October 15, 2019

2060 words 10 mins read

Paper Group NANR 132

Paper Group NANR 132

Word Embeddings-Based Uncertainty Detection in Financial Disclosures. EmotionX-DLC: Self-Attentive BiLSTM for Detecting Sequential Emotions in Dialogues. Sentence Classification for Investment Rules Detection. Significantly Fast and Robust Fuzzy C-MeansClustering Algorithm Based on MorphologicalReconstruction and Membership Filtering. A Helping Han …

Word Embeddings-Based Uncertainty Detection in Financial Disclosures

Title Word Embeddings-Based Uncertainty Detection in Financial Disclosures
Authors Christoph Kilian Theil, Sanja {\v{S}}tajner, Heiner Stuckenschmidt
Abstract In this paper, we use NLP techniques to detect linguistic uncertainty in financial disclosures. Leveraging general-domain and domain-specific word embedding models, we automatically expand an existing dictionary of uncertainty triggers. We furthermore examine how an expert filtering affects the quality of such an expansion. We show that the dictionary expansions significantly improve regressions on stock return volatility. Lastly, we prove that the expansions significantly boost the automatic detection of uncertain sentences.
Tasks Sentence Classification, Word Embeddings
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3104/
PDF https://www.aclweb.org/anthology/W18-3104
PWC https://paperswithcode.com/paper/word-embeddings-based-uncertainty-detection
Repo
Framework

EmotionX-DLC: Self-Attentive BiLSTM for Detecting Sequential Emotions in Dialogues

Title EmotionX-DLC: Self-Attentive BiLSTM for Detecting Sequential Emotions in Dialogues
Authors Linkai Luo, Haiqin Yang, Francis Y. L. Chin
Abstract In this paper, we propose a self-attentive bidirectional long short-term memory (SA-BiLSTM) network to predict multiple emotions for the EmotionX challenge. The BiLSTM exhibits the power of modeling the word dependencies, and extracting the most relevant features for emotion classification. Building on top of BiLSTM, the self-attentive network can model the contextual dependencies between utterances which are helpful for classifying the ambiguous emotions. We achieve 59.6 and 55.0 unweighted accuracy scores in the Friends and the EmotionPush test sets, respectively.
Tasks Emotion Classification, Sentence Classification, Sentence Embedding
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3506/
PDF https://www.aclweb.org/anthology/W18-3506
PWC https://paperswithcode.com/paper/emotionx-dlc-self-attentive-bilstm-for
Repo
Framework

Sentence Classification for Investment Rules Detection

Title Sentence Classification for Investment Rules Detection
Authors Youness Mansar, Sira Ferradans
Abstract In the last years, compliance requirements for the banking sector have greatly augmented, making the current compliance processes difficult to maintain. Any process that allows to accelerate the identification and implementation of compliance requirements can help address this issues. The contributions of the paper are twofold: we propose a new NLP task that is the investment rule detection, and a group of methods identify them. We show that the proposed methods are highly performing and fast, thus can be deployed in production.
Tasks Sentence Classification
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3106/
PDF https://www.aclweb.org/anthology/W18-3106
PWC https://paperswithcode.com/paper/sentence-classification-for-investment-rules
Repo
Framework

Significantly Fast and Robust Fuzzy C-MeansClustering Algorithm Based on MorphologicalReconstruction and Membership Filtering

Title Significantly Fast and Robust Fuzzy C-MeansClustering Algorithm Based on MorphologicalReconstruction and Membership Filtering
Authors Tao Lei, Xiaohong Jia, Yanning Zhang, Senior Member, IEEE, Lifeng He, Senior Member, IEEE, Hongy-ing Meng, Senior Member, IEEE, and Asoke K. Nandi, Fellow, IEEE
Abstract As fuzzy c-means clustering (FCM) algorithm issensitive to noise, local spatial information is often introducedto an objective function to improve the robustness of the FCMalgorithm for image segmentation. However, the introduction oflocal spatial information often leads to a high computationalcomplexity, arising out of an iterative calculation of the distancebetween pixels within local spatial neighbors and clusteringcenters. To address this issue, an improved FCM algorithmbased on morphological reconstruction and membership filtering(FRFCM) that is significantly faster and more robust than FCM,is proposed in this paper. Firstly, the local spatial informationof images is incorporated into FRFCM by introducing mor-phological reconstruction operation to guarantee noise-immunityand image detail-preservation. Secondly, the modification ofmembership partition, based on the distance between pixelswithin local spatial neighbors and clustering centers, is replacedby local membership filtering that depends only on the spatialneighbors of membership partition. Compared to state-of-the-art algorithms, the proposed FRFCM algorithm is simpler andsignificantly faster, since it is unnecessary to compute the distancebetween pixels within local spatial neighbors and clusteringcenters. In addition, it is efficient for noisy image segmentationbecause membership filtering are able to improve membershippartition matrix efficiently. Experiments performed on syntheticand real-world images demonstrate that the proposed algorithmnot only achieves better results, but also requires less time thanstate-of-the-art algorithms for image segmentation.
Tasks Semantic Segmentation
Published 2018-01-23
URL https://ieeexplore.ieee.org/document/8265186
PDF https://ieeexplore.ieee.org/document/8265186
PWC https://paperswithcode.com/paper/significantly-fast-and-robust-fuzzy-c
Repo
Framework

A Helping Hand: Transfer Learning for Deep Sentiment Analysis

Title A Helping Hand: Transfer Learning for Deep Sentiment Analysis
Authors Xin Dong, Gerard de Melo
Abstract Deep convolutional neural networks excel at sentiment polarity classification, but tend to require substantial amounts of training data, which moreover differs quite significantly between domains. In this work, we present an approach to feed generic cues into the training process of such networks, leading to better generalization abilities given limited training data. We propose to induce sentiment embeddings via supervision on extrinsic data, which are then fed into the model via a dedicated memory-based component. We observe significant gains in effectiveness on a range of different datasets in seven different languages.
Tasks Sentiment Analysis, Transfer Learning, Word Embeddings
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1235/
PDF https://www.aclweb.org/anthology/P18-1235
PWC https://paperswithcode.com/paper/a-helping-hand-transfer-learning-for-deep
Repo
Framework

A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery

Title A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery
Authors Xiao Zhang, Lingxiao Wang, Yaodong Yu, Quanquan Gu
Abstract We propose a primal-dual based framework for analyzing the global optimality of nonconvex low-rank matrix recovery. Our analysis are based on the restricted strongly convex and smooth conditions, which can be verified for a broad family of loss functions. In addition, our analytic framework can directly handle the widely-used incoherence constraints through the lens of duality. We illustrate the applicability of the proposed framework to matrix completion and one-bit matrix completion, and prove that all these problems have no spurious local minima. Our results not only improve the sample complexity required for characterizing the global optimality of matrix completion, but also resolve an open problem in Ge et al. (2017) regarding one-bit matrix completion. Numerical experiments show that primal-dual based algorithm can successfully recover the global optimum for various low-rank problems.
Tasks Matrix Completion
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2096
PDF http://proceedings.mlr.press/v80/zhang18m/zhang18m.pdf
PWC https://paperswithcode.com/paper/a-primal-dual-analysis-of-global-optimality
Repo
Framework

Building a Finnish SOM-based ontology concept tagger and harvester

Title Building a Finnish SOM-based ontology concept tagger and harvester
Authors Seppo Nyrkk{"o}
Abstract
Tasks Information Retrieval, Morphological Analysis, Word Sense Disambiguation
Published 2018-01-01
URL https://www.aclweb.org/anthology/W18-0202/
PDF https://www.aclweb.org/anthology/W18-0202
PWC https://paperswithcode.com/paper/building-a-finnish-som-based-ontology-concept
Repo
Framework

Joint Modeling of Structure Identification and Nuclearity Recognition in Macro Chinese Discourse Treebank

Title Joint Modeling of Structure Identification and Nuclearity Recognition in Macro Chinese Discourse Treebank
Authors Xiaomin Chu, Feng Jiang, Yi Zhou, Guodong Zhou, Qiaoming Zhu
Abstract Discourse parsing is a challenging task and plays a critical role in discourse analysis. This paper focus on the macro level discourse structure analysis, which has been less studied in the previous researches. We explore a macro discourse structure presentation schema to present the macro level discourse structure, and propose a corresponding corpus, named Macro Chinese Discourse Treebank. On these bases, we concentrate on two tasks of macro discourse structure analysis, including structure identification and nuclearity recognition. In order to reduce the error transmission between the associated tasks, we adopt a joint model of the two tasks, and an Integer Linear Programming approach is proposed to achieve global optimization with various kinds of constraints.
Tasks Machine Translation, Question Answering, Text Summarization
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1045/
PDF https://www.aclweb.org/anthology/C18-1045
PWC https://paperswithcode.com/paper/joint-modeling-of-structure-identification
Repo
Framework

Sound-aligned corpus of Udmurt dialectal texts

Title Sound-aligned corpus of Udmurt dialectal texts
Authors Timofey Arkhangelskiy, Ekaterina Georgieva
Abstract
Tasks
Published 2018-01-01
URL https://www.aclweb.org/anthology/W18-0203/
PDF https://www.aclweb.org/anthology/W18-0203
PWC https://paperswithcode.com/paper/sound-aligned-corpus-of-udmurt-dialectal
Repo
Framework

Data-Driven Pronunciation Modeling of Swiss German Dialectal Speech for Automatic Speech Recognition

Title Data-Driven Pronunciation Modeling of Swiss German Dialectal Speech for Automatic Speech Recognition
Authors Michael Stadtschnitzer, Christoph Schmidt
Abstract
Tasks Information Retrieval, Language Modelling, Robust Speech Recognition, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1498/
PDF https://www.aclweb.org/anthology/L18-1498
PWC https://paperswithcode.com/paper/data-driven-pronunciation-modeling-of-swiss
Repo
Framework

Proceedings of the Society for Computation in Linguistics (SCiL) 2018

Title Proceedings of the Society for Computation in Linguistics (SCiL) 2018
Authors
Abstract
Tasks
Published 2018-01-01
URL https://www.aclweb.org/anthology/W18-0300/
PDF https://www.aclweb.org/anthology/W18-0300
PWC https://paperswithcode.com/paper/proceedings-of-the-society-for-computation-in
Repo
Framework

Learning To Learn Around A Common Mean

Title Learning To Learn Around A Common Mean
Authors Giulia Denevi, Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil
Abstract The problem of learning-to-learn (LTL) or meta-learning is gaining increasing attention due to recent empirical evidence of its effectiveness in applications. The goal addressed in LTL is to select an algorithm that works well on tasks sampled from a meta-distribution. In this work, we consider the family of algorithms given by a variant of Ridge Regression, in which the regularizer is the square distance to an unknown mean vector. We show that, in this setting, the LTL problem can be reformulated as a Least Squares (LS) problem and we exploit a novel meta- algorithm to efficiently solve it. At each iteration the meta-algorithm processes only one dataset. Specifically, it firstly estimates the stochastic LS objective function, by splitting this dataset into two subsets used to train and test the inner algorithm, respectively. Secondly, it performs a stochastic gradient step with the estimated value. Under specific assumptions, we present a bound for the generalization error of our meta-algorithm, which suggests the right splitting parameter to choose. When the hyper-parameters of the problem are fixed, this bound is consistent as the number of tasks grows, even if the sample size is kept constant. Preliminary experiments confirm our theoretical findings, highlighting the advantage of our approach, with respect to independent task learning.
Tasks Meta-Learning
Published 2018-12-01
URL http://papers.nips.cc/paper/8220-learning-to-learn-around-a-common-mean
PDF http://papers.nips.cc/paper/8220-learning-to-learn-around-a-common-mean.pdf
PWC https://paperswithcode.com/paper/learning-to-learn-around-a-common-mean
Repo
Framework

Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching

Title Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching
Authors Johannes L. Schonberger, Sudipta N. Sinha, Marc Pollefeys
Abstract Semi-Global Matching (SGM) uses an aggregation scheme to combine costs from multiple 1D scanline optimizations that tends to hurt its accuracy in difficult scenarios. We propose replacing this aggregation scheme with a new learning-based method that fuses disparity proposals estimated using scanline optimization. Our proposed SGM-Forest algorithm solves this problem using per-pixel classification. SGM-Forest currently ranks 1st on the ETH3D stereo benchmark and is ranked competitively on the Middlebury 2014 and KITTI 2015 benchmarks. It consistently outperforms SGM in challenging settings and under difficult training protocols that demonstrate robust generalization, while adding only a small computational overhead to SGM.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Johannes_Schoenberger_Learning_to_Fuse_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Johannes_Schoenberger_Learning_to_Fuse_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/learning-to-fuse-proposals-from-multiple
Repo
Framework

Cogent: A Generic Dialogue System Shell Based on a Collaborative Problem Solving Model

Title Cogent: A Generic Dialogue System Shell Based on a Collaborative Problem Solving Model
Authors Lucian Galescu, Choh Man Teng, James Allen, Ian Perera
Abstract The bulk of current research in dialogue systems is focused on fairly simple task models, primarily state-based. Progress on developing dialogue systems for more complex tasks has been limited by the lack generic toolkits to build from. In this paper we report on our development from the ground up of a new dialogue model based on collaborative problem solving. We implemented the model in a dialogue system shell (Cogent) that al-lows developers to plug in problem-solving agents to create dialogue systems in new domains. The Cogent shell has now been used by several independent teams of researchers to develop dialogue systems in different domains, with varied lexicons and interaction style, each with their own problem-solving back-end. We believe this to be the first practical demonstration of the feasibility of a CPS-based dialogue system shell.
Tasks Dialogue Management, Dialogue State Tracking
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5048/
PDF https://www.aclweb.org/anthology/W18-5048
PWC https://paperswithcode.com/paper/cogent-a-generic-dialogue-system-shell-based
Repo
Framework

HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUs

Title HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUs
Authors Zerong Zheng, Tao Yu, Hao Li, Kaiwen Guo, Qionghai Dai, Lu Fang, Yebin Liu
Abstract We propose a light-weight and highly robust real-time human performance capture method based on a single depth camera and sparse inertial measurement units (IMUs). The proposed method combines non-rigid surface tracking and volumetric surface fusion to simultaneously reconstruct challenging motions, detailed geometries and the inner human body shapes of a clothed subject. The proposed hybrid motion tracking algorithm and efficient per-frame sensor calibration technique enable non-rigid surface reconstruction for fast motions and challenging poses with severe occlusions. Significant fusion artifacts are reduced using a new confidence measurement for our adaptive TSDF-based fusion. The above contributions benefit each other in our real-time reconstruction system, which enable practical human performance capture that is real-time, robust, low-cost and easy to deploy. Our experiments show how extremely challenging performances and loop closure problems can be handled successfully.
Tasks Calibration
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Zerong_Zheng_HybridFusion_Real-Time_Performance_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Zerong_Zheng_HybridFusion_Real-Time_Performance_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/hybridfusion-real-time-performance-capture
Repo
Framework
comments powered by Disqus