October 16, 2019

3450 words 17 mins read

Paper Group ANR 1140

A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data. Data-Efficient Graph Embedding Learning for PCB Component Detection. A two-stage 3D Unet framework for multi-class segmentation on full resolution image. Towards Modeling the Interaction of Spatial-Associative Neural Network Representations for Multise …

A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data


Title	A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data
Authors	Jingang Wang, Junfeng Tian, Long Qiu, Sheng Li, Jun Lang, Luo Si, Man Lan
Abstract	It is a challenging and practical research problem to obtain effective compression of lengthy product titles for E-commerce. This is particularly important as more and more users browse mobile E-commerce apps and more merchants make the original product titles redundant and lengthy for Search Engine Optimization. Traditional text summarization approaches often require a large amount of preprocessing costs and do not capture the important issue of conversion rate in E-commerce. This paper proposes a novel multi-task learning approach for improving product title compression with user search log data. In particular, a pointer network-based sequence-to-sequence approach is utilized for title compression with an attentive mechanism as an extractive method and an attentive encoder-decoder approach is utilized for generating user search queries. The encoding parameters (i.e., semantic embedding of original titles) are shared among the two tasks and the attention distributions are jointly optimized. An extensive set of experiments with both human annotated data and online deployment demonstrate the advantage of the proposed research for both compression qualities and online business values.
Tasks	Multi-Task Learning, Text Summarization
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01725v1
PDF	http://arxiv.org/pdf/1801.01725v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-task-learning-approach-for-improving
Repo
Framework

Data-Efficient Graph Embedding Learning for PCB Component Detection


Title	Data-Efficient Graph Embedding Learning for PCB Component Detection
Authors	Chia-Wen Kuo, Jacob Ashmore, David Huggins, Zsolt Kira
Abstract	This paper presents a challenging computer vision task, namely the detection of generic components on a PCB, and a novel set of deep-learning methods that are able to jointly leverage the appearance of individual components and the propagation of information across the structure of the board to accurately detect and identify various types of components on a PCB. Due to the expense of manual data labeling, a highly unbalanced distribution of component types, and significant domain shift across boards, most earlier attempts based on traditional image processing techniques fail to generalize well to PCB images with various quality, lighting conditions, etc. Newer object detection pipelines such as Faster R-CNN, on the other hand, require a large amount of labeled data, do not deal with domain shift, and do not leverage structure. To address these issues, we propose a three stage pipeline in which a class-agnostic region proposal network is followed by a low-shot similarity prediction classifier. In order to exploit the data dependency within a PCB, we design a novel Graph Network block to refine the component features conditioned on each PCB. To the best of our knowledge, this is one of the earliest attempts to train a deep learning based model for such tasks, and we demonstrate improvements over recent graph networks for this task. We also provide in-depth analysis and discussion for this challenging task, pointing to future research.
Tasks	Graph Embedding, Object Detection
Published	2018-11-16
URL	http://arxiv.org/abs/1811.06994v2
PDF	http://arxiv.org/pdf/1811.06994v2.pdf
PWC	https://paperswithcode.com/paper/data-efficient-graph-embedding-learning-for
Repo
Framework

A two-stage 3D Unet framework for multi-class segmentation on full resolution image


Title	A two-stage 3D Unet framework for multi-class segmentation on full resolution image
Authors	Chengjia Wang, Tom MacGillivray, Gillian Macnaught, Guang Yang, David Newby
Abstract	Deep convolutional neural networks (CNNs) have been intensively used for multi-class segmentation of data from different modalities and achieved state-of-the-art performances. However, a common problem when dealing with large, high resolution 3D data is that the volumes input into the deep CNNs has to be either cropped or downsampled due to limited memory capacity of computing devices. These operations lead to loss of resolution and increment of class imbalance in the input data batches, which can downgrade the performances of segmentation algorithms. Inspired by the architecture of image super-resolution CNN (SRCNN) and self-normalization network (SNN), we developed a two-stage modified Unet framework that simultaneously learns to detect a ROI within the full volume and to classify voxels without losing the original resolution. Experiments on a variety of multi-modal volumes demonstrated that, when trained with a simply weighted dice coefficients and our customized learning procedure, this framework shows better segmentation performances than state-of-the-art Deep CNNs with advanced similarity metrics.
Tasks	Image Super-Resolution, Super-Resolution
Published	2018-04-12
URL	http://arxiv.org/abs/1804.04341v1
PDF	http://arxiv.org/pdf/1804.04341v1.pdf
PWC	https://paperswithcode.com/paper/a-two-stage-3d-unet-framework-for-multi-class
Repo
Framework

Towards Modeling the Interaction of Spatial-Associative Neural Network Representations for Multisensory Perception


Title	Towards Modeling the Interaction of Spatial-Associative Neural Network Representations for Multisensory Perception
Authors	German I. Parisi, Jonathan Tong, Pablo Barros, Brigitte Röder, Stefan Wermter
Abstract	Our daily perceptual experience is driven by different neural mechanisms that yield multisensory interaction as the interplay between exogenous stimuli and endogenous expectations. While the interaction of multisensory cues according to their spatiotemporal properties and the formation of multisensory feature-based representations have been widely studied, the interaction of spatial-associative neural representations has received considerably less attention. In this paper, we propose a neural network architecture that models the interaction of spatial-associative representations to perform causal inference of audiovisual stimuli. We investigate the spatial alignment of exogenous audiovisual stimuli modulated by associative congruence. In the spatial layer, topographically arranged networks account for the interaction of audiovisual input in terms of population codes. In the associative layer, congruent audiovisual representations are obtained via the experience-driven development of feature-based associations. Levels of congruency are obtained as a by-product of the neurodynamics of self-organizing networks, where the amount of neural activation triggered by the input can be expressed via a nonlinear distance function. Our novel proposal is that activity-driven levels of congruency can be used as top-down modulatory projections to spatially distributed representations of sensory input, e.g. semantically related audiovisual pairs will yield a higher level of integration than unrelated pairs. Furthermore, levels of neural response in unimodal layers may be seen as sensory reliability for the dynamic weighting of crossmodal cues. We describe a series of planned experiments to validate our model in the tasks of multisensory interaction on the basis of semantic congruence and unimodal cue reliability.
Tasks	Causal Inference
Published	2018-07-13
URL	http://arxiv.org/abs/1807.05222v1
PDF	http://arxiv.org/pdf/1807.05222v1.pdf
PWC	https://paperswithcode.com/paper/towards-modeling-the-interaction-of-spatial
Repo
Framework

Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates


Title	Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates
Authors	Sonali Parbhoo, Mario Wieser, Aleksander Wieczorek, Volker Roth
Abstract	Estimating the causal effects of an intervention from high-dimensional observational data is difficult due to the presence of confounding. The task is often complicated by the fact that we may have a systematic missingness in our data at test time. Our approach uses the information bottleneck to perform a low-dimensional compression of covariates by explicitly considering the relevance of information. Based on the sufficiently reduced covariate, we transfer the relevant information to cases where data is missing at test time, allowing us to reliably and accurately estimate the effects of an intervention, even where data is incomplete. Our results on causal inference benchmarks and a real application for treating sepsis show that our method achieves state-of-the art performance, without sacrificing interpretability.
Tasks	Causal Inference
Published	2018-07-06
URL	https://arxiv.org/abs/1807.02326v3
PDF	https://arxiv.org/pdf/1807.02326v3.pdf
PWC	https://paperswithcode.com/paper/cause-effect-deep-information-bottleneck-for
Repo
Framework

Learning Better Internal Structure of Words for Sequence Labeling


Title	Learning Better Internal Structure of Words for Sequence Labeling
Authors	Yingwei Xin, Ethan Hart, Vibhuti Mahajan, Jean-David Ruvini
Abstract	Character-based neural models have recently proven very useful for many NLP tasks. However, there is a gap of sophistication between methods for learning representations of sentences and words. While most character models for learning representations of sentences are deep and complex, models for learning representations of words are shallow and simple. Also, in spite of considerable research on learning character embeddings, it is still not clear which kind of architecture is the best for capturing character-to-word representations. To address these questions, we first investigate the gaps between methods for learning word and sentence representations. We conduct detailed experiments and comparisons of different state-of-the-art convolutional models, and also investigate the advantages and disadvantages of their constituents. Furthermore, we propose IntNet, a funnel-shaped wide convolutional neural architecture with no down-sampling for learning representations of the internal structure of words by composing their characters from limited, supervised training corpora. We evaluate our proposed model on six sequence labeling datasets, including named entity recognition, part-of-speech tagging, and syntactic chunking. Our in-depth analysis shows that IntNet significantly outperforms other character embedding models and obtains new state-of-the-art performance without relying on any external knowledge or resources.
Tasks	Chunking, Named Entity Recognition, Part-Of-Speech Tagging
Published	2018-10-29
URL	http://arxiv.org/abs/1810.12443v1
PDF	http://arxiv.org/pdf/1810.12443v1.pdf
PWC	https://paperswithcode.com/paper/learning-better-internal-structure-of-words
Repo
Framework

Cell Selection with Deep Reinforcement Learning in Sparse Mobile Crowdsensing


Title	Cell Selection with Deep Reinforcement Learning in Sparse Mobile Crowdsensing
Authors	Leye Wang, Wenbin Liu, Daqing Zhang, Yasha Wang, En Wang, Yongjian Yang
Abstract	Sparse Mobile CrowdSensing (MCS) is a novel MCS paradigm where data inference is incorporated into the MCS process for reducing sensing costs while its quality is guaranteed. Since the sensed data from different cells (sub-areas) of the target sensing area will probably lead to diverse levels of inference data quality, cell selection (i.e., choose which cells of the target area to collect sensed data from participants) is a critical issue that will impact the total amount of data that requires to be collected (i.e., data collection costs) for ensuring a certain level of quality. To address this issue, this paper proposes a Deep Reinforcement learning based Cell selection mechanism for Sparse MCS, called DR-Cell. First, we properly model the key concepts in reinforcement learning including state, action, and reward, and then propose to use a deep recurrent Q-network for learning the Q-function that can help decide which cell is a better choice under a certain state during cell selection. Furthermore, we leverage the transfer learning techniques to reduce the amount of data required for training the Q-function if there are multiple correlated MCS tasks that need to be conducted in the same target area. Experiments on various real-life sensing datasets verify the effectiveness of DR-Cell over the state-of-the-art cell selection mechanisms in Sparse MCS by reducing up to 15% of sensed cells with the same data inference quality guarantee.
Tasks	Transfer Learning
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07047v2
PDF	http://arxiv.org/pdf/1804.07047v2.pdf
PWC	https://paperswithcode.com/paper/cell-selection-with-deep-reinforcement
Repo
Framework

Tuning metaheuristics by sequential optimization of regression models


Title	Tuning metaheuristics by sequential optimization of regression models
Authors	Áthila R. Trindade, Felipe Campelo
Abstract	Tuning parameters is an important step for the application of metaheuristics to problem classes of interest. In this work we present a tuning framework based on the sequential optimization of perturbed regression models. Besides providing algorithm configurations with good expected performance, the proposed methodology can also provide insights on the relevance of each parameter and their interactions, as well as models of expected algorithm performance for a given problem class, conditional on the parameter values. A test case is presented for the tuning of six parameters of a decomposition-based multiobjective optimization algorithm, in which an instantiation of the proposed framework is compared against the results obtained by the most recent version the Iterated Racing (Irace) procedure. The results suggest that the proposed approach returns solutions that are as good as those of Irace in terms of mean performance, with the advantage of providing more information on the relevance and effect of each parameter on the expected performance of the algorithm.
Tasks	Multiobjective Optimization
Published	2018-09-11
URL	http://arxiv.org/abs/1809.03646v2
PDF	http://arxiv.org/pdf/1809.03646v2.pdf
PWC	https://paperswithcode.com/paper/tuning-metaheuristics-by-sequential
Repo
Framework

Non-convex non-local flows for saliency detection


Title	Non-convex non-local flows for saliency detection
Authors	Iván Ramírez, Gonzalo Galiano, Emanuele Schiavi
Abstract	We propose and numerically solve a new variational model for automatic saliency detection in digital images. Using a non-local framework we consider a family of edge preserving functions combined with a new quadratic saliency detection term. Such term defines a constrained bilateral obstacle problem for image classification driven by p-Laplacian operators, including the so-called hyper-Laplacian case (0 < p < 1). The related non-convex non-local reactive flows are then considered and applied for glioblastoma segmentation in magnetic resonance fluid-attenuated inversion recovery (MRI-Flair) images. A fast convolutional kernel based approximated solution is computed. The numerical experiments show how the non-convexity related to the hyperLaplacian operators provides monotonically better results in terms of the standard metrics.
Tasks	Image Classification, Saliency Detection
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09408v1
PDF	http://arxiv.org/pdf/1805.09408v1.pdf
PWC	https://paperswithcode.com/paper/non-convex-non-local-flows-for-saliency
Repo
Framework

Improved Complexities of Conditional Gradient-Type Methods with Applications to Robust Matrix Recovery Problems


Title	Improved Complexities of Conditional Gradient-Type Methods with Applications to Robust Matrix Recovery Problems
Authors	Dan Garber, Shoham Sabach, Atara Kaplan
Abstract	Motivated by robust matrix recovery problems such as Robust Principal Component Analysis, we consider a general optimization problem of minimizing a smooth and strongly convex loss function applied to the sum of two blocks of variables, where each block of variables is constrained or regularized individually. We study a Conditional Gradient-Type method which is able to leverage the special structure of the problem to obtain faster convergence rates than those attainable via standard methods, under a variety of assumptions. In particular, our method is appealing for matrix problems in which one of the blocks corresponds to a low-rank matrix since it avoids prohibitive full-rank singular value decompositions required by most standard methods. While our initial motivation comes from problems which originated in statistics, our analysis does not impose any statistical assumptions on the data.
Tasks
Published	2018-02-15
URL	https://arxiv.org/abs/1802.05581v3
PDF	https://arxiv.org/pdf/1802.05581v3.pdf
PWC	https://paperswithcode.com/paper/fast-generalized-conditional-gradient-method
Repo
Framework

The Data Science of Hollywood: Using Emotional Arcs of Movies to Drive Business Model Innovation in Entertainment Industries


Title	The Data Science of Hollywood: Using Emotional Arcs of Movies to Drive Business Model Innovation in Entertainment Industries
Authors	Marco Del Vecchio, Alexander Kharlamov, Glenn Parry, Ganna Pogrebna
Abstract	Much of business literature addresses the issues of consumer-centric design: how can businesses design customized services and products which accurately reflect consumer preferences? This paper uses data science natural language processing methodology to explore whether and to what extent emotions shape consumer preferences for media and entertainment content. Using a unique filtered dataset of 6,174 movie scripts, we generate a mapping of screen content to capture the emotional trajectory of each motion picture. We then combine the obtained mappings into clusters which represent groupings of consumer emotional journeys. These clusters are used to predict overall success parameters of the movies including box office revenues, viewer satisfaction levels (captured by IMDb ratings), awards, as well as the number of viewers’ and critics’ reviews. We find that like books all movie stories are dominated by 6 basic shapes. The highest box offices are associated with the Man in a Hole shape which is characterized by an emotional fall followed by an emotional rise. This shape results in financially successful movies irrespective of genre and production budget. Yet, Man in a Hole succeeds not because it produces most “liked” movies but because it generates most “talked about” movies. Interestingly, a carefully chosen combination of production budget and genre may produce a financially successful movie with any emotional shape. Implications of this analysis for generating on-demand content and for driving business model innovation in entertainment industries are discussed.
Tasks
Published	2018-07-06
URL	http://arxiv.org/abs/1807.02221v2
PDF	http://arxiv.org/pdf/1807.02221v2.pdf
PWC	https://paperswithcode.com/paper/the-data-science-of-hollywood-using-emotional
Repo
Framework

Predicting the Semantic Textual Similarity with Siamese CNN and LSTM


Title	Predicting the Semantic Textual Similarity with Siamese CNN and LSTM
Authors	Elvys Linhares Pontes, Stéphane Huet, Andréa Carneiro Linhares, Juan-Manuel Torres-Moreno
Abstract	Semantic Textual Similarity (STS) is the basis of many applications in Natural Language Processing (NLP). Our system combines convolution and recurrent neural networks to measure the semantic similarity of sentences. It uses a convolution network to take account of the local context of words and an LSTM to consider the global context of sentences. This combination of networks helps to preserve the relevant information of sentences and improves the calculation of the similarity between sentences. Our model has achieved good results and is competitive with the best state-of-the-art systems.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2018-10-24
URL	http://arxiv.org/abs/1810.10641v1
PDF	http://arxiv.org/pdf/1810.10641v1.pdf
PWC	https://paperswithcode.com/paper/predicting-the-semantic-textual-similarity
Repo
Framework

Fully Understanding the Hashing Trick


Title	Fully Understanding the Hashing Trick
Authors	Casper Benjamin Freksen, Lior Kamma, Kasper Green Larsen
Abstract	Feature hashing, also known as {\em the hashing trick}, introduced by Weinberger et al. (2009), is one of the key techniques used in scaling-up machine learning algorithms. Loosely speaking, feature hashing uses a random sparse projection matrix $A : \mathbb{R}^n \to \mathbb{R}^m$ (where $m \ll n$) in order to reduce the dimension of the data from $n$ to $m$ while approximately preserving the Euclidean norm. Every column of $A$ contains exactly one non-zero entry, equals to either $-1$ or $1$. Weinberger et al. showed tail bounds on $\Ax_2^2$. Specifically they showed that for every $\varepsilon, \delta$, if $\x_{\infty} / \x_2$ is sufficiently small, and $m$ is sufficiently large, then $$\Pr[ ; ;\Ax_2^2 - \x_2^2; < \varepsilon \x_2^2 ;] \ge 1 - \delta ;.$$ These bounds were later extended by Dasgupta \etal (2010) and most recently refined by Dahlgaard et al. (2017), however, the true nature of the performance of this key technique, and specifically the correct tradeoff between the pivotal parameters $\x_{\infty} / \x_2, m, \varepsilon, \delta$ remained an open question. We settle this question by giving tight asymptotic bounds on the exact tradeoff between the central parameters, thus providing a complete understanding of the performance of feature hashing. We complement the asymptotic bound with empirical data, which shows that the constants “hiding” in the asymptotic notation are, in fact, very close to $1$, thus further illustrating the tightness of the presented bounds in practice.
Tasks
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08539v1
PDF	http://arxiv.org/pdf/1805.08539v1.pdf
PWC	https://paperswithcode.com/paper/fully-understanding-the-hashing-trick
Repo
Framework

WISER: A Semantic Approach for Expert Finding in Academia based on Entity Linking


Title	WISER: A Semantic Approach for Expert Finding in Academia based on Entity Linking
Authors	Paolo Cifariello, Paolo Ferragina, Marco Ponza
Abstract	We present WISER, a new semantic search engine for expert finding in academia. Our system is unsupervised and it jointly combines classical language modeling techniques, based on text evidences, with the Wikipedia Knowledge Graph, via entity linking. WISER indexes each academic author through a novel profiling technique which models her expertise with a small, labeled and weighted graph drawn from Wikipedia. Nodes in this graph are the Wikipedia entities mentioned in the author’s publications, whereas the weighted edges express the semantic relatedness among these entities computed via textual and graph-based relatedness functions. Every node is also labeled with a relevance score which models the pertinence of the corresponding entity to author’s expertise, and is computed by means of a proper random-walk calculation over that graph; and with a latent vector representation which is learned via entity and other kinds of structural embeddings derived from Wikipedia. At query time, experts are retrieved by combining classic document-centric approaches, which exploit the occurrences of query terms in the author’s documents, with a novel set of profile-centric scoring strategies, which compute the semantic relatedness between the author’s expertise and the query topic via the above graph-based profiles. The effectiveness of our system is established over a large-scale experimental test on a standard dataset for this task. We show that WISER achieves better performance than all the other competitors, thus proving the effectiveness of modelling author’s profile via our “semantic” graph of entities. Finally, we comment on the use of WISER for indexing and profiling the whole research community within the University of Pisa, and its application to technology transfer in our University.
Tasks	Entity Linking, Language Modelling
Published	2018-05-10
URL	https://arxiv.org/abs/1805.03947v2
PDF	https://arxiv.org/pdf/1805.03947v2.pdf
PWC	https://paperswithcode.com/paper/wiser-a-semantic-approach-for-expert-finding
Repo
Framework

3D Human Action Recognition with Siamese-LSTM Based Deep Metric Learning


Title	3D Human Action Recognition with Siamese-LSTM Based Deep Metric Learning
Authors	Seyma Yucer, Yusuf Sinan Akgul
Abstract	This paper proposes a new 3D Human Action Recognition system as a two-phase system: (1) Deep Metric Learning Module which learns a similarity metric between two 3D joint sequences using Siamese-LSTM networks; (2) A Multiclass Classification Module that uses the output of the first module to produce the final recognition output. This model has several advantages: the first module is trained with a larger set of data because it uses many combinations of sequence pairs.Our deep metric learning module can also be trained independently of the datasets, which makes our system modular and generalizable. We tested the proposed system on standard and newly introduced datasets that showed us that initial results are promising. We will continue developing this system by adding more sophisticated LSTM blocks and by cross-training between different datasets.
Tasks	3D Human Action Recognition, Metric Learning, Temporal Action Localization
Published	2018-07-05
URL	http://arxiv.org/abs/1807.02131v1
PDF	http://arxiv.org/pdf/1807.02131v1.pdf
PWC	https://paperswithcode.com/paper/3d-human-action-recognition-with-siamese-lstm
Repo
Framework