May 5, 2019

2867 words 14 mins read

Paper Group ANR 499

Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing. A Data-Driven Approach for Semantic Role Labeling from Induced Grammar Structures in Language. Learning to Reason With Adaptive Computation. Drug response prediction by inferring pathway-response associations with Kernelized Bayesian Matrix Factorization. ABtree: An Algorithm fo …

Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing


Title	Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing
Authors	Shashi Narayan, Siva Reddy, Shay B. Cohen
Abstract	One of the limitations of semantic parsing approaches to open-domain question answering is the lexicosyntactic gap between natural language questions and knowledge base entries – there are many ways to ask a question, all with the same answer. In this paper we propose to bridge this gap by generating paraphrases of the input question with the goal that at least one of them will be correctly mapped to a knowledge-base query. We introduce a novel grammar model for paraphrase generation that does not require any sentence-aligned paraphrase corpus. Our key idea is to leverage the flexibility and scalability of latent-variable probabilistic context-free grammars to sample paraphrases. We do an extrinsic evaluation of our paraphrases by plugging them into a semantic parser for Freebase. Our evaluation experiments on the WebQuestions benchmark dataset show that the performance of the semantic parser significantly improves over strong baselines.
Tasks	Open-Domain Question Answering, Paraphrase Generation, Question Answering, Semantic Parsing
Published	2016-01-22
URL	http://arxiv.org/abs/1601.06068v2
PDF	http://arxiv.org/pdf/1601.06068v2.pdf
PWC	https://paperswithcode.com/paper/paraphrase-generation-from-latent-variable
Repo
Framework

A Data-Driven Approach for Semantic Role Labeling from Induced Grammar Structures in Language


Title	A Data-Driven Approach for Semantic Role Labeling from Induced Grammar Structures in Language
Authors	Vivek Datla, David Lin, Max Louwerse, Abhinav Vishnu
Abstract	Semantic roles play an important role in extracting knowledge from text. Current unsupervised approaches utilize features from grammar structures, to induce semantic roles. The dependence on these grammars, however, makes it difficult to adapt to noisy and new languages. In this paper we develop a data-driven approach to identifying semantic roles, the approach is entirely unsupervised up to the point where rules need to be learned to identify the position the semantic role occurs. Specifically we develop a modified-ADIOS algorithm based on ADIOS Solan et al. (2005) to learn grammar structures, and use these grammar structures to learn the rules for identifying the semantic roles based on the context in which the grammar structures appeared. The results obtained are comparable with the current state-of-art models that are inherently dependent on human annotated data.
Tasks	Semantic Role Labeling
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06274v1
PDF	http://arxiv.org/pdf/1606.06274v1.pdf
PWC	https://paperswithcode.com/paper/a-data-driven-approach-for-semantic-role
Repo
Framework

Learning to Reason With Adaptive Computation


Title	Learning to Reason With Adaptive Computation
Authors	Mark Neumann, Pontus Stenetorp, Sebastian Riedel
Abstract	Multi-hop inference is necessary for machine learning systems to successfully solve tasks such as Recognising Textual Entailment and Machine Reading. In this work, we demonstrate the effectiveness of adaptive computation for learning the number of inference steps required for examples of different complexity and that learning the correct number of inference steps is difficult. We introduce the first model involving Adaptive Computation Time which provides a small performance benefit on top of a similar model without an adaptive component as well as enabling considerable insight into the reasoning process of the model.
Tasks	Natural Language Inference, Reading Comprehension
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07647v2
PDF	http://arxiv.org/pdf/1610.07647v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-reason-with-adaptive-computation
Repo
Framework

Drug response prediction by inferring pathway-response associations with Kernelized Bayesian Matrix Factorization


Title	Drug response prediction by inferring pathway-response associations with Kernelized Bayesian Matrix Factorization
Authors	Muhammad Ammad-ud-din, Suleiman A. Khan, Disha Malani, Astrid Murumägi, Olli Kallioniemi, Tero Aittokallio, Samuel Kaski
Abstract	A key goal of computational personalized medicine is to systematically utilize genomic and other molecular features of samples to predict drug responses for a previously unseen sample. Such predictions are valuable for developing hypotheses for selecting therapies tailored for individual patients. This is especially valuable in oncology, where molecular and genetic heterogeneity of the cells has a major impact on the response. However, the prediction task is extremely challenging, raising the need for methods that can effectively model and predict drug responses. In this study, we propose a novel formulation of multi-task matrix factorization that allows selective data integration for predicting drug responses. To solve the modeling task, we extend the state-of-the-art kernelized Bayesian matrix factorization (KBMF) method with component-wise multiple kernel learning. In addition, our approach exploits the known pathway information in a novel and biologically meaningful fashion to learn the drug response associations. Our method quantitatively outperforms the state of the art on predicting drug responses in two publicly available cancer data sets as well as on a synthetic data set. In addition, we validated our model predictions with lab experiments using an in-house cancer cell line panel. We finally show the practical applicability of the proposed method by utilizing prior knowledge to infer pathway-drug response associations, opening up the opportunity for elucidating drug action mechanisms. We demonstrate that pathway-response associations can be learned by the proposed model for the well known EGFR and MEK inhibitors.
Tasks
Published	2016-06-11
URL	http://arxiv.org/abs/1606.03623v1
PDF	http://arxiv.org/pdf/1606.03623v1.pdf
PWC	https://paperswithcode.com/paper/drug-response-prediction-by-inferring-pathway
Repo
Framework

ABtree: An Algorithm for Subgroup-Based Treatment Assignment


Title	ABtree: An Algorithm for Subgroup-Based Treatment Assignment
Authors	Derek Feng, Xiaofei Wang
Abstract	Given two possible treatments, there may exist subgroups who benefit greater from one treatment than the other. This problem is relevant to the field of marketing, where treatments may correspond to different ways of selling a product. It is similarly relevant to the field of public policy, where treatments may correspond to specific government programs. And finally, personalized medicine is a field wholly devoted to understanding which subgroups of individuals will benefit from particular medical treatments. We present a computationally fast tree-based method, ABtree, for treatment effect differentiation. Unlike other methods, ABtree specifically produces decision rules for optimal treatment assignment on a per-individual basis. The treatment choices are selected for maximizing the overall occurrence of a desired binary outcome, conditional on a set of covariates. In this poster, we present the methodology on tree growth and pruning, and show performance results when applied to simulated data as well as real data.
Tasks
Published	2016-05-13
URL	http://arxiv.org/abs/1605.04262v1
PDF	http://arxiv.org/pdf/1605.04262v1.pdf
PWC	https://paperswithcode.com/paper/abtree-an-algorithm-for-subgroup-based
Repo
Framework

Deep Function Machines: Generalized Neural Networks for Topological Layer Expression


Title	Deep Function Machines: Generalized Neural Networks for Topological Layer Expression
Authors	William H. Guss
Abstract	In this paper we propose a generalization of deep neural networks called deep function machines (DFMs). DFMs act on vector spaces of arbitrary (possibly infinite) dimension and we show that a family of DFMs are invariant to the dimension of input data; that is, the parameterization of the model does not directly hinge on the quality of the input (eg. high resolution images). Using this generalization we provide a new theory of universal approximation of bounded non-linear operators between function spaces. We then suggest that DFMs provide an expressive framework for designing new neural network layer types with topological considerations in mind. Finally, we introduce a novel architecture, RippLeNet, for resolution invariant computer vision, which empirically achieves state of the art invariance.
Tasks
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04799v2
PDF	http://arxiv.org/pdf/1612.04799v2.pdf
PWC	https://paperswithcode.com/paper/deep-function-machines-generalized-neural
Repo
Framework

Online Segment to Segment Neural Transduction


Title	Online Segment to Segment Neural Transduction
Authors	Lei Yu, Jan Buys, Phil Blunsom
Abstract	We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits exact polynomial marginalization of the latent segmentation during training, and during decoding beam search is employed to find the best alignment path together with the predicted output sequence. Our model tackles the bottleneck of vanilla encoder-decoders that have to read and memorize the entire input sequence in their fixed-length hidden states before producing any output. It is different from previous attentive models in that, instead of treating the attention weights as output of a deterministic function, our model assigns attention weights to a sequential latent variable which can be marginalized out and permits online generation. Experiments on abstractive sentence summarization and morphological inflection show significant performance gains over the baseline encoder-decoders.
Tasks	Abstractive Sentence Summarization, Morphological Inflection
Published	2016-09-26
URL	http://arxiv.org/abs/1609.08194v1
PDF	http://arxiv.org/pdf/1609.08194v1.pdf
PWC	https://paperswithcode.com/paper/online-segment-to-segment-neural-transduction
Repo
Framework

Optimal Black-Box Reductions Between Optimization Objectives


Title	Optimal Black-Box Reductions Between Optimization Objectives
Authors	Zeyuan Allen-Zhu, Elad Hazan
Abstract	The diverse world of machine learning applications has given rise to a plethora of algorithms and optimization methods, finely tuned to the specific regression or classification task at hand. We reduce the complexity of algorithm design for machine learning by reductions: we develop reductions that take a method developed for one setting and apply it to the entire spectrum of smoothness and strong-convexity in applications. Furthermore, unlike existing results, our new reductions are OPTIMAL and more PRACTICAL. We show how these new reductions give rise to new and faster running times on training linear classifiers for various families of loss functions, and conclude with experiments showing their successes also in practice.
Tasks
Published	2016-03-17
URL	http://arxiv.org/abs/1603.05642v3
PDF	http://arxiv.org/pdf/1603.05642v3.pdf
PWC	https://paperswithcode.com/paper/optimal-black-box-reductions-between
Repo
Framework

A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding


Title	A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding
Authors	Renqiao Zhang, Jiajun Wu, Chengkai Zhang, William T. Freeman, Joshua B. Tenenbaum
Abstract	Humans demonstrate remarkable abilities to predict physical events in complex scenes. Two classes of models for physical scene understanding have recently been proposed: “Intuitive Physics Engines”, or IPEs, which posit that people make predictions by running approximate probabilistic simulations in causal mental models similar in nature to video-game physics engines, and memory-based models, which make judgments based on analogies to stored experiences of previously encountered scenes and physical outcomes. Versions of the latter have recently been instantiated in convolutional neural network (CNN) architectures. Here we report four experiments that, to our knowledge, are the first rigorous comparisons of simulation-based and CNN-based models, where both approaches are concretely instantiated in algorithms that can run on raw image inputs and produce as outputs physical judgments such as whether a stack of blocks will fall. Both approaches can achieve super-human accuracy levels and can quantitatively predict human judgments to a similar degree, but only the simulation-based models generalize to novel situations in ways that people do, and are qualitatively consistent with systematic perceptual illusions and judgment asymmetries that people show.
Tasks	Scene Understanding
Published	2016-05-04
URL	http://arxiv.org/abs/1605.01138v2
PDF	http://arxiv.org/pdf/1605.01138v2.pdf
PWC	https://paperswithcode.com/paper/a-comparative-evaluation-of-approximate
Repo
Framework

Building Energy Load Forecasting using Deep Neural Networks


Title	Building Energy Load Forecasting using Deep Neural Networks
Authors	Daniel L. Marino, Kasun Amarasinghe, Milos Manic
Abstract	Ensuring sustainability demands more efficient energy management with minimized energy wastage. Therefore, the power grid of the future should provide an unprecedented level of flexibility in energy management. To that end, intelligent decision making requires accurate predictions of future energy demand/load, both at aggregate and individual site level. Thus, energy load forecasting have received increased attention in the recent past, however has proven to be a difficult problem. This paper presents a novel energy load forecasting methodology based on Deep Neural Networks, specifically Long Short Term Memory (LSTM) algorithms. The presented work investigates two variants of the LSTM: 1) standard LSTM and 2) LSTM-based Sequence to Sequence (S2S) architecture. Both methods were implemented on a benchmark data set of electricity consumption data from one residential customer. Both architectures where trained and tested on one hour and one-minute time-step resolution datasets. Experimental results showed that the standard LSTM failed at one-minute resolution data while performing well in one-hour resolution data. It was shown that S2S architecture performed well on both datasets. Further, it was shown that the presented methods produced comparable results with the other deep learning methods for energy forecasting in literature.
Tasks	Decision Making, Load Forecasting
Published	2016-10-29
URL	http://arxiv.org/abs/1610.09460v1
PDF	http://arxiv.org/pdf/1610.09460v1.pdf
PWC	https://paperswithcode.com/paper/building-energy-load-forecasting-using-deep
Repo
Framework

Hypergraph Modelling for Geometric Model Fitting


Title	Hypergraph Modelling for Geometric Model Fitting
Authors	Guobao Xiao, Hanzi Wang, Taotao Lai, David Suter
Abstract	In this paper, we propose a novel hypergraph based method (called HF) to fit and segment multi-structural data. The proposed HF formulates the geometric model fitting problem as a hypergraph partition problem based on a novel hypergraph model. In the hypergraph model, vertices represent data points and hyperedges denote model hypotheses. The hypergraph, with large and “data-determined” degrees of hyperedges, can express the complex relationships between model hypotheses and data points. In addition, we develop a robust hypergraph partition algorithm to detect sub-hypergraphs for model fitting. HF can effectively and efficiently estimate the number of, and the parameters of, model instances in multi-structural data heavily corrupted with outliers simultaneously. Experimental results show the advantages of the proposed method over previous methods on both synthetic data and real images.
Tasks
Published	2016-07-11
URL	http://arxiv.org/abs/1607.02829v1
PDF	http://arxiv.org/pdf/1607.02829v1.pdf
PWC	https://paperswithcode.com/paper/hypergraph-modelling-for-geometric-model
Repo
Framework

Lasso estimation for GEFCom2014 probabilistic electric load forecasting


Title	Lasso estimation for GEFCom2014 probabilistic electric load forecasting
Authors	Florian Ziel, Bidong Liu
Abstract	We present a methodology for probabilistic load forecasting that is based on lasso (least absolute shrinkage and selection operator) estimation. The model considered can be regarded as a bivariate time-varying threshold autoregressive(AR) process for the hourly electric load and temperature. The joint modeling approach incorporates the temperature effects directly, and reflects daily, weekly, and annual seasonal patterns and public holiday effects. We provide two empirical studies, one based on the probabilistic load forecasting track of the Global Energy Forecasting Competition 2014 (GEFCom2014-L), and the other based on another recent probabilistic load forecasting competition that follows a setup similar to that of GEFCom2014-L. In both empirical case studies, the proposed methodology outperforms two multiple linear regression based benchmarks from among the top eight entries to GEFCom2014-L.
Tasks	Load Forecasting
Published	2016-03-04
URL	http://arxiv.org/abs/1603.01376v1
PDF	http://arxiv.org/pdf/1603.01376v1.pdf
PWC	https://paperswithcode.com/paper/lasso-estimation-for-gefcom2014-probabilistic
Repo
Framework

Union is strength in lossy image compression


Title	Union is strength in lossy image compression
Authors	Mario Mastriani
Abstract	In this work, we present a comparison between different techniques of image compression. First, the image is divided in blocks which are organized according to a certain scan. Later, several compression techniques are applied, combined or alone. Such techniques are: wavelets (Haar’s basis), Karhunen-Loeve Transform, etc. Simulations show that the combined versions are the best, with minor Mean Squared Error (MSE), and higher Peak Signal to Noise Ratio (PSNR) and better image quality, even in the presence of noise.
Tasks	Image Compression
Published	2016-07-31
URL	http://arxiv.org/abs/1608.00268v1
PDF	http://arxiv.org/pdf/1608.00268v1.pdf
PWC	https://paperswithcode.com/paper/union-is-strength-in-lossy-image-compression
Repo
Framework

Object Boundary Guided Semantic Segmentation


Title	Object Boundary Guided Semantic Segmentation
Authors	Qin Huang, Chunyang Xia, Wenchao Zheng, Yuhang Song, Hao Xu, C. -C. Jay Kuo
Abstract	Semantic segmentation is critical to image content understanding and object localization. Recent development in fully-convolutional neural network (FCN) has enabled accurate pixel-level labeling. One issue in previous works is that the FCN based method does not exploit the object boundary information to delineate segmentation details since the object boundary label is ignored in the network training. To tackle this problem, we introduce a double branch fully convolutional neural network, which separates the learning of the desirable semantic class labeling with mask-level object proposals guided by relabeled boundaries. This network, called object boundary guided FCN (OBG-FCN), is able to integrate the distinct properties of object shape and class features elegantly in a fully convolutional way with a designed masking architecture. We conduct experiments on the PASCAL VOC segmentation benchmark, and show that the end-to-end trainable OBG-FCN system offers great improvement in optimizing the target semantic segmentation quality.
Tasks	Object Localization, Semantic Segmentation
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09742v4
PDF	http://arxiv.org/pdf/1603.09742v4.pdf
PWC	https://paperswithcode.com/paper/object-boundary-guided-semantic-segmentation
Repo
Framework

Estimating the Size of a Large Network and its Communities from a Random Sample


Title	Estimating the Size of a Large Network and its Communities from a Random Sample
Authors	Lin Chen, Amin Karbasi, Forrest W. Crawford
Abstract	Most real-world networks are too large to be measured or studied directly and there is substantial interest in estimating global network properties from smaller sub-samples. One of the most important global properties is the number of vertices/nodes in the network. Estimating the number of vertices in a large network is a major challenge in computer science, epidemiology, demography, and intelligence analysis. In this paper we consider a population random graph G = (V;E) from the stochastic block model (SBM) with K communities/blocks. A sample is obtained by randomly choosing a subset W and letting G(W) be the induced subgraph in G of the vertices in W. In addition to G(W), we observe the total degree of each sampled vertex and its block membership. Given this partial information, we propose an efficient PopULation Size Estimation algorithm, called PULSE, that correctly estimates the size of the whole population as well as the size of each community. To support our theoretical analysis, we perform an exhaustive set of experiments to study the effects of sample size, K, and SBM model parameters on the accuracy of the estimates. The experimental results also demonstrate that PULSE significantly outperforms a widely-used method called the network scale-up estimator in a wide variety of scenarios. We conclude with extensions and directions for future work.
Tasks	Epidemiology
Published	2016-10-26
URL	http://arxiv.org/abs/1610.08473v1
PDF	http://arxiv.org/pdf/1610.08473v1.pdf
PWC	https://paperswithcode.com/paper/estimating-the-size-of-a-large-network-and
Repo
Framework