standard taxonomy.
Tasks Semantic Similarity, Semantic Textual Similarity
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-2037/
PDF https://www.aclweb.org/anthology/N18-2037
PWC https://paperswithcode.com/paper/similarity-measures-for-the-detection-of
Repo
Framework

Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees

Title Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees
Authors Ola R{\o}nning, Daniel Hardt, Anders S{\o}gaard
Abstract Sluice resolution in English is the problem of finding antecedents of \textit{wh}-fronted ellipses. Previous work has relied on hand-crafted features over syntax trees that scale poorly to other languages and domains; in particular, to dialogue, which is one of the most interesting applications of sluice resolution. Syntactic information is arguably important for sluice resolution, but we show that multi-task learning with partial parsing as auxiliary tasks effectively closes the gap and buys us an additional 9{%} error reduction over previous work. Since we are not directly relying on features from partial parsers, our system is more robust to domain shifts, giving a 26{%} error reduction on embedded sluices in dialogue.
Tasks Feature Engineering, Multi-Task Learning
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-2038/
PDF https://www.aclweb.org/anthology/N18-2038
PWC https://paperswithcode.com/paper/sluice-resolution-without-hand-crafted
Repo
Framework

The SSIX Corpora: Three Gold Standard Corpora for Sentiment Analysis in English, Spanish and German Financial Microblogs

Title The SSIX Corpora: Three Gold Standard Corpora for Sentiment Analysis in English, Spanish and German Financial Microblogs
Authors Thomas Gaillat, Manel Zarrouk, Andr{'e} Freitas, Brian Davis
Abstract
Tasks Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1423/
PDF https://www.aclweb.org/anthology/L18-1423
PWC https://paperswithcode.com/paper/the-ssix-corpora-three-gold-standard-corpora
Repo
Framework

An Operation Network for Abstractive Sentence Compression

Title An Operation Network for Abstractive Sentence Compression
Authors Naitong Yu, Jie Zhang, Minlie Huang, Xiaoyan Zhu
Abstract Sentence compression condenses a sentence while preserving its most important contents. Delete-based models have the strong ability to delete undesired words, while generate-based models are able to reorder or rephrase the words, which are more coherent to human sentence compression. In this paper, we propose Operation Network, a neural network approach for abstractive sentence compression, which combines the advantages of both delete-based and generate-based sentence compression models. The central idea of Operation Network is to model the sentence compression process as an editing procedure. First, unnecessary words are deleted from the source sentence, then new words are either generated from a large vocabulary or copied directly from the source sentence. A compressed sentence can be obtained by a series of such edit operations (delete, copy and generate). Experiments show that Operation Network outperforms state-of-the-art baselines.
Tasks Sentence Compression, Text Generation
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1091/
PDF https://www.aclweb.org/anthology/C18-1091
PWC https://paperswithcode.com/paper/an-operation-network-for-abstractive-sentence
Repo
Framework

Scaling the Poisson GLM to massive neural datasets through polynomial approximations

Title Scaling the Poisson GLM to massive neural datasets through polynomial approximations
Authors David Zoltowski, Jonathan W. Pillow
Abstract Recent advances in recording technologies have allowed neuroscientists to record simultaneous spiking activity from hundreds to thousands of neurons in multiple brain regions. Such large-scale recordings pose a major challenge to existing statistical methods for neural data analysis. Here we develop highly scalable approximate inference methods for Poisson generalized linear models (GLMs) that require only a single pass over the data. Our approach relies on a recently proposed method for obtaining approximate sufficient statistics for GLMs using polynomial approximations [Huggins et al., 2017], which we adapt to the Poisson GLM setting. We focus on inference using quadratic approximations to nonlinear terms in the Poisson GLM log-likelihood with Gaussian priors, for which we derive closed-form solutions to the approximate maximum likelihood and MAP estimates, posterior distribution, and marginal likelihood. We introduce an adaptive procedure to select the polynomial approximation interval and show that the resulting method allows for efficient and accurate inference and regularization of high-dimensional parameters. We use the quadratic estimator to fit a fully-coupled Poisson GLM to spike train data recorded from 831 neurons across five regions of the mouse brain for a duration of 41 minutes, binned at 1 ms resolution. Across all neurons, this model is fit to over 2 billion spike count bins and identifies fine-timescale statistical dependencies between neurons within and across cortical and subcortical areas.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7611-scaling-the-poisson-glm-to-massive-neural-datasets-through-polynomial-approximations
PDF http://papers.nips.cc/paper/7611-scaling-the-poisson-glm-to-massive-neural-datasets-through-polynomial-approximations.pdf
PWC https://paperswithcode.com/paper/scaling-the-poisson-glm-to-massive-neural
Repo
Framework

Proceedings of the Eight Workshop on Cognitive Aspects of Computational Language Learning and Processing

Title Proceedings of the Eight Workshop on Cognitive Aspects of Computational Language Learning and Processing
Authors
Abstract
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2800/
PDF https://www.aclweb.org/anthology/W18-2800
PWC https://paperswithcode.com/paper/proceedings-of-the-eight-workshop-on
Repo
Framework

Elicitation protocol and material for a corpus of long prepared monologues in Sign Language

Title Elicitation protocol and material for a corpus of long prepared monologues in Sign Language
Authors Michael Filhol, Mohamed Nassime Hadjadj
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1669/
PDF https://www.aclweb.org/anthology/L18-1669
PWC https://paperswithcode.com/paper/elicitation-protocol-and-material-for-a
Repo
Framework

Seq2Seq Models with Dropout can Learn Generalizable Reduplication

Title Seq2Seq Models with Dropout can Learn Generalizable Reduplication
Authors Br Prickett, on, Aaron Traylor, Joe Pater
Abstract Natural language reduplication can pose a challenge to neural models of language, and has been argued to require variables (Marcus et al., 1999). Sequence-to-sequence neural networks have been shown to perform well at a number of other morphological tasks (Cotterell et al., 2016), and produce results that highly correlate with human behavior (Kirov, 2017; Kirov {&} Cotterell, 2018) but do not include any explicit variables in their architecture. We find that they can learn a reduplicative pattern that generalizes to novel segments if they are trained with dropout (Srivastava et al., 2014). We argue that this matches the scope of generalization observed in human reduplication.
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5810/
PDF https://www.aclweb.org/anthology/W18-5810
PWC https://paperswithcode.com/paper/seq2seq-models-with-dropout-can-learn
Repo
Framework

Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Title Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Authors
Abstract
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-2000/
PDF https://www.aclweb.org/anthology/N18-2000
PWC https://paperswithcode.com/paper/proceedings-of-the-2018-conference-of-the-4
Repo
Framework

The Well-Tempered Lasso

Title The Well-Tempered Lasso
Authors Yuanzhi Li, Yoram Singer
Abstract We study the complexity of the entire regularization path for least squares regression with 1-norm penalty, known as the Lasso. Every regression parameter in the Lasso changes linearly as a function of the regularization value. The number of changes is regarded as the Lasso’s complexity. Experimental results using exact path following exhibit polynomial complexity of the Lasso in the problem size. Alas, the path complexity of the Lasso on artificially designed regression problems is exponential We use smoothed analysis as a mechanism for bridging the gap between worst case settings and the de facto low complexity. Our analysis assumes that the observed data has a tiny amount of intrinsic noise. We then prove that the Lasso’s complexity is polynomial in the problem size.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2401
PDF http://proceedings.mlr.press/v80/li18f/li18f.pdf
PWC https://paperswithcode.com/paper/the-well-tempered-lasso-1
Repo
Framework

Memory Architectures in Recurrent Neural Network Language Models

Title Memory Architectures in Recurrent Neural Network Language Models
Authors Dani Yogatama, Yishu Miao, Gabor Melis, Wang Ling, Adhiguna Kuncoro, Chris Dyer, Phil Blunsom
Abstract We compare and analyze sequential, random access, and stack memory architectures for recurrent neural network language models. Our experiments on the Penn Treebank and Wikitext-2 datasets show that stack-based memory architectures consistently achieve the best performance in terms of held out perplexity. We also propose a generalization to existing continuous stack models (Joulin & Mikolov,2015; Grefenstette et al., 2015) to allow a variable number of pop operations more naturally that further improves performance. We further evaluate these language models in terms of their ability to capture non-local syntactic dependencies on a subject-verb agreement dataset (Linzen et al., 2016) and establish new state of the art results using memory augmented language models. Our results demonstrate the value of stack-structured memory for explaining the distribution of words in natural language, in line with linguistic theories claiming a context-free backbone for natural language.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=SkFqf0lAZ
PDF https://openreview.net/pdf?id=SkFqf0lAZ
PWC https://paperswithcode.com/paper/memory-architectures-in-recurrent-neural
Repo
Framework

HydraNets: Specialized Dynamic Architectures for Efficient Inference

Title HydraNets: Specialized Dynamic Architectures for Efficient Inference
Authors Ravi Teja Mullapudi, William R. Mark, Noam Shazeer, Kayvon Fatahalian
Abstract There is growing interest in improving the design of deep network architectures to be both accurate and low cost. This paper explores semantic specialization as a mechanism for improving the computational efficiency (accuracy-per-unit-cost) of inference in the context of image classification. Specifically, we propose a network architecture template called HydraNet, which enables state-of-the-art architectures for image classification to be transformed into dynamic architectures which exploit conditional execution for efficient inference. HydraNets are wide networks containing distinct components specialized to compute features for visually similar classes, but they retain efficiency by dynamically selecting only a small number of components to evaluate for any one input image. This design is made possible by a soft gating mechanism that encourages component specialization during training and accurately performs component selection during inference. We evaluate the HydraNet approach on both the CIFAR-100 and ImageNet classification tasks. On CIFAR, applying the HydraNet template to the ResNet and DenseNet family of models reduces inference cost by 2-4x while retaining the accuracy of the baseline architectures. On ImageNet, applying the HydraNet template improves accuracy up to 2.5% when compared to an efficient baseline architecture with similar inference cost.
Tasks Image Classification
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Mullapudi_HydraNets_Specialized_Dynamic_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Mullapudi_HydraNets_Specialized_Dynamic_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/hydranets-specialized-dynamic-architectures
Repo
Framework

Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back

Title Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back
Authors Elliot Meyerson, Risto Miikkulainen
Abstract Deep multitask learning boosts performance by sharing learned structure across related tasks. This paper adapts ideas from deep multitask learning to the setting where only a single task is available. The method is formalized as pseudo-task augmentation, in which models are trained with multiple decoders for each task. Pseudo-tasks simulate the effect of training towards closely-related tasks drawn from the same universe. In a suite of experiments, pseudo-task augmentation is shown to improve performance on single-task learning problems. When combined with multitask learning, further improvements are achieved, including state-of-the-art performance on the CelebA dataset, showing that pseudo-task augmentation and multitask learning have complementary value. All in all, pseudo-task augmentation is a broadly applicable and efficient way to boost performance in deep learning systems.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2256
PDF http://proceedings.mlr.press/v80/meyerson18a/meyerson18a.pdf
PWC https://paperswithcode.com/paper/pseudo-task-augmentation-from-deep-multitask-1
Repo
Framework

Corpus Creation and Emotion Prediction for Hindi-English Code-Mixed Social Media Text

Title Corpus Creation and Emotion Prediction for Hindi-English Code-Mixed Social Media Text
Authors Deepanshu Vijay, Aditya Bohra, Vinay Singh, Syed Sarfaraz Akhtar, Manish Shrivastava
Abstract Emotion Prediction is a Natural Language Processing (NLP) task dealing with detection and classification of emotions in various monolingual and bilingual texts. While some work has been done on code-mixed social media text and in emotion prediction separately, our work is the first attempt which aims at identifying the emotion associated with Hindi-English code-mixed social media text. In this paper, we analyze the problem of emotion identification in code-mixed content and present a Hindi-English code-mixed corpus extracted from twitter and annotated with the associated emotion. For every tweet in the dataset, we annotate the source language of all the words present, and also the causal language of the expressed emotion. Finally, we propose a supervised classification system which uses various machine learning techniques for detecting the emotion associated with the text using a variety of character level, word level, and lexicon based features.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-4018/
PDF https://www.aclweb.org/anthology/N18-4018
PWC https://paperswithcode.com/paper/corpus-creation-and-emotion-prediction-for
Repo
Framework
comments powered by Disqus