October 16, 2019

3112 words 15 mins read

Paper Group ANR 1008

Deep Dialog Act Recognition using Multiple Token, Segment, and Context Information Representations. AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks. Unified recurrent neural network for many feature types. Opinion Spam Recognition Method for Online Reviews using Ontological Features. Multi-task Learning for Universal Sent …

Deep Dialog Act Recognition using Multiple Token, Segment, and Context Information Representations


Title	Deep Dialog Act Recognition using Multiple Token, Segment, and Context Information Representations
Authors	Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
Abstract	Dialog act (DA) recognition is a task that has been widely explored over the years. Recently, most approaches to the task explored different DNN architectures to combine the representations of the words in a segment and generate a segment representation that provides cues for intention. In this study, we explore means to generate more informative segment representations, not only by exploring different network architectures, but also by considering different token representations, not only at the word level, but also at the character and functional levels. At the word level, in addition to the commonly used uncontextualized embeddings, we explore the use of contextualized representations, which provide information concerning word sense and segment structure. Character-level tokenization is important to capture intention-related morphological aspects that cannot be captured at the word level. Finally, the functional level provides an abstraction from words, which shifts the focus to the structure of the segment. We also explore approaches to enrich the segment representation with context information from the history of the dialog, both in terms of the classifications of the surrounding segments and the turn-taking history. This kind of information has already been proved important for the disambiguation of DAs in previous studies. Nevertheless, we are able to capture additional information by considering a summary of the dialog history and a wider turn-taking context. By combining the best approaches at each step, we achieve results that surpass the previous state-of-the-art on generic DA recognition on both SwDA and MRDA, two of the most widely explored corpora for the task. Furthermore, by considering both past and future context, simulating annotation scenario, our approach achieves a performance similar to that of a human annotator on SwDA and surpasses it on MRDA.
Tasks	Tokenization, Word Embeddings
Published	2018-07-23
URL	https://arxiv.org/abs/1807.08587v2
PDF	https://arxiv.org/pdf/1807.08587v2.pdf
PWC	https://paperswithcode.com/paper/deep-dialog-act-recognition-using-multiple
Repo
Framework

AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks


Title	AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks
Authors	Yu Shi, Huan Gui, Qi Zhu, Lance Kaplan, Jiawei Han
Abstract	Heterogeneous information networks (HINs) are ubiquitous in real-world applications. Due to the heterogeneity in HINs, the typed edges may not fully align with each other. In order to capture the semantic subtlety, we propose the concept of aspects with each aspect being a unit representing one underlying semantic facet. Meanwhile, network embedding has emerged as a powerful method for learning network representation, where the learned embedding can be used as features in various downstream applications. Therefore, we are motivated to propose a novel embedding learning framework—AspEm—to preserve the semantic information in HINs based on multiple aspects. Instead of preserving information of the network in one semantic space, AspEm encapsulates information regarding each aspect individually. In order to select aspects for embedding purpose, we further devise a solution for AspEm based on dataset-wide statistics. To corroborate the efficacy of AspEm, we conducted experiments on two real-words datasets with two types of applications—classification and link prediction. Experiment results demonstrate that AspEm can outperform baseline network embedding learning methods by considering multiple aspects, where the aspects can be selected from the given HIN in an unsupervised manner.
Tasks	Link Prediction, Network Embedding
Published	2018-03-05
URL	http://arxiv.org/abs/1803.01848v1
PDF	http://arxiv.org/pdf/1803.01848v1.pdf
PWC	https://paperswithcode.com/paper/aspem-embedding-learning-by-aspects-in
Repo
Framework

Unified recurrent neural network for many feature types


Title	Unified recurrent neural network for many feature types
Authors	Alexander Stec, Diego Klabjan, Jean Utke
Abstract	There are time series that are amenable to recurrent neural network (RNN) solutions when treated as sequences, but some series, e.g. asynchronous time series, provide a richer variation of feature types than current RNN cells take into account. In order to address such situations, we introduce a unified RNN that handles five different feature types, each in a different manner. Our RNN framework separates sequential features into two groups dependent on their frequency, which we call sparse and dense features, and which affect cell updates differently. Further, we also incorporate time features at the sequential level that relate to the time between specified events in the sequence and are used to modify the cell’s memory state. We also include two types of static (whole sequence level) features, one related to time and one not, which are combined with the encoder output. The experiments show that the modeling framework proposed does increase performance compared to standard cells.
Tasks	Time Series
Published	2018-09-24
URL	http://arxiv.org/abs/1809.08717v1
PDF	http://arxiv.org/pdf/1809.08717v1.pdf
PWC	https://paperswithcode.com/paper/unified-recurrent-neural-network-for-many
Repo
Framework

Opinion Spam Recognition Method for Online Reviews using Ontological Features


Title	Opinion Spam Recognition Method for Online Reviews using Ontological Features
Authors	L. H. Nguyen, N. T. H. Pham, V. M. Ngo
Abstract	Nowadays, there are a lot of people using social media opinions to make their decision on buying products or services. Opinion spam detection is a hard problem because fake reviews can be made by organizations as well as individuals for different purposes. They write fake reviews to mislead readers or automated detection system by promoting or demoting target products to promote them or to damage their reputations. In this paper, we pro-pose a new approach using knowledge-based Ontology to detect opinion spam with high accuracy (higher than 75%). Keywords: Opinion spam, Fake review, E-commercial, Ontology.
Tasks
Published	2018-07-29
URL	http://arxiv.org/abs/1807.11024v1
PDF	http://arxiv.org/pdf/1807.11024v1.pdf
PWC	https://paperswithcode.com/paper/opinion-spam-recognition-method-for-online
Repo
Framework

Multi-task Learning for Universal Sentence Embeddings: A Thorough Evaluation using Transfer and Auxiliary Tasks


Title	Multi-task Learning for Universal Sentence Embeddings: A Thorough Evaluation using Transfer and Auxiliary Tasks
Authors	Wasi Uddin Ahmad, Xueying Bai, Zhechao Huang, Chao Jiang, Nanyun Peng, Kai-Wei Chang
Abstract	Learning distributed sentence representations is one of the key challenges in natural language processing. Previous work demonstrated that a recurrent neural network (RNNs) based sentence encoder trained on a large collection of annotated natural language inference data, is efficient in the transfer learning to facilitate other related tasks. In this paper, we show that joint learning of multiple tasks results in better generalizable sentence representations by conducting extensive experiments and analysis comparing the multi-task and single-task learned sentence encoders. The quantitative analysis using auxiliary tasks show that multi-task learning helps to embed better semantic information in the sentence representations compared to single-task learning. In addition, we compare multi-task sentence encoders with contextualized word representations and show that combining both of them can further boost the performance of transfer learning.
Tasks	Multi-Task Learning, Natural Language Inference, Sentence Embeddings, Transfer Learning
Published	2018-04-21
URL	http://arxiv.org/abs/1804.07911v2
PDF	http://arxiv.org/pdf/1804.07911v2.pdf
PWC	https://paperswithcode.com/paper/multi-task-learning-for-universal-sentence
Repo
Framework


Title	Multi-Task Pharmacovigilance Mining from Social Media Posts
Authors	Shaika Chowdhury, Chenwei Zhang, Philip S. Yu
Abstract	Social media has grown to be a crucial information source for pharmacovigilance studies where an increasing number of people post adverse reactions to medical drugs that are previously unreported. Aiming to effectively monitor various aspects of Adverse Drug Reactions (ADRs) from diversely expressed social medical posts, we propose a multi-task neural network framework that learns several tasks associated with ADR monitoring with different levels of supervisions collectively. Besides being able to correctly classify ADR posts and accurately extract ADR mentions from online posts, the proposed framework is also able to further understand reasons for which the drug is being taken, known as ‘indication’, from the given social media post. A coverage-based attention mechanism is adopted in our framework to help the model properly identify ‘phrasal’ ADRs and Indications that are attentive to multiple words in a post. Our framework is applicable in situations where limited parallel data for different pharmacovigilance tasks are available.We evaluate the proposed framework on real-world Twitter datasets, where the proposed model outperforms the state-of-the-art alternatives of each individual task consistently.
Tasks
Published	2018-01-19
URL	http://arxiv.org/abs/1801.06294v5
PDF	http://arxiv.org/pdf/1801.06294v5.pdf
PWC	https://paperswithcode.com/paper/multi-task-pharmacovigilance-mining-from
Repo
Framework

Tree-structured Kronecker Convolutional Network for Semantic Segmentation


Title	Tree-structured Kronecker Convolutional Network for Semantic Segmentation
Authors	Tianyi Wu, Sheng Tang, Rui Zhang, Juan Cao, Jintao Li
Abstract	Most existing semantic segmentation methods employ atrous convolution to enlarge the receptive field of filters, but neglect partial information. To tackle this issue, we firstly propose a novel Kronecker convolution which adopts Kronecker product to expand the standard convolutional kernel for taking into account the partial feature neglected by atrous convolutions. Therefore, it can capture partial information and enlarge the receptive field of filters simultaneously without introducing extra parameters. Secondly, we propose Tree-structured Feature Aggregation (TFA) module which follows a recursive rule to expand and forms a hierarchical structure. Thus, it can naturally learn representations of multi-scale objects and encode hierarchical contextual information in complex scenes. Finally, we design Tree-structured Kronecker Convolutional Networks (TKCN) which employs Kronecker convolution and TFA module. Extensive experiments on three datasets, PASCAL VOC 2012, PASCAL-Context and Cityscapes, verify the effectiveness of our proposed approach. We make the code and the trained model publicly available at https://github.com/wutianyiRosun/TKCN.
Tasks	Semantic Segmentation
Published	2018-12-12
URL	http://arxiv.org/abs/1812.04945v2
PDF	http://arxiv.org/pdf/1812.04945v2.pdf
PWC	https://paperswithcode.com/paper/tree-structured-kronecker-convolutional
Repo
Framework

EEG-based video identification using graph signal modeling and graph convolutional neural network


Title	EEG-based video identification using graph signal modeling and graph convolutional neural network
Authors	Soobeom Jang, Seong-Eun Moon, Jong-Seok Lee
Abstract	This paper proposes a novel graph signal-based deep learning method for electroencephalography (EEG) and its application to EEG-based video identification. We present new methods to effectively represent EEG data as signals on graphs, and learn them using graph convolutional neural networks. Experimental results for video identification using EEG responses obtained while watching videos show the effectiveness of the proposed approach in comparison to existing methods. Effective schemes for graph signal representation of EEG are also discussed.
Tasks	EEG
Published	2018-09-12
URL	http://arxiv.org/abs/1809.04229v1
PDF	http://arxiv.org/pdf/1809.04229v1.pdf
PWC	https://paperswithcode.com/paper/eeg-based-video-identification-using-graph
Repo
Framework

Normalization in Training U-Net for 2D Biomedical Semantic Segmentation


Title	Normalization in Training U-Net for 2D Biomedical Semantic Segmentation
Authors	Xiao-Yun Zhou, Guang-Zhong Yang
Abstract	2D biomedical semantic segmentation is important for robotic vision in surgery. Segmentation methods based on Deep Convolutional Neural Network (DCNN) can out-perform conventional methods in terms of both accuracy and levels of automation. One common issue in training a DCNN for biomedical semantic segmentation is the internal covariate shift where the training of convolutional kernels is encumbered by the distribution change of input features, hence both the training speed and performance are decreased. Batch Normalization (BN) is the first proposed method for addressing internal covariate shift and is widely used. Instance Normalization (IN) and Layer Normalization (LN) have also been proposed. Group Normalization (GN) is proposed more recently and has not yet been applied to 2D biomedical semantic segmentation, however, no specific validations on GN were given. Most DCNNs for biomedical semantic segmentation adopt BN as the normalization method by default, without reviewing its performance. In this paper, four normalization methods - BN, IN, LN and GN are compared in details, specifically for 2D biomedical semantic segmentation. U-Net is adopted as the basic DCNN structure. Three datasets regarding the Right Ventricle (RV), aorta, and Left Ventricle (LV) are used for the validation. The results show that detailed subdivision of the feature map, i.e. GN with a large group number or IN, achieves higher accuracy. This accuracy improvement mainly comes from better model generalization. Codes are uploaded and maintained at Xiao-Yun Zhou’s Github.
Tasks	Semantic Segmentation
Published	2018-09-11
URL	http://arxiv.org/abs/1809.03783v3
PDF	http://arxiv.org/pdf/1809.03783v3.pdf
PWC	https://paperswithcode.com/paper/normalization-in-training-u-net-for-2d
Repo
Framework

Sentiment Transfer using Seq2Seq Adversarial Autoencoders


Title	Sentiment Transfer using Seq2Seq Adversarial Autoencoders
Authors	Ayush Singh, Ritu Palod
Abstract	Expressing in language is subjective. Everyone has a different style of reading and writing, apparently it all boil downs to the way their mind understands things (in a specific format). Language style transfer is a way to preserve the meaning of a text and change the way it is expressed. Progress in language style transfer is lagged behind other domains, such as computer vision, mainly because of the lack of parallel data, use cases, and reliable evaluation metrics. In response to the challenge of lacking parallel data, we explore learning style transfer from non-parallel data. We propose a model combining seq2seq, autoencoders, and adversarial loss to achieve this goal. The key idea behind the proposed models is to learn separate content representations and style representations using adversarial networks. Considering the problem of evaluating style transfer tasks, we frame the problem as sentiment transfer and evaluation using a sentiment classifier to calculate how many sentiments was the model able to transfer. We report our results on several kinds of models.
Tasks	Style Transfer
Published	2018-04-10
URL	http://arxiv.org/abs/1804.04003v1
PDF	http://arxiv.org/pdf/1804.04003v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-transfer-using-seq2seq-adversarial
Repo
Framework

Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation


Title	Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
Authors	Chao Chen, Zhihong Chen, Boyuan Jiang, Xinyu Jin
Abstract	Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution discrepancy across different domains. Due to the fact that all the domain alignment approaches can only reduce, but not remove the domain shift. Target domain samples distributed near the edge of the clusters, or far from their corresponding class centers are easily to be misclassified by the hyperplane learned from the source domain. To alleviate this issue, we propose to joint domain alignment and discriminative feature learning, which could benefit both domain alignment and final classification. Specifically, an instance-based discriminative feature learning method and a center-based discriminative feature learning method are proposed, both of which guarantee the domain invariant features with better intra-class compactness and inter-class separability. Extensive experiments show that learning the discriminative features in the shared feature space can significantly boost the performance of deep domain adaptation methods.
Tasks	Domain Adaptation
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09347v2
PDF	http://arxiv.org/pdf/1808.09347v2.pdf
PWC	https://paperswithcode.com/paper/joint-domain-alignment-and-discriminative
Repo
Framework

DeepCAS: A Deep Reinforcement Learning Algorithm for Control-Aware Scheduling


Title	DeepCAS: A Deep Reinforcement Learning Algorithm for Control-Aware Scheduling
Authors	Burak Demirel, Arunselvan Ramaswamy, Daniel E. Quevedo, Holger Karl
Abstract	We consider networked control systems consisting of multiple independent controlled subsystems, operating over a shared communication network. Such systems are ubiquitous in cyber-physical systems, Internet of Things, and large-scale industrial systems. In many large-scale settings, the size of the communication network is smaller than the size of the system. In consequence, scheduling issues arise. The main contribution of this paper is to develop a deep reinforcement learning-based \emph{control-aware} scheduling (\textsc{DeepCAS}) algorithm to tackle these issues. We use the following (optimal) design strategy: First, we synthesize an optimal controller for each subsystem; next, we design a learning algorithm that adapts to the chosen subsystems (plants) and controllers. As a consequence of this adaptation, our algorithm finds a schedule that minimizes the \emph{control loss}. We present empirical results to show that \textsc{DeepCAS} finds schedules with better performance than periodic ones.
Tasks
Published	2018-03-08
URL	http://arxiv.org/abs/1803.02998v2
PDF	http://arxiv.org/pdf/1803.02998v2.pdf
PWC	https://paperswithcode.com/paper/deepcas-a-deep-reinforcement-learning
Repo
Framework

Achieving Fluency and Coherency in Task-oriented Dialog


Title	Achieving Fluency and Coherency in Task-oriented Dialog
Authors	Rashmi Gangadharaiah, Balakrishnan Narayanaswamy, Charles Elkan
Abstract	We consider real world task-oriented dialog settings, where agents need to generate both fluent natural language responses and correct external actions like database queries and updates. We demonstrate that, when applied to customer support chat transcripts, Sequence to Sequence (Seq2Seq) models often generate short, incoherent and ungrammatical natural language responses that are dominated by words that occur with high frequency in the training data. These phenomena do not arise in synthetic datasets such as bAbI, where we show Seq2Seq models are nearly perfect. We develop techniques to learn embeddings that succinctly capture relevant information from the dialog history, and demonstrate that nearest neighbor based approaches in this learned neural embedding space generate more fluent responses. However, we see that these methods are not able to accurately predict when to execute an external action. We show how to combine nearest neighbor and Seq2Seq methods in a hybrid model, where nearest neighbor is used to generate fluent responses and Seq2Seq type models ensure dialog coherency and generate accurate external actions. We show that this approach is well suited for customer support scenarios, where agents’ responses are typically script-driven, and correct external actions are critically important. The hybrid model on the customer support data achieves a 78% relative improvement in fluency scores, and a 130% improvement in accuracy of external calls.
Tasks
Published	2018-04-11
URL	http://arxiv.org/abs/1804.03799v1
PDF	http://arxiv.org/pdf/1804.03799v1.pdf
PWC	https://paperswithcode.com/paper/achieving-fluency-and-coherency-in-task
Repo
Framework

Hierarchical Classification using Binary Data


Title	Hierarchical Classification using Binary Data
Authors	Denali Molitor, Deanna Needell
Abstract	In classification problems, especially those that categorize data into a large number of classes, the classes often naturally follow a hierarchical structure. That is, some classes are likely to share similar structures and features. Those characteristics can be captured by considering a hierarchical relationship among the class labels. Here, we extend a recent simple classification approach on binary data in order to efficiently classify hierarchical data. In certain settings, specifically, when some classes are significantly easier to identify than others, we showcase computational and accuracy advantages.
Tasks
Published	2018-07-23
URL	http://arxiv.org/abs/1807.08825v1
PDF	http://arxiv.org/pdf/1807.08825v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-classification-using-binary-data
Repo
Framework

Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks


Title	Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks
Authors	Ruth Fong, Andrea Vedaldi
Abstract	In an effort to understand the meaning of the intermediate representations captured by deep networks, recent papers have tried to associate specific semantic concepts to individual neural network filter responses, where interesting correlations are often found, largely by focusing on extremal filter responses. In this paper, we show that this approach can favor easy-to-interpret cases that are not necessarily representative of the average behavior of a representation. A more realistic but harder-to-study hypothesis is that semantic representations are distributed, and thus filters must be studied in conjunction. In order to investigate this idea while enabling systematic visualization and quantification of multiple filter responses, we introduce the Net2Vec framework, in which semantic concepts are mapped to vectorial embeddings based on corresponding filter responses. By studying such embeddings, we are able to show that 1., in most cases, multiple filters are required to code for a concept, that 2., often filters are not concept specific and help encode multiple concepts, and that 3., compared to single filter activations, filter embeddings are able to better characterize the meaning of a representation and its relationship to other concepts.
Tasks
Published	2018-01-10
URL	http://arxiv.org/abs/1801.03454v2
PDF	http://arxiv.org/pdf/1801.03454v2.pdf
PWC	https://paperswithcode.com/paper/net2vec-quantifying-and-explaining-how
Repo
Framework