October 15, 2019

2493 words 12 mins read

Paper Group NANR 95

Paper Group NANR 95

Discourse and Lexicons: Lexemes, MWEs, Grammatical Constructions and Compositional Word Combinations to Signal Discourse Relations. Jerk-Aware Video Acceleration Magnification. Efficient and Consistent Adversarial Bipartite Matching. Towards Automatic Fake News Detection: Cross-Level Stance Detection in News Articles. An Efficient Pruning Algorithm …

Discourse and Lexicons: Lexemes, MWEs, Grammatical Constructions and Compositional Word Combinations to Signal Discourse Relations

Title Discourse and Lexicons: Lexemes, MWEs, Grammatical Constructions and Compositional Word Combinations to Signal Discourse Relations
Authors Laurence Danlos
Abstract Lexicons generally record a list of lexemes or non-compositional multiword expressions. We propose to build lexicons for compositional word combinations, namely {}secondary discourse connectives{''}. Secondary discourse connectives play the same function as {}primary discourse connectives{''} but the latter are either lexemes or non-compositional multiword expressions. The paper defines primary and secondary connectives, and explains why it is possible to build a lexicon for the compositional ones and how it could be organized. It also puts forward the utility of such a lexicon in discourse annotation and parsing. Finally, it opens the discussion on the constructions that signal a discourse relation between two spans of text.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4906/
PDF https://www.aclweb.org/anthology/W18-4906
PWC https://paperswithcode.com/paper/discourse-and-lexicons-lexemes-mwes
Repo
Framework

Jerk-Aware Video Acceleration Magnification

Title Jerk-Aware Video Acceleration Magnification
Authors Shoichiro Takeda, Kazuki Okami, Dan Mikami, Megumi Isogai, Hideaki Kimata
Abstract Video magnification reveals subtle changes invisible to the naked eye, but such tiny yet meaningful changes are often hidden under large motions: small deformation of the muscles in doing sports, or tiny vibrations of strings in ukulele playing. For magnifying subtle changes under large motions, video acceleration magnification method has recently been proposed. This method magnifies subtle acceleration changes and ignores slow large motions. However, quick large motions severely distort this method. In this paper, we present a novel use of jerk to make the acceleration method robust to quick large motions. Jerk has been used to assess smoothness of time series data in the neuroscience and mechanical engineering fields. On the basis of our observation that subtle changes are smoother than quick large motions at temporal scale, we used jerk-based smoothness to design a jerk-aware filter that passes subtle changes only under quick large motions. By applying our filter to the acceleration method, we obtain impressive magnification results better than those obtained with state-of-the-art.
Tasks Time Series
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Takeda_Jerk-Aware_Video_Acceleration_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Takeda_Jerk-Aware_Video_Acceleration_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/jerk-aware-video-acceleration-magnification
Repo
Framework

Efficient and Consistent Adversarial Bipartite Matching

Title Efficient and Consistent Adversarial Bipartite Matching
Authors Rizal Fathony, Sima Behpour, Xinhua Zhang, Brian Ziebart
Abstract Many important structured prediction problems, including learning to rank items, correspondence-based natural language processing, and multi-object tracking, can be formulated as weighted bipartite matching optimizations. Existing structured prediction approaches have significant drawbacks when applied under the constraints of perfect bipartite matchings. Exponential family probabilistic models, such as the conditional random field (CRF), provide statistical consistency guarantees, but suffer computationally from the need to compute the normalization term of its distribution over matchings, which is a #P-hard matrix permanent computation. In contrast, the structured support vector machine (SSVM) provides computational efficiency, but lacks Fisher consistency, meaning that there are distributions of data for which it cannot learn the optimal matching even under ideal learning conditions (i.e., given the true distribution and selecting from all measurable potential functions). We propose adversarial bipartite matching to avoid both of these limitations. We develop this approach algorithmically, establish its computational efficiency and Fisher consistency properties, and apply it to matching problems that demonstrate its empirical benefits.
Tasks Learning-To-Rank, Multi-Object Tracking, Object Tracking, Structured Prediction
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2162
PDF http://proceedings.mlr.press/v80/fathony18a/fathony18a.pdf
PWC https://paperswithcode.com/paper/efficient-and-consistent-adversarial
Repo
Framework

Towards Automatic Fake News Detection: Cross-Level Stance Detection in News Articles

Title Towards Automatic Fake News Detection: Cross-Level Stance Detection in News Articles
Authors Costanza Conforti, Mohammad Taher Pilehvar, Nigel Collier
Abstract In this paper, we propose to adapt the four-staged pipeline proposed by Zubiaga et al. (2018) for the Rumor Verification task to the problem of Fake News Detection. We show that the recently released FNC-1 corpus covers two of its steps, namely the \textit{Tracking} and the \textit{Stance Detection} task. We identify asymmetry in length in the input to be a key characteristic of the latter step, when adapted to the framework of Fake News Detection, and propose to handle it as a specific type of \textit{Cross-Level Stance Detection}. Inspired by theories from the field of Journalism Studies, we implement and test two architectures to successfully model the internal structure of an article and its interactions with a claim.
Tasks Fake News Detection, Stance Detection
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5507/
PDF https://www.aclweb.org/anthology/W18-5507
PWC https://paperswithcode.com/paper/towards-automatic-fake-news-detection-cross
Repo
Framework

An Efficient Pruning Algorithm for Robust Isotonic Regression

Title An Efficient Pruning Algorithm for Robust Isotonic Regression
Authors Cong Han Lim
Abstract We study a generalization of the classic isotonic regression problem where we allow separable nonconvex objective functions, focusing on the case of estimators used in robust regression. A simple dynamic programming approach allows us to solve this problem to within ε-accuracy (of the global minimum) in time linear in 1/ε and the dimension. We can combine techniques from the convex case with branch-and-bound ideas to form a new algorithm for this problem that naturally exploits the shape of the objective function. Our algorithm achieves the best bounds for both the general nonconvex and convex case (linear in log (1/ε)), while performing much faster in practice than a straightforward dynamic programming approach, especially as the desired accuracy increases.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7306-an-efficient-pruning-algorithm-for-robust-isotonic-regression
PDF http://papers.nips.cc/paper/7306-an-efficient-pruning-algorithm-for-robust-isotonic-regression.pdf
PWC https://paperswithcode.com/paper/an-efficient-pruning-algorithm-for-robust
Repo
Framework

Unsupervised Semantic Abstractive Summarization

Title Unsupervised Semantic Abstractive Summarization
Authors Shibhansh Dohare, Vivek Gupta, Harish Karnick
Abstract Automatic abstractive summary generation remains a significant open problem for natural language processing. In this work, we develop a novel pipeline for Semantic Abstractive Summarization (SAS). SAS, as introduced by Liu et. al. (2015) first generates an AMR graph of an input story, through which it extracts a summary graph and finally, creates summary sentences from this summary graph. Compared to earlier approaches, we develop a more comprehensive method to generate the story AMR graph using state-of-the-art co-reference resolution and Meta Nodes. Which we then use in a novel unsupervised algorithm based on how humans summarize a piece of text to extract the summary sub-graph. Our algorithm outperforms the state of the art SAS method by 1.7{%} F1 score in node prediction.
Tasks Abstractive Text Summarization, Sentence Compression
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-3011/
PDF https://www.aclweb.org/anthology/P18-3011
PWC https://paperswithcode.com/paper/unsupervised-semantic-abstractive
Repo
Framework

ContextNet: Deep learning for Star Galaxy Classification

Title ContextNet: Deep learning for Star Galaxy Classification
Authors Noble Kennamer, David Kirkby, Alexander Ihler, Francisco Javier Sanchez-Lopez
Abstract We present a framework to compose artificial neural networks in cases where the data cannot be treated as independent events. Our particular motivation is star galaxy classification for ground based optical surveys. Due to a turbulent atmosphere and imperfect instruments, a single image of an astronomical object is not enough to definitively classify it as a star or galaxy. Instead the context of the surrounding objects imaged at the same time need to be considered in order to make an optimal classification. The model we present is divided into three distinct ANNs: one designed to capture local features about each object, the second to compare these features across all objects in an image, and the third to make a final prediction for each object based on the local and compared features. By exploiting the ability to replicate the weights of an ANN, the model can handle an arbitrary and variable number of individual objects embedded in a larger exposure. We train and test our model on simulations of a large up and coming ground based survey, the Large Synoptic Survey Telescope (LSST). We compare to the state of the art approach, showing improved overall performance as well as better performance for a specific class of objects that is important for the LSST.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2195
PDF http://proceedings.mlr.press/v80/kennamer18a/kennamer18a.pdf
PWC https://paperswithcode.com/paper/contextnet-deep-learning-for-star-galaxy
Repo
Framework

Similarity-Based Reconstruction Loss for Meaning Representation

Title Similarity-Based Reconstruction Loss for Meaning Representation
Authors Olga Kovaleva, Anna Rumshisky, Alexey Romanov
Abstract This paper addresses the problem of representation learning. Using an autoencoder framework, we propose and evaluate several loss functions that can be used as an alternative to the commonly used cross-entropy reconstruction loss. The proposed loss functions use similarities between words in the embedding space, and can be used to train any neural model for text generation. We show that the introduced loss functions amplify semantic diversity of reconstructed sentences, while preserving the original meaning of the input. We test the derived autoencoder-generated representations on paraphrase detection and language inference tasks and demonstrate performance improvement compared to the traditional cross-entropy loss.
Tasks Dialogue Generation, Machine Translation, Question Answering, Representation Learning, Sentence Embeddings, Text Generation, Transfer Learning, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1525/
PDF https://www.aclweb.org/anthology/D18-1525
PWC https://paperswithcode.com/paper/similarity-based-reconstruction-loss-for
Repo
Framework

Improved Neural Machine Translation using Side Information

Title Improved Neural Machine Translation using Side Information
Authors Cong Duy Vu Hoang, Gholamreza Haffari, Trevor Cohn
Abstract In this work, we investigate whether side information is helpful in neural machine translation (NMT). We study various kinds of side information, including topical information, personal trait, then propose different ways of incorporating them into the existing NMT models. Our experimental results show the benefits of side information in improving the NMT models.
Tasks Machine Translation
Published 2018-12-01
URL https://www.aclweb.org/anthology/U18-1001/
PDF https://www.aclweb.org/anthology/U18-1001
PWC https://paperswithcode.com/paper/improved-neural-machine-translation-using
Repo
Framework

An Exploration of Three Lightly-supervised Representation Learning Approaches for Named Entity Classification

Title An Exploration of Three Lightly-supervised Representation Learning Approaches for Named Entity Classification
Authors Ajay Nagesh, Mihai Surdeanu
Abstract Several semi-supervised representation learning methods have been proposed recently that mitigate the drawbacks of traditional bootstrapping: they reduce the amount of semantic drift introduced by iterative approaches through one-shot learning; others address the sparsity of data through the learning of custom, dense representation for the information modeled. In this work, we are the first to adapt three of these methods, most of which have been originally proposed for image processing, to an information extraction task, specifically, named entity classification. Further, we perform a rigorous comparative analysis on two distinct datasets. Our analysis yields several important observations. First, all representation learning methods outperform state-of-the-art semi-supervised methods that do not rely on representation learning. To the best of our knowledge, we report the latest state-of-the-art results on the semi-supervised named entity classification task. Second, one-shot learning methods clearly outperform iterative representation learning approaches. Lastly, one of the best performers relies on the mean teacher framework (Tarvainen and Valpola, 2017), a simple teacher/student approach that is independent of the underlying task-specific model.
Tasks One-Shot Learning, Representation Learning
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1196/
PDF https://www.aclweb.org/anthology/C18-1196
PWC https://paperswithcode.com/paper/an-exploration-of-three-lightly-supervised
Repo
Framework

CEA LIST: Processing Low-Resource Languages for CoNLL 2018

Title CEA LIST: Processing Low-Resource Languages for CoNLL 2018
Authors Elie Duthoo, Olivier Mesnard
Abstract In this paper, we describe the system used for our first participation at the CoNLL 2018 shared task. The submitted system largely reused the state of the art parser from CoNLL 2017 (\url{https://github.com/tdozat/Parser-v2}). We enhanced this system for morphological features predictions, and we used all available resources to provide accurate models for low-resource languages. We ranked 5th of 27 participants in MLAS for building morphology aware dependency trees, 2nd for morphological features only, and 3rd for tagging (UPOS) and parsing (LAS) low-resource languages.
Tasks Tokenization, Word Alignment, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-2003/
PDF https://www.aclweb.org/anthology/K18-2003
PWC https://paperswithcode.com/paper/cea-list-processing-low-resource-languages
Repo
Framework

Predicting Authorship and Author Traits from Keystroke Dynamics

Title Predicting Authorship and Author Traits from Keystroke Dynamics
Authors Barbara Plank
Abstract Written text transmits a good deal of nonverbal information related to the author{'}s identity and social factors, such as age, gender and personality. However, it is less known to what extent behavioral biometric traces transmit such information. We use typist data to study the predictiveness of authorship, and present first experiments on predicting both age and gender from keystroke dynamics. Our results show that the model based on keystroke features, while being two orders of magnitude smaller, leads to significantly higher accuracies for authorship than the text-based system. For user attribute prediction, the best approach is to combine the two, suggesting that extralinguistic factors are disclosed to a larger degree in written text, while author identity is better transmitted in typing behavior.
Tasks Machine Translation
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-1113/
PDF https://www.aclweb.org/anthology/W18-1113
PWC https://paperswithcode.com/paper/predicting-authorship-and-author-traits-from
Repo
Framework

Robustness of Classifiers to Universal Perturbations: A Geometric Perspective

Title Robustness of Classifiers to Universal Perturbations: A Geometric Perspective
Authors Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard, Stefano Soatto
Abstract Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers. In this paper, we provide a quantitative analysis of the robustness of classifiers to universal perturbations, and draw a formal link between the robustness to universal perturbations, and the geometry of the decision boundary. Specifically, we establish theoretical bounds on the robustness of classifiers under two decision boundary models (flat and curved models). We show in particular that the robustness of deep networks to universal perturbations is driven by a key property of their curvature: there exist shared directions along which the decision boundary of deep networks is systematically positively curved. Under such conditions, we prove the existence of small universal perturbations. Our analysis further provides a novel geometric method for computing universal perturbations, in addition to explaining their properties.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=ByrZyglCb
PDF https://openreview.net/pdf?id=ByrZyglCb
PWC https://paperswithcode.com/paper/robustness-of-classifiers-to-universal
Repo
Framework

Using Adversarial Examples in Natural Language Processing

Title Using Adversarial Examples in Natural Language Processing
Authors Petr B{\v{e}}lohl{'a}vek, Ond{\v{r}}ej Pl{'a}tek, Zden{\v{e}}k {\v{Z}}abokrtsk{'y}, Milan Straka
Abstract
Tasks Image Classification
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1584/
PDF https://www.aclweb.org/anthology/L18-1584
PWC https://paperswithcode.com/paper/using-adversarial-examples-in-natural
Repo
Framework

A Full End-to-End Semantic Role Labeler, Syntactic-agnostic Over Syntactic-aware?

Title A Full End-to-End Semantic Role Labeler, Syntactic-agnostic Over Syntactic-aware?
Authors Jiaxun Cai, Shexia He, Zuchao Li, Hai Zhao
Abstract Semantic role labeling (SRL) is to recognize the predicate-argument structure of a sentence, including subtasks of predicate disambiguation and argument labeling. Previous studies usually formulate the entire SRL problem into two or more subtasks. For the first time, this paper introduces an end-to-end neural model which unifiedly tackles the predicate disambiguation and the argument labeling in one shot. Using a biaffine scorer, our model directly predicts all semantic role labels for all given word pairs in the sentence without relying on any syntactic parse information. Specifically, we augment the BiLSTM encoder with a non-linear transformation to further distinguish the predicate and the argument in a given sentence, and model the semantic role labeling process as a word pair classification task by employing the biaffine attentional mechanism. Though the proposed model is syntax-agnostic with local decoder, it outperforms the state-of-the-art syntax-aware SRL systems on the CoNLL-2008, 2009 benchmarks for both English and Chinese. To our best knowledge, we report the first syntax-agnostic SRL model that surpasses all known syntax-aware models.
Tasks Machine Translation, Question Answering, Semantic Parsing, Semantic Role Labeling
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1233/
PDF https://www.aclweb.org/anthology/C18-1233
PWC https://paperswithcode.com/paper/a-full-end-to-end-semantic-role-labeler
Repo
Framework
comments powered by Disqus