October 15, 2019

2653 words 13 mins read

Paper Group NANR 120

Paper Group NANR 120

Automatic Generation of Wiktionary Entries for Finno-Ugric Minority Languages. Bilevel learning of the Group Lasso structure. On the Local Hessian in Back-propagation. Initial Experiments in Data-Driven Morphological Analysis for Finnish. Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation. Direc …

Automatic Generation of Wiktionary Entries for Finno-Ugric Minority Languages

Title Automatic Generation of Wiktionary Entries for Finno-Ugric Minority Languages
Authors Zsanett Ferenczi, Iv{'a}n Mittelholcz, Eszter Simon
Abstract
Tasks
Published 2018-01-01
URL https://www.aclweb.org/anthology/W18-0204/
PDF https://www.aclweb.org/anthology/W18-0204
PWC https://paperswithcode.com/paper/automatic-generation-of-wiktionary-entries
Repo
Framework

Bilevel learning of the Group Lasso structure

Title Bilevel learning of the Group Lasso structure
Authors Jordan Frecon, Saverio Salzo, Massimiliano Pontil
Abstract Regression with group-sparsity penalty plays a central role in high-dimensional prediction problems. Most of existing methods require the group structure to be known a priori. In practice, this may be a too strong assumption, potentially hampering the effectiveness of the regularization method. To circumvent this issue, we present a method to estimate the group structure by means of a continuous bilevel optimization problem where the data is split into training and validation sets. Our approach relies on an approximation scheme where the lower level problem is replaced by a smooth dual forward-backward algorithm with Bregman distances. We provide guarantees regarding the convergence of the approximate procedure to the exact problem and demonstrate the well behaviour of the proposed method on synthetic experiments. Finally, a preliminary application to genes expression data is tackled with the purpose of unveiling functional groups.
Tasks bilevel optimization
Published 2018-12-01
URL http://papers.nips.cc/paper/8051-bilevel-learning-of-the-group-lasso-structure
PDF http://papers.nips.cc/paper/8051-bilevel-learning-of-the-group-lasso-structure.pdf
PWC https://paperswithcode.com/paper/bilevel-learning-of-the-group-lasso-structure
Repo
Framework

On the Local Hessian in Back-propagation

Title On the Local Hessian in Back-propagation
Authors Huishuai Zhang, Wei Chen, Tie-Yan Liu
Abstract Back-propagation (BP) is the foundation for successfully training deep neural networks. However, BP sometimes has difficulties in propagating a learning signal deep enough effectively, e.g., the vanishing gradient phenomenon. Meanwhile, BP often works well when combining with ``designing tricks’’ like orthogonal initialization, batch normalization and skip connection. There is no clear understanding on what is essential to the efficiency of BP. In this paper, we take one step towards clarifying this problem. We view BP as a solution of back-matching propagation which minimizes a sequence of back-matching losses each corresponding to one block of the network. We study the Hessian of the local back-matching loss (local Hessian) and connect it to the efficiency of BP. It turns out that those designing tricks facilitate BP by improving the spectrum of local Hessian. In addition, we can utilize the local Hessian to balance the training pace of each block and design new training algorithms. Based on a scalar approximation of local Hessian, we propose a scale-amended SGD algorithm. We apply it to train neural networks with batch normalization, and achieve favorable results over vanilla SGD. This corroborates the importance of local Hessian from another side. |
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7887-on-the-local-hessian-in-back-propagation
PDF http://papers.nips.cc/paper/7887-on-the-local-hessian-in-back-propagation.pdf
PWC https://paperswithcode.com/paper/on-the-local-hessian-in-back-propagation
Repo
Framework

Initial Experiments in Data-Driven Morphological Analysis for Finnish

Title Initial Experiments in Data-Driven Morphological Analysis for Finnish
Authors Miikka Silfverberg, Mans Hulden
Abstract
Tasks Morphological Analysis, Word Embeddings
Published 2018-01-01
URL https://www.aclweb.org/anthology/W18-0209/
PDF https://www.aclweb.org/anthology/W18-0209
PWC https://paperswithcode.com/paper/initial-experiments-in-data-driven
Repo
Framework

Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation

Title Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation
Authors Tao Song, Leiyu Sun, Di Xie, Haiming Sun, Shiliang Pu
Abstract A critical issue in pedestrian detection is to detect small-scale objects that will introduce feeble contrast and motion blur in images and videos, which in our opinion should partially resort to deep-rooted annotation bias. Motivated by this, we propose a novel method integrated with somatic topological line localization (TLL) and temporal feature aggregation for detecting multi-scale pedestrians, which works particularly well with small-scale pedestrians that are relatively far from the camera. Moreover, a post-processing scheme based on Markov Ran- dom Field (MRF) is introduced to eliminate ambiguities in occlusion cases. Applying with these methodologies comprehensively, we achieve best detection performance on Caltech benchmark and improve performance of small-scale objects signicantly (miss rate decreases from 74.53% to 60.79%). Beyond this, we also achieve competitive performance on CityPersons dataset and show the existence of annotation bias in KITTI dataset.
Tasks Pedestrian Detection
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Tao_Song_Small-scale_Pedestrian_Detection_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Tao_Song_Small-scale_Pedestrian_Detection_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/small-scale-pedestrian-detection-based-on-1
Repo
Framework

Direct Shape Regression Networks for End-to-End Face Alignment

Title Direct Shape Regression Networks for End-to-End Face Alignment
Authors Xin Miao, Xiantong Zhen, Xianglong Liu, Cheng Deng, Vassilis Athitsos, Heng Huang
Abstract Face alignment has been extensively studied in computer vision community due to its fundamental role in facial analysis, but it remains an unsolved problem. The major challenges lie in the highly nonlinear relationship between face images and associated facial shapes, which is coupled by underlying correlation of landmarks. Existing methods mainly rely on cascaded regression, suffering from intrinsic shortcomings, e.g., strong dependency on initialization and failure to exploit landmark correlations. In this paper, we propose the direct shape regression network (DSRN) for end-to-end face alignment by jointly handling the aforementioned challenges in a unified framework. Specifically, by deploying doubly convolutional layer and by using the Fourier feature pooling layer proposed in this paper, DSRN efficiently constructs strong representations to disentangle highly nonlinear relationships between images and shapes; by incorporating a linear layer of low-rank learning, DSRN effectively encodes correlations of landmarks to improve performance. DSRN leverages the strengths of kernels for nonlinear feature extraction and neural networks for structured prediction, and provides the first end-to-end learning architecture for direct face alignment. Its effectiveness and generality are validated by extensive experiments on five benchmark datasets, including AFLW, 300W, CelebA, MAFL, and 300VW. All empirical results demonstrate that DSRN consistently produces high performance and in most cases surpasses state-of-the-art.
Tasks Face Alignment, Structured Prediction
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Miao_Direct_Shape_Regression_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Miao_Direct_Shape_Regression_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/direct-shape-regression-networks-for-end-to
Repo
Framework

Variance-Reduced Stochastic Gradient Descent on Streaming Data

Title Variance-Reduced Stochastic Gradient Descent on Streaming Data
Authors Ellango Jothimurugesan, Ashraf Tahmasbi, Phillip Gibbons, Srikanta Tirthapura
Abstract We present an algorithm STRSAGA for efficiently maintaining a machine learning model over data points that arrive over time, quickly updating the model as new training data is observed. We present a competitive analysis comparing the sub-optimality of the model maintained by STRSAGA with that of an offline algorithm that is given the entire data beforehand, and analyze the risk-competitiveness of STRSAGA under different arrival patterns. Our theoretical and experimental results show that the risk of STRSAGA is comparable to that of offline algorithms on a variety of input arrival patterns, and its experimental performance is significantly better than prior algorithms suited for streaming data, such as SGD and SSVRG.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/8196-variance-reduced-stochastic-gradient-descent-on-streaming-data
PDF http://papers.nips.cc/paper/8196-variance-reduced-stochastic-gradient-descent-on-streaming-data.pdf
PWC https://paperswithcode.com/paper/variance-reduced-stochastic-gradient-descent
Repo
Framework

Towards Generating Personalized Hospitalization Summaries

Title Towards Generating Personalized Hospitalization Summaries
Authors Sabita Acharya, Barbara Di Eugenio, Andrew Boyd, Richard Cameron, Karen Dunn Lopez, Pamela Martyn-Nemeth, Carolyn Dickens, Amer Ardati
Abstract Most of the health documents, including patient education materials and discharge notes, are usually flooded with medical jargons and contain a lot of generic information about the health issue. In addition, patients are only provided with the doctor{'}s perspective of what happened to them in the hospital while the care procedure performed by nurses during their entire hospital stay is nowhere included. The main focus of this research is to generate personalized hospital-stay summaries for patients by combining information from physician discharge notes and nursing plan of care. It uses a metric to identify medical concepts that are Complex, extracts definitions for the concept from three external knowledge sources, and provides the simplest definition to the patient. It also takes various features of the patient into account, like their concerns and strengths, ability to understand basic health information, level of engagement in taking care of their health, and familiarity with the health issue and personalizes the content of the summaries accordingly. Our evaluation showed that the summaries contain 80{%} of the medical concepts that are considered as being important by both doctor and nurses. Three patient advisors (i.e. individuals who are trained in understanding patient experience extensively) verified the usability of our summaries and mentioned that they would like to get such summaries when they are discharged from hospital.
Tasks Document Summarization, Multi-Document Summarization, Text Generation
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-4011/
PDF https://www.aclweb.org/anthology/N18-4011
PWC https://paperswithcode.com/paper/towards-generating-personalized
Repo
Framework
Title Give Me More Feedback: Annotating Argument Persuasiveness and Related Attributes in Student Essays
Authors Winston Carlile, Nishant Gurrapadi, Zixuan Ke, Vincent Ng
Abstract While argument persuasiveness is one of the most important dimensions of argumentative essay quality, it is relatively little studied in automated essay scoring research. Progress on scoring argument persuasiveness is hindered in part by the scarcity of annotated corpora. We present the first corpus of essays that are simultaneously annotated with argument components, argument persuasiveness scores, and attributes of argument components that impact an argument{'}s persuasiveness. This corpus could trigger the development of novel computational models concerning argument persuasiveness that provide useful feedback to students on why their arguments are (un)persuasive in addition to how persuasive they are.
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1058/
PDF https://www.aclweb.org/anthology/P18-1058
PWC https://paperswithcode.com/paper/give-me-more-feedback-annotating-argument
Repo
Framework

A Comparison of Character Neural Language Model and Bootstrapping for Language Identification in Multilingual Noisy Texts

Title A Comparison of Character Neural Language Model and Bootstrapping for Language Identification in Multilingual Noisy Texts
Authors Wafia Adouane, Simon Dobnik, Jean-Philippe Bernardy, Nasredine Semmar
Abstract This paper seeks to examine the effect of including background knowledge in the form of character pre-trained neural language model (LM), and data bootstrapping to overcome the problem of unbalanced limited resources. As a test, we explore the task of language identification in mixed-language short non-edited texts with an under-resourced language, namely the case of Algerian Arabic for which both labelled and unlabelled data are limited. We compare the performance of two traditional machine learning methods and a deep neural networks (DNNs) model. The results show that overall DNNs perform better on labelled data for the majority categories and struggle with the minority ones. While the effect of the untokenised and unlabelled data encoded as LM differs for each category, bootstrapping, however, improves the performance of all systems and all categories. These methods are language independent and could be generalised to other under-resourced languages for which a small labelled data and a larger unlabelled data are available.
Tasks Language Identification, Language Modelling, Multi-Task Learning
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-1203/
PDF https://www.aclweb.org/anthology/W18-1203
PWC https://paperswithcode.com/paper/a-comparison-of-character-neural-language
Repo
Framework

Bi-box Regression for Pedestrian Detection and Occlusion Estimation

Title Bi-box Regression for Pedestrian Detection and Occlusion Estimation
Authors Chunluan Zhou, Junsong Yuan
Abstract Occlusions present a great challenge for pedestrian detection in practical applications. In this paper, we propose a novel approach to simultaneous pedestrian detection and occlusion estimation by regressing two bounding boxes to localize the full body as well as the visible part of a pedestrian respectively. For this purpose, we learn a deep convolutional neural network (CNN) consisting of two branches, one for full body estimation and the other for visible part estimation. The two branches are treated differently during training such that they are learned to produce complementary outputs which can be further fused to improve detection performance. The full body estimation branch is trained to regress full body regions for positive pedestrian proposals, while the visible part estimation branch is trained to regress visible part regions for both positive and negative pedestrian proposals. The visible part region of a negative pedestrian proposal is forced to shrink to its center. In addition, we introduce a new criterion for selecting positive training examples, which contributes largely to heavily occluded pedestrian detection. We validate the effectiveness of the proposed bi-box regression approach on the Caltech and CityPersons datasets. Experimental results show that our approach achieves promising performance for detecting both non-occluded and occluded pedestrians, especially heavily occluded ones.
Tasks Pedestrian Detection
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/CHUNLUAN_ZHOU_Bi-box_Regression_for_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/CHUNLUAN_ZHOU_Bi-box_Regression_for_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/bi-box-regression-for-pedestrian-detection
Repo
Framework

Disney at IEST 2018: Predicting Emotions using an Ensemble

Title Disney at IEST 2018: Predicting Emotions using an Ensemble
Authors Wojciech Witon, Pierre Colombo, Ashutosh Modi, Mubbasir Kapadia
Abstract This paper describes our participating system in the WASSA 2018 shared task on emotion prediction. The task focuses on implicit emotion prediction in a tweet. In this task, keywords corresponding to the six emotion labels used (anger, fear, disgust, joy, sad, and surprise) have been removed from the tweet text, making emotion prediction implicit and the task challenging. We propose a model based on an ensemble of classifiers for prediction. Each classifier uses a sequence of Convolutional Neural Network (CNN) architecture blocks and uses ELMo (Embeddings from Language Model) as an input. Our system achieves a 66.2{%} F1 score on the test set. The best performing system in the shared task has reported a 71.4{%} F1 score.
Tasks Emotion Classification, Language Modelling, Sentence Classification, Sentence Embedding, Sentiment Analysis
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6236/
PDF https://www.aclweb.org/anthology/W18-6236
PWC https://paperswithcode.com/paper/disney-at-iest-2018-predicting-emotions-using
Repo
Framework

The BQ Corpus: A Large-scale Domain-specific Chinese Corpus For Sentence Semantic Equivalence Identification

Title The BQ Corpus: A Large-scale Domain-specific Chinese Corpus For Sentence Semantic Equivalence Identification
Authors Jing Chen, Qingcai Chen, Xin Liu, Haijun Yang, Daohe Lu, Buzhou Tang
Abstract This paper introduces the Bank Question (BQ) corpus, a Chinese corpus for sentence semantic equivalence identification (SSEI). The BQ corpus contains 120,000 question pairs from 1-year online bank custom service logs. To efficiently process and annotate questions from such a large scale of logs, this paper proposes a clustering based annotation method to achieve questions with the same intent. First, the deduplicated questions with the same answer are clustered into stacks by the Word Mover{'}s Distance (WMD) based Affinity Propagation (AP) algorithm. Then, the annotators are asked to assign the clustered questions into different intent categories. Finally, the positive and negative question pairs for SSEI are selected in the same intent category and between different intent categories respectively. We also present six SSEI benchmark performance on our corpus, including state-of-the-art algorithms. As the largest manually annotated public Chinese SSEI corpus in the bank domain, the BQ corpus is not only useful for Chinese question semantic matching research, but also a significant resource for cross-lingual and cross-domain SSEI research. The corpus is available in public.
Tasks Paraphrase Identification, Question Answering, Semantic Textual Similarity
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1536/
PDF https://www.aclweb.org/anthology/D18-1536
PWC https://paperswithcode.com/paper/the-bq-corpus-a-large-scale-domain-specific
Repo
Framework

Arguments and Adjuncts in Universal Dependencies

Title Arguments and Adjuncts in Universal Dependencies
Authors Adam Przepi{'o}rkowski, Agnieszka Patejuk
Abstract The aim of this paper is to argue for a coherent Universal Dependencies approach to the core vs. non-core distinction. We demonstrate inconsistencies in the current version 2 of UD in this respect {–} mostly resulting from the preservation of the argument{–}adjunct dichotomy despite the declared avoidance of this distinction {–} and propose a relatively conservative modification of UD that is free from these problems.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1324/
PDF https://www.aclweb.org/anthology/C18-1324
PWC https://paperswithcode.com/paper/arguments-and-adjuncts-in-universal
Repo
Framework

RECIPE: Applying Open Domain Question Answering to Privacy Policies

Title RECIPE: Applying Open Domain Question Answering to Privacy Policies
Authors Yan Shvartzshanider, Ananth Balashankar, Thomas Wies, Lakshminarayanan Subramanian
Abstract We describe our experiences in using an open domain question answering model (Chen et al., 2017) to evaluate an out-of-domain QA task of assisting in analyzing privacy policies of companies. Specifically, Relevant CI Parameters Extractor (RECIPE) seeks to answer questions posed by the theory of contextual integrity (CI) regarding the information flows described in the privacy statements. These questions have a simple syntactic structure and the answers are factoids or descriptive in nature. The model achieved an F1 score of 72.33, but we noticed that combining the results of this model with a neural dependency parser based approach yields a significantly higher F1 score of 92.35 compared to manual annotations. This indicates that future work which in-corporates signals from parsing like NLP tasks more explicitly can generalize better on out-of-domain tasks.
Tasks Open-Domain Question Answering, Question Answering, Reading Comprehension
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2608/
PDF https://www.aclweb.org/anthology/W18-2608
PWC https://paperswithcode.com/paper/recipe-applying-open-domain-question
Repo
Framework
comments powered by Disqus