October 16, 2019

2799 words 14 mins read

Paper Group NAWR 8

Paper Group NAWR 8

Automatic support vector data description. Triplet Loss in Siamese Network for Object Tracking. A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss. Using J-K-fold Cross Validation To Reduce Variance When Tuning NLP Models. Zero-Shot Learning Based Approach For Medieval Word Recognition Using Deep-Learned Features. …

Automatic support vector data description

Title Automatic support vector data description
Authors Reza Sadeghi, Javad Hamidzadeh
Abstract Event handlers have wide range of applications such as medical assistant systems and fire suppression systems. These systems try to provide accurate responses based on the least information. Support vector data description (SVDD) is one of the appropriate tools for such detections, which should handle lack of information. Therefore, many efforts have been done to improve SVDD. Unfortunately, the existing descriptors suffer from weak data characteristic in sparse data sets and their tuning parameters are organized improperly. These issues cause reduction of accuracy in event handlers when they are faced with data shortage. Therefore, we propose automatic support vector data description (ASVDD) based on both validation degree, which is originated from fuzzy rough set to discover data characteristic, and assigning effective values for tuning parameters by chaotic bat algorithm. To evaluate the performance of ASVDD, several experiments have been conducted on various data sets of UCI repository. The experimental results demonstrate superiority of the proposed method over state-of-the-art ones in terms of classification accuracy and AUC. In order to prove meaningful distinction between the accuracy results of the proposed method and the leading-edge ones, the Wilcoxon statistical test has been conducted.
Tasks One-class classifier, Outlier Detection
Published 2018-01-01
URL https://link.springer.com/article/10.1007/s00500-016-2317-5
PDF https://www.researchgate.net/publication/306312292_Automatic_support_vector_data_description
PWC https://paperswithcode.com/paper/automatic-support-vector-data-description
Repo https://github.com/RezaSadeghiWSU/ASVDD
Framework none

Triplet Loss in Siamese Network for Object Tracking

Title Triplet Loss in Siamese Network for Object Tracking
Authors Xingping Dong, Jianbing Shen
Abstract Object tracking is still a critical and challenging problem with many applications in computer vision. For this challenge, more and more researchers pay attention to applying deep learning to get powerful feature for better tracking accuracy. In this paper, a novel triplet loss is proposed to extract expressive deep feature for object tracking by adding it into Siamese network framework instead of pairwise loss for training. Without adding any inputs, our approach is able to utilize more elements for training to achieve more powerful feature via the combination of original samples. Furthermore, we propose a theoretical analysis by combining comparison of gradients and back-propagation, to prove the effectiveness of our method. In experiments, we apply the proposed triplet loss for three real-time trackers based on Siamese network. And the results on several popular tracking benchmarks show our variants operate at almost the same frame-rate with baseline trackers and achieve superior tracking performance than them, as well as the comparable accuracy with recent state-of-the-art real-time trackers.
Tasks Object Tracking
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Xingping_Dong_Triplet_Loss_with_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Xingping_Dong_Triplet_Loss_with_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/triplet-loss-in-siamese-network-for-object
Repo https://github.com/shenjianbing/TripletTracking
Framework none

A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss

Title A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
Authors Wan-TingHsu1, Chieh-KaiLin1, Ming-YingLee1, KeruiMin2, JingTang2, MinSun1 1 National Tsing Hua University, 2 Cheetah Mobile
Abstract We propose a unified model combining the strength of extractive and abstractive summarization. On the one hand, a simple extractive model can obtain sentence-level attention with high ROUGE scores but less readable. On the other hand, a more complicated abstractive model can obtain word-level dynamic attention to generate a more readable paragraph. In our model, sentence-level attention is used to modulate the word-level attention such that words in less attended sentences are less likely to be generated. Moreover, a novel inconsistency loss function is introduced to penalize the inconsistency between two levels of attentions. By end-to-end training our model with the inconsistency loss and original losses of extractive and abstractive models, we achieve state-of-theart ROUGE scores while being the most informative and readable summarization on the CNN/Daily Mail dataset in a solid human evaluation.
Tasks Abstractive Text Summarization
Published 2018-07-05
URL https://arxiv.org/pdf/1805.06266.pdf
PDF https://arxiv.org/pdf/1805.06266.pdf
PWC https://paperswithcode.com/paper/a-unified-model-for-extractive-and-2
Repo https://github.com/HsuWanTing/unified-summarization
Framework tf

Using J-K-fold Cross Validation To Reduce Variance When Tuning NLP Models

Title Using J-K-fold Cross Validation To Reduce Variance When Tuning NLP Models
Authors Henry Moss, David Leslie, Paul Rayson
Abstract K-fold cross validation (CV) is a popular method for estimating the true performance of machine learning models, allowing model selection and parameter tuning. However, the very process of CV requires random partitioning of the data and so our performance estimates are in fact stochastic, with variability that can be substantial for natural language processing tasks. We demonstrate that these unstable estimates cannot be relied upon for effective parameter tuning. The resulting tuned parameters are highly sensitive to how our data is partitioned, meaning that we often select sub-optimal parameter choices and have serious reproducibility issues. Instead, we propose to use the less variable J-K-fold CV, in which J independent K-fold cross validations are used to assess performance. Our main contributions are extending J-K-fold CV from performance estimation to parameter tuning and investigating how to choose J and K. We argue that variability is more important than bias for effective tuning and so advocate lower choices of K than are typically seen in the NLP literature and instead use the saved computation to increase J. To demonstrate the generality of our recommendations we investigate a wide range of case-studies: sentiment classification (both general and target-specific), part-of-speech tagging and document classification.
Tasks Document Classification, Model Selection, Part-Of-Speech Tagging, Sentiment Analysis
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1252/
PDF https://www.aclweb.org/anthology/C18-1252
PWC https://paperswithcode.com/paper/using-j-k-fold-cross-validation-to-reduce-1
Repo https://github.com/henrymoss/COLING2018
Framework none

Zero-Shot Learning Based Approach For Medieval Word Recognition Using Deep-Learned Features

Title Zero-Shot Learning Based Approach For Medieval Word Recognition Using Deep-Learned Features
Authors Sukalpa Chanda, Jochem Baas, Daniël Haitink, Sebastien Hamely, Dominique Stutzmanny, Lambert Schomaker
Abstract Historical manuscripts reflect our past. Recently digitization of large quantities of historical handwritten docu- ments is taking place in every corner of the world, and are being archived. From those digital repositories, automatic text indexing and retrieval system fetch only those documents to an end user that they are interested in. A regular OCR technology is not capable of rendering this service to an end user in a reliable manner. Instead, a word recognition/spotting algorithm performs the task. Word recognition based systems require enough labelled data per class to train the system. Moreover, all word classes need to be taught beforehand. Though word spotting could evade this drawback of prior training, these systems often need to have additional overheads like a language model to deal with “out of lexicon” words. Zero-shot learning could be a possible alternative to counter such situation. A Zero-shot learning algorithm is capable of handling unseen classes, provided the algorithm has been fortified with rich discriminating features and reliable “attribute description” per class during training. Since deeply learned features have enough discriminating power, a deep learning framework has been used here for feature extraction purpose. To the best of our knowledge, this is probably the first work on “out of lexicon” medieval word recognition using a Zero-Shot Learning framework. We obtained very encouraging results(accuracy ≈57% for “out of lexicon” classes) while dealing with 166 training classes and 50 unseen test classes.
Tasks Language Modelling, Optical Character Recognition, Zero-Shot Learning
Published 2018-10-01
URL https://www.researchgate.net/publication/328630035_Zero-Shot_Learning_Based_Approach_For_Medieval_Word_Recognition_Using_Deep-Learned_Features
PDF https://www.researchgate.net/publication/328630035_Zero-Shot_Learning_Based_Approach_For_Medieval_Word_Recognition_Using_Deep-Learned_Features
PWC https://paperswithcode.com/paper/zero-shot-learning-based-approach-for
Repo https://github.com/Zero-Shot/Zero-Shot-Learning
Framework none

Diacritics Restoration Using Neural Networks

Title Diacritics Restoration Using Neural Networks
Authors Jakub N{'a}plava, Milan Straka, Pavel Stra{\v{n}}{'a}k, Jan Haji{\v{c}}
Abstract
Tasks Language Modelling
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1247/
PDF https://www.aclweb.org/anthology/L18-1247
PWC https://paperswithcode.com/paper/diacritics-restoration-using-neural-networks
Repo https://github.com/arahusky/diacritics_restoration
Framework tf

ArguminSci: A Tool for Analyzing Argumentation and Rhetorical Aspects in Scientific Writing

Title ArguminSci: A Tool for Analyzing Argumentation and Rhetorical Aspects in Scientific Writing
Authors Anne Lauscher, Goran Glava{\v{s}}, Kai Eckert
Abstract Argumentation is arguably one of the central features of scientific language. We present \textit{ArguminSci}, an easy-to-use tool that analyzes argumentation and other rhetorical aspects of scientific writing, which we collectively dub \textit{scitorics}. The main aspect we focus on is the fine-grained argumentative analysis of scientific text through identification of argument components. The functionality of \textit{ArguminSci} is accessible via three interfaces: as a command line tool, via a RESTful application programming interface, and as a web application.
Tasks Argument Mining
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5203/
PDF https://www.aclweb.org/anthology/W18-5203
PWC https://paperswithcode.com/paper/arguminsci-a-tool-for-analyzing-argumentation
Repo https://github.com/anlausch/ArguminSci
Framework none

Author Profiling for Abuse Detection

Title Author Profiling for Abuse Detection
Authors Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis, Ekaterina Shutova
Abstract The rapid growth of social media in recent years has fed into some highly undesirable phenomena such as proliferation of hateful and offensive language on the Internet. Previous research suggests that such abusive content tends to come from users who share a set of common stereotypes and form communities around them. The current state-of-the-art approaches to abuse detection are oblivious to user and community information and rely entirely on textual (i.e., lexical and semantic) cues. In this paper, we propose a novel approach to this problem that incorporates community-based profiling features of Twitter users. Experimenting with a dataset of 16k tweets, we show that our methods significantly outperform the current state of the art in abuse detection. Further, we conduct a qualitative analysis of model characteristics. We release our code, pre-trained models and all the resources used in the public domain.
Tasks Abuse Detection
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1093/
PDF https://www.aclweb.org/anthology/C18-1093
PWC https://paperswithcode.com/paper/author-profiling-for-abuse-detection
Repo https://github.com/pushkarmishra/AuthorProfilingAbuseDetection
Framework none

An Encoder-Decoder Approach to the Paradigm Cell Filling Problem

Title An Encoder-Decoder Approach to the Paradigm Cell Filling Problem
Authors Miikka Silfverberg, Mans Hulden
Abstract The Paradigm Cell Filling Problem in morphology asks to complete word inflection tables from partial ones. We implement novel neural models for this task, evaluating them on 18 data sets in 8 languages, showing performance that is comparable with previous work with far less training data. We also publish a new dataset for this task and code implementing the system described in this paper.
Tasks Denoising, Language Acquisition, Morphological Inflection
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1315/
PDF https://www.aclweb.org/anthology/D18-1315
PWC https://paperswithcode.com/paper/an-encoder-decoder-approach-to-the-paradigm
Repo https://github.com/mpsilfve/pcfp-data
Framework none

A Convolutional Neural Network Smartphone App for Real-Time Voice Activity Detection

Title A Convolutional Neural Network Smartphone App for Real-Time Voice Activity Detection
Authors Abhishek Sehgal, Nasser Kehtarnavaz
Abstract This paper presents a smartphone app that performs real-time voice activity detection based on convolutional neural network. Real-time implementation issues are discussed showing how the slow inference time associated with convolutional neural networks is addressed. The developed smartphone app is meant to act as a switch for noise reduction in the signal processing pipelines of hearing devices, enabling noise estimation or classification to be conducted in noise-only parts of noisy speech signals. The developed smartphone app is compared with a previously developed voice activity detection app as well as with two highly cited voice activity detection algorithms. The experimental results indicate that the developed app using convolutional neural network outperforms the previously developed smartphone app.
Tasks Action Detection, Activity Detection
Published 2018-02-01
URL https://ieeexplore.ieee.org/abstract/document/8278160
PDF https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8278160
PWC https://paperswithcode.com/paper/a-convolutional-neural-network-smartphone-app
Repo https://github.com/SIP-Lab/CNN-VAD
Framework none

Deep, complex, invertible networks for inversion of transmission effects in multimode optical fibres

Title Deep, complex, invertible networks for inversion of transmission effects in multimode optical fibres
Authors Oisín Moran, Piergiorgio Caramazza, Daniele Faccio, Roderick Murray-Smith
Abstract We use complex-weighted, deep networks to invert the effects of multimode optical fibre distortion of a coherent input image. We generated experimental data based on collections of optical fibre responses to greyscale input images generated with coherent light, by measuring only image amplitude (not amplitude and phase as is typical) at the output of \SI{1}{\metre} and \SI{10}{\metre} long, \SI{105}{\micro\metre} diameter multimode fibre. This data is made available as the {\it Optical fibre inverse problem} Benchmark collection. The experimental data is used to train complex-weighted models with a range of regularisation approaches. A {\it unitary regularisation} approach for complex-weighted networks is proposed which performs well in robustly inverting the fibre transmission matrix, which fits well with the physical theory. A key benefit of the unitary constraint is that it allows us to learn a forward unitary model and analytically invert it to solve the inverse problem. We demonstrate this approach, and show how it can improve performance by incorporating knowledge of the phase shift induced by the spatial light modulator.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7589-deep-complex-invertible-networks-for-inversion-of-transmission-effects-in-multimode-optical-fibres
PDF http://papers.nips.cc/paper/7589-deep-complex-invertible-networks-for-inversion-of-transmission-effects-in-multimode-optical-fibres.pdf
PWC https://paperswithcode.com/paper/deep-complex-invertible-networks-for
Repo https://github.com/rodms/opticalfibreml
Framework tf

Fast Light Field Reconstruction With Deep Coarse-To-Fine Modeling of Spatial-Angular Clues

Title Fast Light Field Reconstruction With Deep Coarse-To-Fine Modeling of Spatial-Angular Clues
Authors Henry Wing Fung Yeung, Junhui Hou, Jie Chen, Yuk Ying Chung, Xiaoming Chen
Abstract Densely-sampled light fields (LFs) are beneficial to many applications such as depth inference and post-capture refocusing. However, it is costly and challenging to capture them. In this paper, we propose a learning based algorithm to reconstruct a densely-sampled LF fast and accurately from a sparsely-sampled LF in one forward pass. Our method uses computationally efficient convolutions to deeply characterize the high dimensional spatial-angular clues in a coarse-tofine manner. Specifically, our end-to-end model first synthesizes a set of intermediate novel sub-aperture images (SAIs) by exploring the coarse characteristics of the sparsely-sampled LF input with spatial-angular alternating convolutions. Then, the synthesized intermediate novel SAIs are efficiently refined by further recovering the fine relations from all SAIs via guided residual learning and stride-2 4-D convolutions. Experimental results on extensive real-world and synthetic LF images show that our model can provide more than 3 dB advantage in reconstruction quality in average than the state-of-the-art methods while being computationally faster by a factor of 30. Besides, more accurate depth can be inferred from the reconstructed densely-sampled LFs by our method.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Henry_W._F._Yeung_Fast_Light_Field_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Henry_W._F._Yeung_Fast_Light_Field_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/fast-light-field-reconstruction-with-deep
Repo https://github.com/angularsr/LightFieldAngularSR
Framework pytorch

How Gender and Skin Tone Modifiers Affect Emoji Semantics in Twitter

Title How Gender and Skin Tone Modifiers Affect Emoji Semantics in Twitter
Authors Francesco Barbieri, Jose Camacho-Collados
Abstract In this paper we analyze the use of emojis in social media with respect to gender and skin tone. By gathering a dataset of over twenty two million tweets from United States some findings are clearly highlighted after performing a simple frequency-based analysis. Moreover, we carry out a semantic analysis on the usage of emojis and their modifiers (e.g. gender and skin tone) by embedding all words, emojis and modifiers into the same vector space. Our analyses reveal that some stereotypes related to the skin color and gender seem to be reflected on the use of these modifiers. For example, emojis representing hand gestures are more widely utilized with lighter skin tones, and the usage across skin tones differs significantly. At the same time, the vector corresponding to the male modifier tends to be semantically close to emojis related to business or technology, whereas their female counterparts appear closer to emojis about love or makeup.
Tasks Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-2011/
PDF https://www.aclweb.org/anthology/S18-2011
PWC https://paperswithcode.com/paper/how-gender-and-skin-tone-modifiers-affect
Repo https://github.com/fvancesco/emoji_modifiers
Framework none

Agree or Disagree: Predicting Judgments on Nuanced Assertions

Title Agree or Disagree: Predicting Judgments on Nuanced Assertions
Authors Michael Wojatzki, Torsten Zesch, Saif Mohammad, Svetlana Kiritchenko
Abstract Being able to predict whether people agree or disagree with an assertion (i.e. an explicit, self-contained statement) has several applications ranging from predicting how many people will like or dislike a social media post to classifying posts based on whether they are in accordance with a particular point of view. We formalize this as two NLP tasks: predicting judgments of (i) individuals and (ii) groups based on the text of the assertion and previous judgments. We evaluate a wide range of approaches on a crowdsourced data set containing over 100,000 judgments on over 2,000 assertions. We find that predicting individual judgments is a hard task with our best results only slightly exceeding a majority baseline, but that judgments of groups can be more reliably predicted using a Siamese neural network, which outperforms all other approaches by a wide margin.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-2026/
PDF https://www.aclweb.org/anthology/S18-2026
PWC https://paperswithcode.com/paper/agree-or-disagree-predicting-judgments-on
Repo https://github.com/muchafel/judgmentPrediction
Framework tf

PICO Element Detection in Medical Text via Long Short-Term Memory Neural Networks

Title PICO Element Detection in Medical Text via Long Short-Term Memory Neural Networks
Authors Di Jin, Peter Szolovits
Abstract Successful evidence-based medicine (EBM) applications rely on answering clinical questions by analyzing large medical literature databases. In order to formulate a well-defined, focused clinical question, a framework called PICO is widely used, which identifies the sentences in a given medical text that belong to the four components: Participants/Problem (P), Intervention (I), Comparison (C) and Outcome (O). In this work, we present a Long Short-Term Memory (LSTM) neural network based model to automatically detect PICO elements. By jointly classifying subsequent sentences in the given text, we achieve state-of-the-art results on PICO element classification compared to several strong baseline models. We also make our curated data public as a benchmarking dataset so that the community can benefit from it.
Tasks Decision Making
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2308/
PDF https://www.aclweb.org/anthology/W18-2308
PWC https://paperswithcode.com/paper/pico-element-detection-in-medical-text-via
Repo https://github.com/jind11/LSTM-PICO-Detection
Framework tf
comments powered by Disqus