October 15, 2019

1587 words 8 mins read

Paper Group NANR 250

Paper Group NANR 250

Combining Concepts and Their Translations from Structured Dictionaries of Uralic Minority Languages. Tools for Building an Interlinked Synonym Lexicon Network. Differentially Private Identity and Equivalence Testing of Discrete Distributions. Annotating Zero Anaphora for Question Answering. Annotation and Quantitative Analysis of Speaker Informatio …

Combining Concepts and Their Translations from Structured Dictionaries of Uralic Minority Languages

Title Combining Concepts and Their Translations from Structured Dictionaries of Uralic Minority Languages
Authors Mika H{"a}m{"a}l{"a}inen, Liisa Lotta Tarvainen, Jack Rueter
Abstract
Tasks Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1138/
PDF https://www.aclweb.org/anthology/L18-1138
PWC https://paperswithcode.com/paper/combining-concepts-and-their-translations
Repo
Framework

Tools for Building an Interlinked Synonym Lexicon Network

Title Tools for Building an Interlinked Synonym Lexicon Network
Authors Zde{\v{n}}ka Ure{\v{s}}ov{'a}, Eva Fu{\v{c}}{'\i}kov{'a}, Eva Haji{\v{c}}ov{'a}, Jan Haji{\v{c}}
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1136/
PDF https://www.aclweb.org/anthology/L18-1136
PWC https://paperswithcode.com/paper/tools-for-building-an-interlinked-synonym
Repo
Framework

Differentially Private Identity and Equivalence Testing of Discrete Distributions

Title Differentially Private Identity and Equivalence Testing of Discrete Distributions
Authors Maryam Aliakbarpour, Ilias Diakonikolas, Ronitt Rubinfeld
Abstract We study the fundamental problems of identity and equivalence testing over a discrete population from random samples. Our goal is to develop efficient testers while guaranteeing differential privacy to the individuals of the population. We provide sample-efficient differentially private testers for these problems. Our theoretical results significantly improve over the best known algorithms for identity testing, and are the first results for private equivalence testing. The conceptual message of our work is that there exist private hypothesis testers that are nearly as sample-efficient as their non-private counterparts. We perform an experimental evaluation of our algorithms on synthetic data. Our experiments illustrate that our private testers achieve small type I and type II errors with sample size sublinear in the domain size of the underlying distributions.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2415
PDF http://proceedings.mlr.press/v80/aliakbarpour18a/aliakbarpour18a.pdf
PWC https://paperswithcode.com/paper/differentially-private-identity-and
Repo
Framework

Annotating Zero Anaphora for Question Answering

Title Annotating Zero Anaphora for Question Answering
Authors Yoshihiko Asao, Ryu Iida, Kentaro Torisawa
Abstract
Tasks Question Answering
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1556/
PDF https://www.aclweb.org/anthology/L18-1556
PWC https://paperswithcode.com/paper/annotating-zero-anaphora-for-question
Repo
Framework

Annotation and Quantitative Analysis of Speaker Information in Novel Conversation Sentences in Japanese

Title Annotation and Quantitative Analysis of Speaker Information in Novel Conversation Sentences in Japanese
Authors Makoto Yamazaki, Yumi Miyazaki, Wakako Kashino
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1174/
PDF https://www.aclweb.org/anthology/L18-1174
PWC https://paperswithcode.com/paper/annotation-and-quantitative-analysis-of
Repo
Framework

Deep Video Quality Assessor: From Spatio-temporal Visual Sensitivity to A Convolutional Neural Aggregation Network

Title Deep Video Quality Assessor: From Spatio-temporal Visual Sensitivity to A Convolutional Neural Aggregation Network
Authors Woojae Kim, Jongyoo Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee
Abstract Incorporating spatio-temporal human visual perception into video quality assessment (VQA) remains a formidable issue. Previous statistical or computational models of spatio-temporal perception have limitations to be applied to the general VQA algorithms. In this paper, we propose a novel full-reference (FR) VQA framework named Deep Video Quality Assessor (DeepVQA) to quantify the spatio-temporal visual perception via a convolutional neural network (CNN) and a convolutional neural aggregation network (CNAN). Our framework enables to figure out the spatio-temporal sensitivity behavior through learning in accordance with the subjective score. In addition, to manipulate the temporal variation of distortions, we propose a novel temporal pooling method using an attention model. In the experiment, we show DeepVQA remarkably achieves the state-of-the-art prediction accuracy of more than 0.9 correlation, which is ~5% higher than those of conventional methods on the LIVE and CSIQ video databases.
Tasks Video Quality Assessment, Visual Question Answering
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Woojae_Kim_Deep_Video_Quality_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Woojae_Kim_Deep_Video_Quality_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/deep-video-quality-assessor-from-spatio
Repo
Framework

Improving Machine Translation of English Relative Clauses with Automatic Text Simplification

Title Improving Machine Translation of English Relative Clauses with Automatic Text Simplification
Authors Sanja {\v{S}}tajner, Maja Popovi{'c}
Abstract
Tasks Machine Translation, Text Simplification
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-7006/
PDF https://www.aclweb.org/anthology/W18-7006
PWC https://paperswithcode.com/paper/improving-machine-translation-of-english
Repo
Framework

Linking, Searching, and Visualizing Entities in Wikipedia

Title Linking, Searching, and Visualizing Entities in Wikipedia
Authors Marcus Klang, Pierre Nugues
Abstract
Tasks Entity Extraction, Named Entity Recognition, Open Information Extraction, Question Answering, Text Categorization
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1540/
PDF https://www.aclweb.org/anthology/L18-1540
PWC https://paperswithcode.com/paper/linking-searching-and-visualizing-entities-in
Repo
Framework

Gaining and Losing Influence in Online Conversation

Title Gaining and Losing Influence in Online Conversation
Authors Arun Sharma, Tomek Strzalkowski
Abstract
Tasks Dialogue Understanding, Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1110/
PDF https://www.aclweb.org/anthology/L18-1110
PWC https://paperswithcode.com/paper/gaining-and-losing-influence-in-online
Repo
Framework

AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning

Title AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning
Authors Ahmed Alaa, Mihaela Schaar
Abstract Clinical prognostic models derived from largescale healthcare data can inform critical diagnostic and therapeutic decisions. To enable off-theshelf usage of machine learning (ML) in prognostic research, we developed AUTOPROGNOSIS: a system for automating the design of predictive modeling pipelines tailored for clinical prognosis. AUTOPROGNOSIS optimizes ensembles of pipeline configurations efficiently using a novel batched Bayesian optimization (BO) algorithm that learns a low-dimensional decomposition of the pipelines’ high-dimensional hyperparameter space in concurrence with the BO procedure. This is achieved by modeling the pipelines’ performances as a black-box function with a Gaussian process prior, and modeling the “similarities” between the pipelines’ baseline algorithms via a sparse additive kernel with a Dirichlet prior. Meta-learning is used to warmstart BO with external data from “similar” patient cohorts by calibrating the priors using an algorithm that mimics the empirical Bayes method. The system automatically explains its predictions by presenting the clinicians with logical association rules that link patients’ features to predicted risk strata. We demonstrate the utility of AUTOPROGNOSIS using 10 major patient cohorts representing various aspects of cardiovascular patient care.
Tasks Meta-Learning
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2050
PDF http://proceedings.mlr.press/v80/alaa18b/alaa18b.pdf
PWC https://paperswithcode.com/paper/autoprognosis-automated-clinical-prognostic-1
Repo
Framework

WLV at SemEval-2018 Task 3: Dissecting Tweets in Search of Irony

Title WLV at SemEval-2018 Task 3: Dissecting Tweets in Search of Irony
Authors Omid Rohanian, Shiva Taslimipoor, Richard Evans, Ruslan Mitkov
Abstract This paper describes the systems submitted to SemEval 2018 Task 3 {``}Irony detection in English tweets{''} for both subtasks A and B. The first system leveraging a combination of sentiment, distributional semantic, and text surface features is ranked third among 44 teams according to the official leaderboard of the subtask A. The second system with slightly different representation of the features ranked ninth in subtask B. We present a method that entails decomposing tweets into separate parts. Searching for contrast within the constituents of a tweet is an integral part of our system. We embrace an extensive definition of contrast which leads to a vast coverage in detecting ironic content. |
Tasks Sentiment Analysis
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1090/
PDF https://www.aclweb.org/anthology/S18-1090
PWC https://paperswithcode.com/paper/wlv-at-semeval-2018-task-3-dissecting-tweets
Repo
Framework

EXPLORING NEURAL ARCHITECTURE SEARCH FOR LANGUAGE TASKS

Title EXPLORING NEURAL ARCHITECTURE SEARCH FOR LANGUAGE TASKS
Authors Minh-Thang Luong, David Dohan, Adams Wei Yu, Quoc V. Le, Barret Zoph, Vijay Vasudevan
Abstract Neural architecture search (NAS), the task of finding neural architectures automatically, has recently emerged as a promising approach for unveiling better models over human-designed ones. However, most success stories are for vision tasks and have been quite limited for text, except for a small language modeling setup. In this paper, we explore NAS for text sequences at scale, by first focusing on the task of language translation and later extending to reading comprehension. From a standard sequence-to-sequence models for translation, we conduct extensive searches over the recurrent cells and attention similarity functions across two translation tasks, IWSLT English-Vietnamese and WMT German-English. We report challenges in performing cell searches as well as demonstrate initial success on attention searches with translation improvements over strong baselines. In addition, we show that results on attention searches are transferable to reading comprehension on the SQuAD dataset.
Tasks Language Modelling, Neural Architecture Search, Reading Comprehension
Published 2018-01-01
URL https://openreview.net/forum?id=r1Zi2Mb0-
PDF https://openreview.net/pdf?id=r1Zi2Mb0-
PWC https://paperswithcode.com/paper/exploring-neural-architecture-search-for
Repo
Framework

Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network

Title Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
Authors Risi Kondor, Zhen Lin, Shubhendu Trivedi
Abstract Recent work by Cohen et al. has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis. In this paper we propose a generalization of this work that generally exhibits improved performace, but from an implementation point of view is actually simpler. An unusual feature of the proposed architecture is that it uses the Clebsch–Gordan transform as its only source of nonlinearity, thus avoiding repeated forward and backward Fourier transforms. The underlying ideas of the paper generalize to constructing neural networks that are invariant to the action of other compact groups.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/8215-clebschgordan-nets-a-fully-fourier-space-spherical-convolutional-neural-network
PDF http://papers.nips.cc/paper/8215-clebschgordan-nets-a-fully-fourier-space-spherical-convolutional-neural-network.pdf
PWC https://paperswithcode.com/paper/clebschgordan-nets-a-fully-fourier-space
Repo
Framework

Learning Deep Descriptors With Scale-Aware Triplet Networks

Title Learning Deep Descriptors With Scale-Aware Triplet Networks
Authors Michel Keller, Zetao Chen, Fabiola Maffra, Patrik Schmuck, Margarita Chli
Abstract Research on learning suitable feature descriptors for Computer Vision has recently shifted to deep learning where the biggest challenge lies with the formulation of appropriate loss functions, especially since the descriptors to be learned are not known at training time. While approaches such as Siamese and triplet losses have been applied with success, it is still not well understood what makes a good loss function. In this spirit, this work demonstrates that many commonly used losses suffer from a range of problems. Based on this analysis, we introduce mixed-context losses and scale-aware sampling, two methods that when combined enable networks to learn consistently scaled descriptors for the first time.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Keller_Learning_Deep_Descriptors_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Keller_Learning_Deep_Descriptors_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/learning-deep-descriptors-with-scale-aware
Repo
Framework

Proceedings of the Workshop on Machine Reading for Question Answering

Title Proceedings of the Workshop on Machine Reading for Question Answering
Authors
Abstract
Tasks Question Answering, Reading Comprehension
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2600/
PDF https://www.aclweb.org/anthology/W18-2600
PWC https://paperswithcode.com/paper/proceedings-of-the-workshop-on-machine-1
Repo
Framework
comments powered by Disqus