May 7, 2019

3328 words 16 mins read

Paper Group AWR 35

The Evolution of Sentiment Analysis - A Review of Research Topics, Venues, and Top Cited Papers. Sampling Requirements and Accelerated Schemes for Sparse Linear Regression with Orthogonal Least-Squares. Linguistic Input Features Improve Neural Machine Translation. Topic Modeling over Short Texts by Incorporating Word Embeddings. Very Deep Convoluti …

The Evolution of Sentiment Analysis - A Review of Research Topics, Venues, and Top Cited Papers


Title	The Evolution of Sentiment Analysis - A Review of Research Topics, Venues, and Top Cited Papers
Authors	Mika Viking Mäntylä, Daniel Graziotin, Miikka Kuutila
Abstract	Sentiment analysis is one of the fastest growing research areas in computer science, making it challenging to keep track of all the activities in the area. We present a computer-assisted literature review, where we utilize both text mining and qualitative coding, and analyze 6,996 papers from Scopus. We find that the roots of sentiment analysis are in the studies on public opinion analysis at the beginning of 20th century and in the text subjectivity analysis performed by the computational linguistics community in 1990’s. However, the outbreak of computer-based sentiment analysis only occurred with the availability of subjective texts on the Web. Consequently, 99% of the papers have been published after 2004. Sentiment analysis papers are scattered to multiple publication venues, and the combined number of papers in the top-15 venues only represent ca. 30% of the papers in total. We present the top-20 cited papers from Google Scholar and Scopus and a taxonomy of research topics. In recent years, sentiment analysis has shifted from analyzing online product reviews to social media texts from Twitter and Facebook. Many topics beyond product reviews like stock markets, elections, disasters, medicine, software engineering and cyberbullying extend the utilization of sentiment analysis
Tasks	Sentiment Analysis, Subjectivity Analysis
Published	2016-12-05
URL	http://arxiv.org/abs/1612.01556v4
PDF	http://arxiv.org/pdf/1612.01556v4.pdf
PWC	https://paperswithcode.com/paper/the-evolution-of-sentiment-analysis-a-review
Repo	https://github.com/HeikkiMustonen/Etrends
Framework	none

Sampling Requirements and Accelerated Schemes for Sparse Linear Regression with Orthogonal Least-Squares


Title	Sampling Requirements and Accelerated Schemes for Sparse Linear Regression with Orthogonal Least-Squares
Authors	Abolfazl Hashemi, Haris Vikalo
Abstract	We study the problem of inferring a sparse vector from random linear combinations of its components. We propose the Accelerated Orthogonal Least-Squares (AOLS) algorithm that improves performance of the well-known Orthogonal Least-Squares (OLS) algorithm while requiring significantly lower computational costs. While OLS greedily selects columns of the coefficient matrix that correspond to non-zero components of the sparse vector, AOLS employs a novel computationally efficient procedure that speeds up the search by anticipating future selections via choosing $L$ columns in each step, where $L$ is an adjustable hyper-parameter. We analyze the performance of AOLS and establish lower bounds on the probability of exact recovery for both noiseless and noisy random linear measurements. In the noiseless scenario, it is shown that when the coefficients are samples from a Gaussian distribution, AOLS with high probability recovers a $k$-sparse $m$-dimensional sparse vector using ${\cal O}(k\log \frac{m}{k+L-1})$ measurements. Similar result is established for the bounded-noise scenario where an additional condition on the smallest nonzero element of the unknown vector is required. The asymptotic sampling complexity of AOLS is lower than the asymptotic sampling complexity of the existing sparse reconstruction algorithms. In simulations, AOLS is compared to state-of-the-art sparse recovery techniques and shown to provide better performance in terms of accuracy, running time, or both. Finally, we consider an application of AOLS to clustering high-dimensional data lying on the union of low-dimensional subspaces and demonstrate its superiority over existing methods.
Tasks
Published	2016-08-08
URL	http://arxiv.org/abs/1608.02549v2
PDF	http://arxiv.org/pdf/1608.02549v2.pdf
PWC	https://paperswithcode.com/paper/sampling-requirements-and-accelerated-schemes
Repo	https://github.com/realabolfazl/AOLS
Framework	none

Linguistic Input Features Improve Neural Machine Translation


Title	Linguistic Input Features Improve Neural Machine Translation
Authors	Rico Sennrich, Barry Haddow
Abstract	Neural machine translation has recently achieved impressive results, while using little in the way of external linguistic information. In this paper we show that the strong learning capability of neural MT models does not make linguistic features redundant; they can be easily incorporated to provide further improvements in performance. We generalize the embedding layer of the encoder in the attentional encoder–decoder architecture to support the inclusion of arbitrary features, in addition to the baseline word feature. We add morphological features, part-of-speech tags, and syntactic dependency labels as input features to English<->German, and English->Romanian neural machine translation systems. In experiments on WMT16 training and test sets, we find that linguistic input features improve model quality according to three metrics: perplexity, BLEU and CHRF3. An open-source implementation of our neural MT system is available, as are sample files and configurations.
Tasks	Machine Translation
Published	2016-06-09
URL	http://arxiv.org/abs/1606.02892v2
PDF	http://arxiv.org/pdf/1606.02892v2.pdf
PWC	https://paperswithcode.com/paper/linguistic-input-features-improve-neural
Repo	https://github.com/rsennrich/wmt16-scripts
Framework	none

Topic Modeling over Short Texts by Incorporating Word Embeddings


Title	Topic Modeling over Short Texts by Incorporating Word Embeddings
Authors	Jipeng Qiang, Ping Chen, Tong Wang, Xindong Wu
Abstract	Inferring topics from the overwhelming amount of short texts becomes a critical but challenging task for many content analysis tasks, such as content charactering, user interest profiling, and emerging topic detecting. Existing methods such as probabilistic latent semantic analysis (PLSA) and latent Dirichlet allocation (LDA) cannot solve this prob- lem very well since only very limited word co-occurrence information is available in short texts. This paper studies how to incorporate the external word correlation knowledge into short texts to improve the coherence of topic modeling. Based on recent results in word embeddings that learn se- mantically representations for words from a large corpus, we introduce a novel method, Embedding-based Topic Model (ETM), to learn latent topics from short texts. ETM not only solves the problem of very limited word co-occurrence information by aggregating short texts into long pseudo- texts, but also utilizes a Markov Random Field regularized model that gives correlated words a better chance to be put into the same topic. The experiments on real-world datasets validate the effectiveness of our model comparing with the state-of-the-art models.
Tasks	Word Embeddings
Published	2016-09-27
URL	http://arxiv.org/abs/1609.08496v1
PDF	http://arxiv.org/pdf/1609.08496v1.pdf
PWC	https://paperswithcode.com/paper/topic-modeling-over-short-texts-by
Repo	https://github.com/williamscott701/Embedding-LJST
Framework	none

Very Deep Convolutional Neural Networks for Raw Waveforms


Title	Very Deep Convolutional Neural Networks for Raw Waveforms
Authors	Wei Dai, Chia Dai, Shuhui Qu, Juncheng Li, Samarjit Das
Abstract	Learning acoustic models directly from the raw waveform data with minimal processing is challenging. Current waveform-based models have generally used very few (~2) convolutional layers, which might be insufficient for building high-level discriminative features. In this work, we propose very deep convolutional neural networks (CNNs) that directly use time-domain waveforms as inputs. Our CNNs, with up to 34 weight layers, are efficient to optimize over very long sequences (e.g., vector of size 32000), necessary for processing acoustic waveforms. This is achieved through batch normalization, residual learning, and a careful design of down-sampling in the initial layers. Our networks are fully convolutional, without the use of fully connected layers and dropout, to maximize representation learning. We use a large receptive field in the first convolutional layer to mimic bandpass filters, but very small receptive fields subsequently to control the model capacity. We demonstrate the performance gains with the deeper models. Our evaluation shows that the CNN with 18 weight layers outperform the CNN with 3 weight layers by over 15% in absolute accuracy for an environmental sound recognition task and matches the performance of models using log-mel features.
Tasks	Representation Learning
Published	2016-10-01
URL	http://arxiv.org/abs/1610.00087v1
PDF	http://arxiv.org/pdf/1610.00087v1.pdf
PWC	https://paperswithcode.com/paper/very-deep-convolutional-neural-networks-for
Repo	https://github.com/lkidane/Very-Deep-Convolutional-Networks-For-Raw-Waveforms-pytorch-implementation
Framework	pytorch

Data Curation APIs


Title	Data Curation APIs
Authors	Seyed-Mehdi-Reza Beheshti, Alireza Tabebordbar, Boualem Benatallah, Reza Nouri
Abstract	Understanding and analyzing big data is firmly recognized as a powerful and strategic priority. For deeper interpretation of and better intelligence with big data, it is important to transform raw data (unstructured, semi-structured and structured data sources, e.g., text, video, image data sets) into curated data: contextualized data and knowledge that is maintained and made available for use by end-users and applications. In particular, data curation acts as the glue between raw data and analytics, providing an abstraction layer that relieves users from time consuming, tedious and error prone curation tasks. In this context, the data curation process becomes a vital analytics asset for increasing added value and insights. In this paper, we identify and implement a set of curation APIs and make them available (on GitHub) to researchers and developers to assist them transforming their raw data into curated data. The curation APIs enable developers to easily add features - such as extracting keyword, part of speech, and named entities such as Persons, Locations, Organizations, Companies, Products, Diseases, Drugs, etc.; providing synonyms and stems for extracted information items leveraging lexical knowledge bases for the English language such as WordNet; linking extracted entities to external knowledge bases such as Google Knowledge Graph and Wikidata; discovering similarity among the extracted information items, such as calculating similarity between string, number, date and time data; classifying, sorting and categorizing data into various types, forms or any other distinct class; and indexing structured and unstructured data - into their applications.
Tasks
Published	2016-12-10
URL	http://arxiv.org/abs/1612.03277v1
PDF	http://arxiv.org/pdf/1612.03277v1.pdf
PWC	https://paperswithcode.com/paper/data-curation-apis
Repo	https://github.com/unsw-cse-soc/Data-curation-API
Framework	none

Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder


Title	Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder
Authors	Chin-Cheng Hsu, Hsin-Te Hwang, Yi-Chiao Wu, Yu Tsao, Hsin-Min Wang
Abstract	We propose a flexible framework for spectral conversion (SC) that facilitates training with unaligned corpora. Many SC frameworks require parallel corpora, phonetic alignments, or explicit frame-wise correspondence for learning conversion functions or for synthesizing a target spectrum with the aid of alignments. However, these requirements gravely limit the scope of practical applications of SC due to scarcity or even unavailability of parallel corpora. We propose an SC framework based on variational auto-encoder which enables us to exploit non-parallel corpora. The framework comprises an encoder that learns speaker-independent phonetic representations and a decoder that learns to reconstruct the designated speaker. It removes the requirement of parallel corpora or phonetic alignments to train a spectral conversion system. We report objective and subjective evaluations to validate our proposed method and compare it to SC methods that have access to aligned corpora.
Tasks	Voice Conversion
Published	2016-10-13
URL	http://arxiv.org/abs/1610.04019v1
PDF	http://arxiv.org/pdf/1610.04019v1.pdf
PWC	https://paperswithcode.com/paper/voice-conversion-from-non-parallel-corpora
Repo	https://github.com/JeremyCCHsu/vae-npvc
Framework	tf

Learning Latent Vector Spaces for Product Search


Title	Learning Latent Vector Spaces for Product Search
Authors	Christophe Van Gysel, Maarten de Rijke, Evangelos Kanoulas
Abstract	We introduce a novel latent vector space model that jointly learns the latent representations of words, e-commerce products and a mapping between the two without the need for explicit annotations. The power of the model lies in its ability to directly model the discriminative relation between products and a particular word. We compare our method to existing latent vector space models (LSI, LDA and word2vec) and evaluate it as a feature in a learning to rank setting. Our latent vector space model achieves its enhanced performance as it learns better product representations. Furthermore, the mapping from words to products and the representations of words benefit directly from the errors propagated back from the product representations during parameter estimation. We provide an in-depth analysis of the performance of our model and analyze the structure of the learned representations.
Tasks	Learning-To-Rank
Published	2016-08-25
URL	http://arxiv.org/abs/1608.07253v1
PDF	http://arxiv.org/pdf/1608.07253v1.pdf
PWC	https://paperswithcode.com/paper/learning-latent-vector-spaces-for-product
Repo	https://github.com/cvangysel/SERT
Framework	none

Volumetric and Multi-View CNNs for Object Classification on 3D Data


Title	Volumetric and Multi-View CNNs for Object Classification on 3D Data
Authors	Charles R. Qi, Hao Su, Matthias Niessner, Angela Dai, Mengyuan Yan, Leonidas J. Guibas
Abstract	3D shape models are becoming widely available and easier to capture, making available 3D information crucial for progress in object classification. Current state-of-the-art methods rely on CNNs to address this problem. Recently, we witness two types of CNNs being developed: CNNs based upon volumetric representations versus CNNs based upon multi-view representations. Empirical results from these two types of CNNs exhibit a large gap, indicating that existing volumetric CNN architectures and approaches are unable to fully exploit the power of 3D representations. In this paper, we aim to improve both volumetric CNNs and multi-view CNNs according to extensive analysis of existing approaches. To this end, we introduce two distinct network architectures of volumetric CNNs. In addition, we examine multi-view CNNs, where we introduce multi-resolution filtering in 3D. Overall, we are able to outperform current state-of-the-art methods for both volumetric CNNs and multi-view CNNs. We provide extensive experiments designed to evaluate underlying design choices, thus providing a better understanding of the space of methods available for object classification on 3D data.
Tasks	3D Object Recognition, Object Classification
Published	2016-04-12
URL	http://arxiv.org/abs/1604.03265v2
PDF	http://arxiv.org/pdf/1604.03265v2.pdf
PWC	https://paperswithcode.com/paper/volumetric-and-multi-view-cnns-for-object
Repo	https://github.com/charlesq34/3dcnn.torch
Framework	torch

Spectral Theory of Unsigned and Signed Graphs. Applications to Graph Clustering: a Survey


Title	Spectral Theory of Unsigned and Signed Graphs. Applications to Graph Clustering: a Survey
Authors	Jean Gallier
Abstract	This is a survey of the method of graph cuts and its applications to graph clustering of weighted unsigned and signed graphs. I provide a fairly thorough treatment of the method of normalized graph cuts, a deeply original method due to Shi and Malik, including complete proofs. The main thrust of this paper is the method of normalized cuts. I give a detailed account for K = 2 clusters, and also for K > 2 clusters, based on the work of Yu and Shi. I also show how both graph drawing and normalized cut K-clustering can be easily generalized to handle signed graphs, which are weighted graphs in which the weight matrix W may have negative coefficients. Intuitively, negative coefficients indicate distance or dissimilarity. The solution is to replace the degree matrix by the matrix in which absolute values of the weights are used, and to replace the Laplacian by the Laplacian with the new degree matrix of absolute values. As far as I know, the generalization of K-way normalized clustering to signed graphs is new. Finally, I show how the method of ratio cuts, in which a cut is normalized by the size of the cluster rather than its volume, is just a special case of normalized cuts.
Tasks	Graph Clustering
Published	2016-01-18
URL	http://arxiv.org/abs/1601.04692v1
PDF	http://arxiv.org/pdf/1601.04692v1.pdf
PWC	https://paperswithcode.com/paper/spectral-theory-of-unsigned-and-signed-graphs
Repo	https://github.com/jsedoc/SignedSpectralClustering
Framework	none

Gated Neural Networks for Option Pricing: Rationality by Design


Title	Gated Neural Networks for Option Pricing: Rationality by Design
Authors	Yongxin Yang, Yu Zheng, Timothy M. Hospedales
Abstract	We propose a neural network approach to price EU call options that significantly outperforms some existing pricing models and comes with guarantees that its predictions are economically reasonable. To achieve this, we introduce a class of gated neural networks that automatically learn to divide-and-conquer the problem space for robust and accurate pricing. We then derive instantiations of these networks that are ‘rational by design’ in terms of naturally encoding a valid call option surface that enforces no arbitrage principles. This integration of human insight within data-driven learning provides significantly better generalisation in pricing performance due to the encoded inductive bias in the learning, guarantees sanity in the model’s predictions, and provides econometrically useful byproduct such as risk neutral density.
Tasks
Published	2016-09-14
URL	https://arxiv.org/abs/1609.07472v3
PDF	https://arxiv.org/pdf/1609.07472v3.pdf
PWC	https://paperswithcode.com/paper/gated-neural-networks-for-option-pricing
Repo	https://github.com/arraystream/fftoptionlib
Framework	none

Convolutional Neural Networks For Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control


Title	Convolutional Neural Networks For Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control
Authors	Bert J. Claessens, Peter Vrancx, Frederik Ruelens
Abstract	Direct load control of a heterogeneous cluster of residential demand flexibility sources is a high-dimensional control problem with partial observability. This work proposes a novel approach that uses a convolutional neural network to extract hidden state-time features to mitigate the curse of partial observability. More specific, a convolutional neural network is used as a function approximator to estimate the state-action value function or Q-function in the supervised learning step of fitted Q-iteration. The approach is evaluated in a qualitative simulation, comprising a cluster of thermostatically controlled loads that only share their air temperature, whilst their envelope temperature remains hidden. The simulation results show that the presented approach is able to capture the underlying hidden features and successfully reduce the electricity cost the cluster.
Tasks
Published	2016-04-28
URL	http://arxiv.org/abs/1604.08382v2
PDF	http://arxiv.org/pdf/1604.08382v2.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-for-automatic-1
Repo	https://github.com/tahanakabi/Deep-Reinforcenment-learning-for-TCL-control
Framework	tf

Image biomarker standardisation initiative


Title	Image biomarker standardisation initiative
Authors	Alex Zwanenburg, Stefan Leger, Martin Vallières, Steffen Löck
Abstract	The image biomarker standardisation initiative (IBSI) is an independent international collaboration which works towards standardising the extraction of image biomarkers from acquired imaging for the purpose of high-throughput quantitative image analysis (radiomics). Lack of reproducibility and validation of high-throughput quantitative image analysis studies is considered to be a major challenge for the field. Part of this challenge lies in the scantiness of consensus-based guidelines and definitions for the process of translating acquired imaging into high-throughput image biomarkers. The IBSI therefore seeks to provide image biomarker nomenclature and definitions, benchmark data sets, and benchmark values to verify image processing and image biomarker calculations, as well as reporting guidelines, for high-throughput image analysis.
Tasks
Published	2016-12-21
URL	https://arxiv.org/abs/1612.07003v9
PDF	https://arxiv.org/pdf/1612.07003v9.pdf
PWC	https://paperswithcode.com/paper/image-biomarker-standardisation-initiative
Repo	https://github.com/albytrav/RadiomicsOntologyIBSI
Framework	none

Fundamental Parameters of Main-Sequence Stars in an Instant with Machine Learning


Title	Fundamental Parameters of Main-Sequence Stars in an Instant with Machine Learning
Authors	Earl P. Bellinger, George C. Angelou, Saskia Hekker, Sarbani Basu, Warrick Ball, Elisabeth Guggenberger
Abstract	Owing to the remarkable photometric precision of space observatories like Kepler, stellar and planetary systems beyond our own are now being characterized en masse for the first time. These characterizations are pivotal for endeavors such as searching for Earth-like planets and solar twins, understanding the mechanisms that govern stellar evolution, and tracing the dynamics of our Galaxy. The volume of data that is becoming available, however, brings with it the need to process this information accurately and rapidly. While existing methods can constrain fundamental stellar parameters such as ages, masses, and radii from these observations, they require substantial computational efforts to do so. We develop a method based on machine learning for rapidly estimating fundamental parameters of main-sequence solar-like stars from classical and asteroseismic observations. We first demonstrate this method on a hare-and-hound exercise and then apply it to the Sun, 16 Cyg A & B, and 34 planet-hosting candidates that have been observed by the Kepler spacecraft. We find that our estimates and their associated uncertainties are comparable to the results of other methods, but with the additional benefit of being able to explore many more stellar parameters while using much less computation time. We furthermore use this method to present evidence for an empirical diffusion-mass relation. Our method is open source and freely available for the community to use. The source code for all analyses and for all figures appearing in this manuscript can be found electronically at https://github.com/earlbellinger/asteroseismology
Tasks
Published	2016-07-06
URL	http://arxiv.org/abs/1607.02137v1
PDF	http://arxiv.org/pdf/1607.02137v1.pdf
PWC	https://paperswithcode.com/paper/fundamental-parameters-of-main-sequence-stars
Repo	https://github.com/earlbellinger/asteroseismology
Framework	none

The Emergence of Organizing Structure in Conceptual Representation


Title	The Emergence of Organizing Structure in Conceptual Representation
Authors	Brenden M. Lake, Neil D. Lawrence, Joshua B. Tenenbaum
Abstract	Both scientists and children make important structural discoveries, yet their computational underpinnings are not well understood. Structure discovery has previously been formalized as probabilistic inference about the right structural form — where form could be a tree, ring, chain, grid, etc. [Kemp & Tenenbaum (2008). The discovery of structural form. PNAS, 105(3), 10687-10692]. While this approach can learn intuitive organizations, including a tree for animals and a ring for the color circle, it assumes a strong inductive bias that considers only these particular forms, and each form is explicitly provided as initial knowledge. Here we introduce a new computational model of how organizing structure can be discovered, utilizing a broad hypothesis space with a preference for sparse connectivity. Given that the inductive bias is more general, the model’s initial knowledge shows little qualitative resemblance to some of the discoveries it supports. As a consequence, the model can also learn complex structures for domains that lack intuitive description, as well as predict human property induction judgments without explicit structural forms. By allowing form to emerge from sparsity, our approach clarifies how both the richness and flexibility of human conceptual organization can coexist.
Tasks
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09384v2
PDF	http://arxiv.org/pdf/1611.09384v2.pdf
PWC	https://paperswithcode.com/paper/the-emergence-of-organizing-structure-in
Repo	https://github.com/brendenlake/structural-sparsity
Framework	none