October 16, 2019

3040 words 15 mins read

Paper Group ANR 1144

Simple and Effective Text Simplification Using Semantic and Neural Methods. Sem-GAN: Semantically-Consistent Image-to-Image Translation. A Comprehensive Survey of Ontology Summarization: Measures and Methods. What If We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals i …

Simple and Effective Text Simplification Using Semantic and Neural Methods


Title	Simple and Effective Text Simplification Using Semantic and Neural Methods
Authors	Elior Sulem, Omri Abend, Ari Rappoport
Abstract	Sentence splitting is a major simplification operator. Here we present a simple and efficient splitting algorithm based on an automatic semantic parser. After splitting, the text is amenable for further fine-tuned simplification operations. In particular, we show that neural Machine Translation can be effectively used in this situation. Previous application of Machine Translation for simplification suffers from a considerable disadvantage in that they are over-conservative, often failing to modify the source in any way. Splitting based on semantic parsing, as proposed here, alleviates this issue. Extensive automatic and human evaluation shows that the proposed method compares favorably to the state-of-the-art in combined lexical and structural simplification.
Tasks	Machine Translation, Semantic Parsing, Text Simplification
Published	2018-10-11
URL	http://arxiv.org/abs/1810.05104v1
PDF	http://arxiv.org/pdf/1810.05104v1.pdf
PWC	https://paperswithcode.com/paper/simple-and-effective-text-simplification
Repo
Framework

Sem-GAN: Semantically-Consistent Image-to-Image Translation


Title	Sem-GAN: Semantically-Consistent Image-to-Image Translation
Authors	Anoop Cherian, Alan Sullivan
Abstract	Unpaired image-to-image translation is the problem of mapping an image in the source domain to one in the target domain, without requiring corresponding image pairs. To ensure the translated images are realistically plausible, recent works, such as Cycle-GAN, demands this mapping to be invertible. While, this requirement demonstrates promising results when the domains are unimodal, its performance is unpredictable in a multi-modal scenario such as in an image segmentation task. This is because, invertibility does not necessarily enforce semantic correctness. To this end, we present a semantically-consistent GAN framework, dubbed Sem-GAN, in which the semantics are defined by the class identities of image segments in the source domain as produced by a semantic segmentation algorithm. Our proposed framework includes consistency constraints on the translation task that, together with the GAN loss and the cycle-constraints, enforces that the images when translated will inherit the appearances of the target domain, while (approximately) maintaining their identities from the source domain. We present experiments on several image-to-image translation tasks and demonstrate that Sem-GAN improves the quality of the translated images significantly, sometimes by more than 20% on the FCN score. Further, we show that semantic segmentation models, trained with synthetic images translated via Sem-GAN, leads to significantly better segmentation results than other variants.
Tasks	Image-to-Image Translation, Semantic Segmentation
Published	2018-07-12
URL	http://arxiv.org/abs/1807.04409v1
PDF	http://arxiv.org/pdf/1807.04409v1.pdf
PWC	https://paperswithcode.com/paper/sem-gan-semantically-consistent-image-to
Repo
Framework

A Comprehensive Survey of Ontology Summarization: Measures and Methods


Title	A Comprehensive Survey of Ontology Summarization: Measures and Methods
Authors	Seyedamin Pouriyeh, Mehdi Allahyari, Krys Kochut, Hamid Reza Arabnia
Abstract	The Semantic Web is becoming a large scale framework that enables data to be published, shared, and reused in the form of ontologies. The ontology which is considered as basic building block of semantic web consists of two layers including data and schema layer. With the current exponential development of ontologies in both data size and complexity of schemas, ontology understanding which is playing an important role in different tasks such as ontology engineering, ontology learning, etc., is becoming more difficult. Ontology summarization as a way to distill knowledge from an ontology and generate an abridge version to facilitate a better understanding is getting more attention recently. There are various approaches available for ontology summarization which are focusing on different measures in order to produce a proper summary for a given ontology. In this paper, we mainly focus on the common metrics which are using for ontology summarization and meet the state-of-the-art in ontology summarization.
Tasks
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01937v1
PDF	http://arxiv.org/pdf/1801.01937v1.pdf
PWC	https://paperswithcode.com/paper/a-comprehensive-survey-of-ontology
Repo
Framework

What If We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Tasks


Title	What If We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Tasks
Authors	Haohan Wang, Da Sun, Eric P. Xing
Abstract	Nature language inference (NLI) task is a predictive task of determining the inference relationship of a pair of natural language sentences. With the increasing popularity of NLI, many state-of-the-art predictive models have been proposed with impressive performances. However, several works have noticed the statistical irregularities in the collected NLI data set that may result in an over-estimated performance of these models and proposed remedies. In this paper, we further investigate the statistical irregularities, what we refer as confounding factors, of the NLI data sets. With the belief that some NLI labels should preserve under swapping operations, we propose a simple yet effective way (swapping the two text fragments) of evaluating the NLI predictive models that naturally mitigate the observed problems. Further, we continue to train the predictive models with our swapping manner and propose to use the deviation of the model’s evaluation performances under different percentages of training text fragments to be swapped to describe the robustness of a predictive model. Our evaluation metrics leads to some interesting understandings of recent published NLI methods. Finally, we also apply the swapping operation on NLI models to see the effectiveness of this straightforward method in mitigating the confounding factor problems in training generic sentence embeddings for other NLP transfer tasks.
Tasks	Sentence Embeddings
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02719v2
PDF	http://arxiv.org/pdf/1809.02719v2.pdf
PWC	https://paperswithcode.com/paper/what-if-we-simply-swap-the-two-text-fragments
Repo
Framework

An ASP Methodology for Understanding Narratives about Stereotypical Activities


Title	An ASP Methodology for Understanding Narratives about Stereotypical Activities
Authors	Daniela Inclezan, Qinglin Zhang, Marcello Balduccini, Ankush Israney
Abstract	We describe an application of Answer Set Programming to the understanding of narratives about stereotypical activities, demonstrated via question answering. Substantial work in this direction was done by Erik Mueller, who modeled stereotypical activities as scripts. His systems were able to understand a good number of narratives, but could not process texts describing exceptional scenarios. We propose addressing this problem by using a theory of intentions developed by Blount, Gelfond, and Balduccini. We present a methodology in which we substitute scripts by activities (i.e., hierarchical plans associated with goals) and employ the concept of an intentional agent to reason about both normal and exceptional scenarios. We exemplify the application of this methodology by answering questions about a number of restaurant stories. This paper is under consideration for acceptance in TPLP.
Tasks	Question Answering
Published	2018-04-26
URL	http://arxiv.org/abs/1804.09855v1
PDF	http://arxiv.org/pdf/1804.09855v1.pdf
PWC	https://paperswithcode.com/paper/an-asp-methodology-for-understanding
Repo
Framework

Interpretable Matrix Completion: A Discrete Optimization Approach


Title	Interpretable Matrix Completion: A Discrete Optimization Approach
Authors	Dimitris Bertsimas, Michael Lingzhi Li
Abstract	We consider the problem of matrix completion on an $n \times m$ matrix. We introduce the problem of Interpretable Matrix Completion that aims to provide meaningful insights for the low-rank matrix using side information. We show that the problem can be reformulated as a binary convex optimization problem. We design OptComplete, based on a novel concept of stochastic cutting planes to enable efficient scaling of the algorithm up to matrices of sizes $n=10^6$ and $m=10^6$. We report experiments on both synthetic and real-world datasets that show that OptComplete has favorable scaling behavior and accuracy when compared with state-of-the-art methods for other types of matrix completion, while providing insight on the factors that affect the matrix.
Tasks	Matrix Completion
Published	2018-12-17
URL	https://arxiv.org/abs/1812.06647v3
PDF	https://arxiv.org/pdf/1812.06647v3.pdf
PWC	https://paperswithcode.com/paper/interpretable-matrix-completion-a-discrete
Repo
Framework

Effect Handling for Composable Program Transformations in Edward2


Title	Effect Handling for Composable Program Transformations in Edward2
Authors	Dave Moore, Maria I. Gorinova
Abstract	Algebraic effects and handlers have emerged in the programming languages community as a convenient, modular abstraction for controlling computational effects. They have found several applications including concurrent programming, meta programming, and more recently, probabilistic programming, as part of Pyro’s Poutines library. We investigate the use of effect handlers as a lightweight abstraction for implementing probabilistic programming languages (PPLs). We interpret the existing design of Edward2 as an accidental implementation of an effect-handling mechanism, and extend that design to support nested, composable transformations. We demonstrate that this enables straightforward implementation of sophisticated model transformations and inference algorithms.
Tasks	Probabilistic Programming
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06150v1
PDF	http://arxiv.org/pdf/1811.06150v1.pdf
PWC	https://paperswithcode.com/paper/effect-handling-for-composable-program
Repo
Framework

Deep Face Image Retrieval: a Comparative Study with Dictionary Learning


Title	Deep Face Image Retrieval: a Comparative Study with Dictionary Learning
Authors	Ahmad S. Tarawneh, Ahmad B. A. Hassanat, Ceyhun Celik, Dmitry Chetverikov, M. Sohel Rahman, Chaman Verma
Abstract	Facial image retrieval is a challenging task since faces have many similar features (areas), which makes it difficult for the retrieval systems to distinguish faces of different people. With the advent of deep learning, deep networks are often applied to extract powerful features that are used in many areas of computer vision. This paper investigates the application of different deep learning models for face image retrieval, namely, Alexlayer6, Alexlayer7, VGG16layer6, VGG16layer7, VGG19layer6, and VGG19layer7, with two types of dictionary learning techniques, namely $K$-means and $K$-SVD. We also investigate some coefficient learning techniques such as the Homotopy, Lasso, Elastic Net and SSF and their effect on the face retrieval system. The comparative results of the experiments conducted on three standard face image datasets show that the best performers for face image retrieval are Alexlayer7 with $K$-means and SSF, Alexlayer6 with $K$-SVD and SSF, and Alexlayer6 with $K$-means and SSF. The APR and ARR of these methods were further compared to some of the state of the art methods based on local descriptors. The experimental results show that deep learning outperforms most of those methods and therefore can be recommended for use in practice of face image retrieval
Tasks	Dictionary Learning, Face Image Retrieval, Image Retrieval
Published	2018-12-13
URL	http://arxiv.org/abs/1812.05490v1
PDF	http://arxiv.org/pdf/1812.05490v1.pdf
PWC	https://paperswithcode.com/paper/deep-face-image-retrieval-a-comparative-study
Repo
Framework

Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions


Title	Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions
Authors	Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, Kentaro Inui
Abstract	In this paper, we propose a new kernel-based co-occurrence measure that can be applied to sparse linguistic expressions (e.g., sentences) with a very short learning time, as an alternative to pointwise mutual information (PMI). As well as deriving PMI from mutual information, we derive this new measure from the Hilbert–Schmidt independence criterion (HSIC); thus, we call the new measure the pointwise HSIC (PHSIC). PHSIC can be interpreted as a smoothed variant of PMI that allows various similarity metrics (e.g., sentence embeddings) to be plugged in as kernels. Moreover, PHSIC can be estimated by simple and fast (linear in the size of the data) matrix calculations regardless of whether we use linear or nonlinear kernels. Empirically, in a dialogue response selection task, PHSIC is learned thousands of times faster than an RNN-based PMI while outperforming PMI in accuracy. In addition, we also demonstrate that PHSIC is beneficial as a criterion of a data selection task for machine translation owing to its ability to give high (low) scores to a consistent (inconsistent) pair with other pairs.
Tasks	Machine Translation, Sentence Embeddings
Published	2018-09-04
URL	http://arxiv.org/abs/1809.00800v1
PDF	http://arxiv.org/pdf/1809.00800v1.pdf
PWC	https://paperswithcode.com/paper/pointwise-hsic-a-linear-time-kernelized-co
Repo
Framework

Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy


Title	Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy
Authors	Lina Rojas-Barahona, Bo-Hsiang Tseng, Yinpei Dai, Clare Mansfield, Osman Ramadan, Stefan Ultes, Michael Crawford, Milica Gasic
Abstract	In recent years, we have seen deep learning and distributed representations of words and sentences make impact on a number of natural language processing tasks, such as similarity, entailment and sentiment analysis. Here we introduce a new task: understanding of mental health concepts derived from Cognitive Behavioural Therapy (CBT). We define a mental health ontology based on the CBT principles, annotate a large corpus where this phenomena is exhibited and perform understanding using deep learning and distributed representations. Our results show that the performance of deep learning models combined with word embeddings or sentence embeddings significantly outperform non-deep-learning models in this difficult task. This understanding module will be an essential component of a statistical dialogue system delivering therapy.
Tasks	Sentence Embeddings, Sentiment Analysis, Word Embeddings
Published	2018-09-03
URL	http://arxiv.org/abs/1809.00640v1
PDF	http://arxiv.org/pdf/1809.00640v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-language-understanding-of
Repo
Framework

Causal Discovery by Telling Apart Parents and Children


Title	Causal Discovery by Telling Apart Parents and Children
Authors	Alexander Marx, Jilles Vreeken
Abstract	We consider the problem of inferring the directed, causal graph from observational data, assuming no hidden confounders. We take an information theoretic approach, and make three main contributions. First, we show how through algorithmic information theory we can obtain SCI, a highly robust, effective and computationally efficient test for conditional independence—and show it outperforms the state of the art when applied in constraint-based inference methods such as stable PC. Second, building upon on SCI, we show how to tell apart the parents and children of a given node based on the algorithmic Markov condition. We give the Climb algorithm to efficiently discover the directed, causal Markov blanket—and show it is at least as accurate as inferring the global network, while being much more efficient. Last, but not least, we detail how we can use the Climb score to direct those edges that state of the art causal discovery algorithms based on PC or GES leave undirected—and show this improves their precision, recall and F1 scores by up to 20%.
Tasks	Causal Discovery
Published	2018-08-20
URL	http://arxiv.org/abs/1808.06356v2
PDF	http://arxiv.org/pdf/1808.06356v2.pdf
PWC	https://paperswithcode.com/paper/causal-discovery-by-telling-apart-parents-and
Repo
Framework

G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification


Title	G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification
Authors	Bingzhe Wu, Xiaolu Zhang, Shiwan Zhao, Lingxi Xie, Caihong Zeng, Zhihong Liu, Guangyu Sun
Abstract	Pathological glomerulus classification plays a key role in the diagnosis of nephropathy. As the difference between different subcategories is subtle, doctors often refer to slides from different staining methods to make decisions. However, creating correspondence across various stains is labor-intensive, bringing major difficulties in collecting data and training a vision-based algorithm to assist nephropathy diagnosis. This paper provides an alternative solution for integrating multi-stained visual cues for glomerulus classification. Our approach, named generator-to-classifier (G2C), is a two-stage framework. Given an input image from a specified stain, several generators are first applied to estimate its appearances in other staining methods, and a classifier follows to combine visual cues from different stains for prediction (whether it is pathological, or which type of pathology it has). We optimize these two stages in a joint manner. To provide a reasonable initialization, we pre-train the generators in an unlabeled reference set under an unpaired image-to-image translation task, and then fine-tune them together with the classifier. We conduct experiments on a glomerulus type classification dataset collected by ourselves (there are no publicly available datasets for this purpose). Although joint optimization slightly harms the authenticity of the generated patches, it boosts classification performance, suggesting more effective visual cues are extracted in an automatic way. We also transfer our model to a public dataset for breast cancer classification, and outperform the state-of-the-arts significantly.
Tasks	Decision Making, Image-to-Image Translation
Published	2018-06-30
URL	http://arxiv.org/abs/1807.03136v3
PDF	http://arxiv.org/pdf/1807.03136v3.pdf
PWC	https://paperswithcode.com/paper/g2c-a-generator-to-classifier-framework
Repo
Framework

A notion of stability for k-means clustering


Title	A notion of stability for k-means clustering
Authors	Thibaut Le Gouic, Quentin Paris
Abstract	In this paper, we define and study a new notion of stability for the $k$-means clustering scheme building upon the notion of quantization of a probability measure. We connect this notion of stability to a geometric feature of the underlying distribution of the data, named absolute margin condition, inspired by recent works on the subject.
Tasks	Quantization
Published	2018-01-29
URL	http://arxiv.org/abs/1801.09419v2
PDF	http://arxiv.org/pdf/1801.09419v2.pdf
PWC	https://paperswithcode.com/paper/a-notion-of-stability-for-k-means-clustering
Repo
Framework

Bayesian Patchworks: An Approach to Case-Based Reasoning


Title	Bayesian Patchworks: An Approach to Case-Based Reasoning
Authors	Ramin Moghaddass, Cynthia Rudin
Abstract	Doctors often rely on their past experience in order to diagnose patients. For a doctor with enough experience, almost every patient would have similarities to key cases seen in the past, and each new patient could be viewed as a mixture of these key past cases. Because doctors often tend to reason this way, an efficient computationally aided diagnostic tool that thinks in the same way might be helpful in locating key past cases of interest that could assist with diagnosis. This article develops a novel mathematical model to mimic the type of logical thinking that physicians use when considering past cases. The proposed model can also provide physicians with explanations that would be similar to the way they would naturally reason about cases. The proposed method is designed to yield predictive accuracy, computational efficiency, and insight into medical data; the key element is the insight into medical data, in some sense we are automating a complicated process that physicians might perform manually. We finally implemented the result of this work on two publicly available healthcare datasets, for heart disease prediction and breast cancer prediction.
Tasks	Disease Prediction
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03541v1
PDF	http://arxiv.org/pdf/1809.03541v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-patchworks-an-approach-to-case-based
Repo
Framework

Object Referring in Videos with Language and Human Gaze


Title	Object Referring in Videos with Language and Human Gaze
Authors	Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
Abstract	We investigate the problem of object referring (OR) i.e. to localize a target object in a visual scene coming with a language description. Humans perceive the world more as continued video snippets than as static images, and describe objects not only by their appearance, but also by their spatio-temporal context and motion features. Humans also gaze at the object when they issue a referring expression. Existing works for OR mostly focus on static images only, which fall short in providing many such cues. This paper addresses OR in videos with language and human gaze. To that end, we present a new video dataset for OR, with 30, 000 objects over 5, 000 stereo video sequences annotated for their descriptions and gaze. We further propose a novel network model for OR in videos, by integrating appearance, motion, gaze, and spatio-temporal context into one network. Experimental results show that our method effectively utilizes motion cues, human gaze, and spatio-temporal context. Our method outperforms previousOR methods. For dataset and code, please refer https://people.ee.ethz.ch/~arunv/ORGaze.html.
Tasks
Published	2018-01-04
URL	http://arxiv.org/abs/1801.01582v2
PDF	http://arxiv.org/pdf/1801.01582v2.pdf
PWC	https://paperswithcode.com/paper/object-referring-in-videos-with-language-and
Repo
Framework