October 19, 2019

3200 words 16 mins read

Paper Group ANR 165

Region Growing Curriculum Generation for Reinforcement Learning. Diverse M-Best Solutions by Dynamic Programming. Computer-Assisted Text Analysis for Social Science: Topic Models and Beyond. DeepLens: Shallow Depth Of Field From A Single Image. A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset. Towards End-to-e …

Region Growing Curriculum Generation for Reinforcement Learning


Title	Region Growing Curriculum Generation for Reinforcement Learning
Authors	Artem Molchanov, Karol Hausman, Stan Birchfield, Gaurav Sukhatme
Abstract	Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the sparsity of rewards in such tasks, applying reinforcement learning in these scenarios can be challenging. Common approaches for tackling this problem include reward engineering with auxiliary rewards, requiring domain-specific knowledge or changing the objective. In this work, we introduce a method based on region-growing that allows learning in an environment with any pair of initial and goal states. Our algorithm first learns how to move between nearby states and then increases the difficulty of the start-goal transitions as the agent’s performance improves. This approach creates an efficient curriculum for learning the objective behavior of reaching any goal from any initial state. In addition, we describe a method to adaptively adjust expansion of the growing region that allows automatic adjustment of the key exploration hyperparameter to environments with different requirements. We evaluate our approach on a set of simulated navigation and manipulation tasks, where we demonstrate that our algorithm can efficiently learn a policy in the presence of sparse rewards.
Tasks
Published	2018-07-04
URL	http://arxiv.org/abs/1807.01425v1
PDF	http://arxiv.org/pdf/1807.01425v1.pdf
PWC	https://paperswithcode.com/paper/region-growing-curriculum-generation-for
Repo
Framework

Diverse M-Best Solutions by Dynamic Programming


Title	Diverse M-Best Solutions by Dynamic Programming
Authors	Carsten Haubold, Virginie Uhlmann, Michael Unser, Fred A. Hamprecht
Abstract	Many computer vision pipelines involve dynamic programming primitives such as finding a shortest path or the minimum energy solution in a tree-shaped probabilistic graphical model. In such cases, extracting not merely the best, but the set of M-best solutions is useful to generate a rich collection of candidate proposals that can be used in downstream processing. In this work, we show how M-best solutions of tree-shaped graphical models can be obtained by dynamic programming on a special graph with M layers. The proposed multi-layer concept is optimal for searching M-best solutions, and so flexible that it can also approximate M-best diverse solutions. We illustrate the usefulness with applications to object detection, panorama stitching and centerline extraction. Note: We have observed that an assumption in section 4 of our paper is not always fulfilled, see the attached corrigendum for details.
Tasks	Object Detection
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05748v1
PDF	http://arxiv.org/pdf/1803.05748v1.pdf
PWC	https://paperswithcode.com/paper/diverse-m-best-solutions-by-dynamic
Repo
Framework


Title	Computer-Assisted Text Analysis for Social Science: Topic Models and Beyond
Authors	Ryan Wesslen
Abstract	Topic models are a family of statistical-based algorithms to summarize, explore and index large collections of text documents. After a decade of research led by computer scientists, topic models have spread to social science as a new generation of data-driven social scientists have searched for tools to explore large collections of unstructured text. Recently, social scientists have contributed to topic model literature with developments in causal inference and tools for handling the problem of multi-modality. In this paper, I provide a literature review on the evolution of topic modeling including extensions for document covariates, methods for evaluation and interpretation, and advances in interactive visualizations along with each aspect’s relevance and application for social science research.
Tasks	Causal Inference, Topic Models
Published	2018-03-29
URL	http://arxiv.org/abs/1803.11045v2
PDF	http://arxiv.org/pdf/1803.11045v2.pdf
PWC	https://paperswithcode.com/paper/computer-assisted-text-analysis-for-social
Repo
Framework

DeepLens: Shallow Depth Of Field From A Single Image


Title	DeepLens: Shallow Depth Of Field From A Single Image
Authors	Lijun Wang, Xiaohui Shen, Jianming Zhang, Oliver Wang, Zhe Lin, Chih-Yao Hsieh, Sarah Kong, Huchuan Lu
Abstract	We aim to generate high resolution shallow depth-of-field (DoF) images from a single all-in-focus image with controllable focal distance and aperture size. To achieve this, we propose a novel neural network model comprised of a depth prediction module, a lens blur module, and a guided upsampling module. All modules are differentiable and are learned from data. To train our depth prediction module, we collect a dataset of 2462 RGB-D images captured by mobile phones with a dual-lens camera, and use existing segmentation datasets to improve border prediction. We further leverage a synthetic dataset with known depth to supervise the lens blur and guided upsampling modules. The effectiveness of our system and training strategies are verified in the experiments. Our method can generate high-quality shallow DoF images at high resolution, and produces significantly fewer artifacts than the baselines and existing solutions for single image shallow DoF synthesis. Compared with the iPhone portrait mode, which is a state-of-the-art shallow DoF solution based on a dual-lens depth camera, our method generates comparable results, while allowing for greater flexibility to choose focal points and aperture size, and is not limited to one capture setup.
Tasks	Depth Estimation
Published	2018-10-18
URL	http://arxiv.org/abs/1810.08100v1
PDF	http://arxiv.org/pdf/1810.08100v1.pdf
PWC	https://paperswithcode.com/paper/deeplens-shallow-depth-of-field-from-a-single
Repo
Framework

A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset


Title	A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset
Authors	Michael Boratko, Harshit Padigela, Divyendra Mikkilineni, Pritish Yuvraj, Rajarshi Das, Andrew McCallum, Maria Chang, Achille Fokoue-Nkoutche, Pavan Kapanipathi, Nicholas Mattei, Ryan Musa, Kartik Talamadupula, Michael Witbrock
Abstract	The recent work of Clark et al. introduces the AI2 Reasoning Challenge (ARC) and the associated ARC dataset that partitions open domain, complex science questions into an Easy Set and a Challenge Set. That paper includes an analysis of 100 questions with respect to the types of knowledge and reasoning required to answer them; however, it does not include clear definitions of these types, nor does it offer information about the quality of the labels. We propose a comprehensive set of definitions of knowledge and reasoning types necessary for answering the questions in the ARC dataset. Using ten annotators and a sophisticated annotation interface, we analyze the distribution of labels across the Challenge Set and statistics related to them. Additionally, we demonstrate that although naive information retrieval methods return sentences that are irrelevant to answering the query, sufficient supporting text is often present in the (ARC) corpus. Evaluating with human-selected relevant sentences improves the performance of a neural machine comprehension model by 42 points.
Tasks	Information Retrieval, Reading Comprehension
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00358v2
PDF	http://arxiv.org/pdf/1806.00358v2.pdf
PWC	https://paperswithcode.com/paper/a-systematic-classification-of-knowledge
Repo
Framework

Towards End-to-end Automatic Code-Switching Speech Recognition


Title	Towards End-to-end Automatic Code-Switching Speech Recognition
Authors	Genta Indra Winata, Andrea Madotto, Chien-Sheng Wu, Pascale Fung
Abstract	Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as “one” in English and “w`an” in Chinese. We propose a CTC-based end-to-end automatic speech recognition model for intra-sentential English-Mandarin code-switching. The model is trained by joint training on monolingual datasets, and fine-tuning with the mixed-language corpus. During the decoding process, we apply a beam search and combine CTC predictions and language model score. The proposed method is effective in leveraging monolingual corpus and detecting language transitions and it improves the CER by 5%.
Tasks	Language Modelling, Speech Recognition
Published	2018-10-30
URL	http://arxiv.org/abs/1810.12620v1
PDF	http://arxiv.org/pdf/1810.12620v1.pdf
PWC	https://paperswithcode.com/paper/towards-end-to-end-automatic-code-switching
Repo
Framework

Scalable Generalized Dynamic Topic Models


Title	Scalable Generalized Dynamic Topic Models
Authors	Patrick Jähnichen, Florian Wenzel, Marius Kloft, Stephan Mandt
Abstract	Dynamic topic models (DTMs) model the evolution of prevalent themes in literature, online media, and other forms of text over time. DTMs assume that word co-occurrence statistics change continuously and therefore impose continuous stochastic process priors on their model parameters. These dynamical priors make inference much harder than in regular topic models, and also limit scalability. In this paper, we present several new results around DTMs. First, we extend the class of tractable priors from Wiener processes to the generic class of Gaussian processes (GPs). This allows us to explore topics that develop smoothly over time, that have a long-term memory or are temporally concentrated (for event detection). Second, we show how to perform scalable approximate inference in these models based on ideas around stochastic variational inference and sparse Gaussian processes. This way we can train a rich family of DTMs to massive data. Our experiments on several large-scale datasets show that our generalized model allows us to find interesting patterns that were not accessible by previous approaches.
Tasks	Gaussian Processes, Topic Models
Published	2018-03-21
URL	http://arxiv.org/abs/1803.07868v1
PDF	http://arxiv.org/pdf/1803.07868v1.pdf
PWC	https://paperswithcode.com/paper/scalable-generalized-dynamic-topic-models
Repo
Framework

Modelling Errors in X-ray Fluoroscopic Imaging Systems Using Photogrammetric Bundle Adjustment With a Data-Driven Self-Calibration Approach


Title	Modelling Errors in X-ray Fluoroscopic Imaging Systems Using Photogrammetric Bundle Adjustment With a Data-Driven Self-Calibration Approach
Authors	Jacky C. K. Chow, Derek Lichti, Kathleen Ang, Gregor Kuntze, Gulshan Sharma, Janet Ronsky
Abstract	X-ray imaging is a fundamental tool of routine clinical diagnosis. Fluoroscopic imaging can further acquire X-ray images at video frame rates, thus enabling non-invasive in-vivo motion studies of joints, gastrointestinal tract, etc. For both the qualitative and quantitative analysis of static and dynamic X-ray images, the data should be free of systematic biases. Besides precise fabrication of hardware, software-based calibration solutions are commonly used for modelling the distortions. In this primary research study, a robust photogrammetric bundle adjustment was used to model the projective geometry of two fluoroscopic X-ray imaging systems. However, instead of relying on an expert photogrammetrist’s knowledge and judgement to decide on a parametric model for describing the systematic errors, a self-tuning data-driven approach is used to model the complex non-linear distortion profile of the sensors. Quality control from the experiment showed that 0.06 mm to 0.09 mm 3D reconstruction accuracy was achievable post-calibration using merely 15 X-ray images. As part of the bundle adjustment, the location of the virtual fluoroscopic system relative to the target field can also be spatially resected with an RMSE between 3.10 mm and 3.31 mm.
Tasks	3D Reconstruction, Calibration
Published	2018-09-29
URL	http://arxiv.org/abs/1810.00138v2
PDF	http://arxiv.org/pdf/1810.00138v2.pdf
PWC	https://paperswithcode.com/paper/modelling-errors-in-x-ray-fluoroscopic
Repo
Framework

Application of Rényi and Tsallis Entropies to Topic Modeling Optimization


Title	Application of Rényi and Tsallis Entropies to Topic Modeling Optimization
Authors	Koltcov Sergei
Abstract	This is full length article (draft version) where problem number of topics in Topic Modeling is discussed. We proposed idea that Renyi and Tsallis entropy can be used for identification of optimal number in large textual collections. We also report results of numerical experiments of Semantic stability for 4 topic models, which shows that semantic stability play very important role in problem topic number. The calculation of Renyi and Tsallis entropy based on thermodynamics approach.
Tasks	Topic Models
Published	2018-02-28
URL	http://arxiv.org/abs/1802.10526v1
PDF	http://arxiv.org/pdf/1802.10526v1.pdf
PWC	https://paperswithcode.com/paper/application-of-renyi-and-tsallis-entropies-to
Repo
Framework

Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures


Title	Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures
Authors	Luke Vilnis, Xiang Li, Shikhar Murty, Andrew McCallum
Abstract	Embedding methods which enforce a partial order or lattice structure over the concept space, such as Order Embeddings (OE) (Vendrov et al., 2016), are a natural way to model transitive relational data (e.g. entailment graphs). However, OE learns a deterministic knowledge base, limiting expressiveness of queries and the ability to use uncertainty for both prediction and learning (e.g. learning from expectations). Probabilistic extensions of OE (Lai and Hockenmaier, 2017) have provided the ability to somewhat calibrate these denotational probabilities while retaining the consistency and inductive bias of ordered models, but lack the ability to model the negative correlations found in real-world knowledge. In this work we show that a broad class of models that assign probability measures to OE can never capture negative correlation, which motivates our construction of a novel box lattice and accompanying probability measure to capture anticorrelation and even disjoint concepts, while still providing the benefits of probabilistic modeling, such as the ability to perform rich joint and conditional queries over arbitrary sets of concepts, and both learning from and predicting calibrated uncertainty. We show improvements over previous approaches in modeling the Flickr and WordNet entailment graphs, and investigate the power of the model.
Tasks	Knowledge Graphs
Published	2018-05-17
URL	http://arxiv.org/abs/1805.06627v1
PDF	http://arxiv.org/pdf/1805.06627v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-embedding-of-knowledge-graphs
Repo
Framework


Title	Attentive cross-modal paratope prediction
Authors	Andreea Deac, Petar Veličković, Pietro Sormanni
Abstract	Antibodies are a critical part of the immune system, having the function of directly neutralising or tagging undesirable objects (the antigens) for future destruction. Being able to predict which amino acids belong to the paratope, the region on the antibody which binds to the antigen, can facilitate antibody design and contribute to the development of personalised medicine. The suitability of deep neural networks has recently been confirmed for this task, with Parapred outperforming all prior physical models. Our contribution is twofold: first, we significantly outperform the computational efficiency of Parapred by leveraging `a trous convolutions and self-attention. Secondly, we implement cross-modal attention by allowing the antibody residues to attend over antigen residues. This leads to new state-of-the-art results on this task, along with insightful interpretations.
Tasks
Published	2018-06-12
URL	http://arxiv.org/abs/1806.04398v1
PDF	http://arxiv.org/pdf/1806.04398v1.pdf
PWC	https://paperswithcode.com/paper/attentive-cross-modal-paratope-prediction
Repo
Framework

The Development of Darwin’s Origin of Species


Title	The Development of Darwin’s Origin of Species
Authors	Jaimie Murdock, Colin Allen, Simon DeDeo
Abstract	From 1837, when he returned to England aboard the $\textit{HMS Beagle}$, to 1860, just after publication of $\textit{The Origin of Species}$, Charles Darwin kept detailed notes of each book he read or wanted to read. His notes and manuscripts provide information about decades of individual scientific practice. Previously, we trained topic models on the full texts of each reading, and applied information-theoretic measures to detect that changes in his reading patterns coincided with the boundaries of his three major intellectual projects in the period 1837-1860. In this new work we apply the reading model to five additional documents, four of them by Darwin: the first edition of $\textit{The Origin of Species}$, two private essays stating intermediate forms of his theory in 1842 and 1844, a third essay of disputed dating, and Alfred Russel Wallace’s essay, which Darwin received in 1858. We address three historical inquiries, previously treated qualitatively: 1) the mythology of “Darwin’s Delay,” that despite completing an extensive draft in 1844, Darwin waited until 1859 to publish $\textit{The Origin of Species}$ due to external pressures; 2) the relationship between Darwin and Wallace’s contemporaneous theories, especially in light of their joint presentation; and 3) dating of the “Outline and Draft” which was rediscovered in 1975 and postulated first as an 1839 draft preceding the Sketch of 1842, then as an interstitial draft between the 1842 and 1844 essays.
Tasks	Topic Models
Published	2018-02-26
URL	http://arxiv.org/abs/1802.09944v1
PDF	http://arxiv.org/pdf/1802.09944v1.pdf
PWC	https://paperswithcode.com/paper/the-development-of-darwins-origin-of-species
Repo
Framework

Deep Semantic Architecture with discriminative feature visualization for neuroimage analysis


Title	Deep Semantic Architecture with discriminative feature visualization for neuroimage analysis
Authors	Arna Ghosh, Fabien dal Maso, Marc Roig, Georgios D Mitsis, Marie-Hélène Boudrias
Abstract	Neuroimaging data analysis often involves \emph{a-priori} selection of data features to study the underlying neural activity. Since this could lead to sub-optimal feature selection and thereby prevent the detection of subtle patterns in neural activity, data-driven methods have recently gained popularity for optimizing neuroimaging data analysis pipelines and thereby, improving our understanding of neural mechanisms. In this context, we developed a deep convolutional architecture that can identify discriminating patterns in neuroimaging data and applied it to electroencephalography (EEG) recordings collected from 25 subjects performing a hand motor task before and after a rest period or a bout of exercise. The deep network was trained to classify subjects into exercise and control groups based on differences in their EEG signals. Subsequently, we developed a novel method termed the cue-combination for Class Activation Map (ccCAM), which enabled us to identify discriminating spatio-temporal features within definite frequency bands (23–33 Hz) and assess the effects of exercise on the brain. Additionally, the proposed architecture allowed the visualization of the differences in the propagation of underlying neural activity across the cortex between the two groups, for the first time in our knowledge. Our results demonstrate the feasibility of using deep network architectures for neuroimaging analysis in different contexts such as, for the identification of robust brain biomarkers to better characterize and potentially treat neurological disorders.
Tasks	EEG, Feature Selection
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11704v2
PDF	http://arxiv.org/pdf/1805.11704v2.pdf
PWC	https://paperswithcode.com/paper/deep-semantic-architecture-with
Repo
Framework

Learning Topic Models by Neighborhood Aggregation


Title	Learning Topic Models by Neighborhood Aggregation
Authors	Ryohei Hisano
Abstract	Topic models are frequently used in machine learning owing to their high interpretability and modular structure. However, extending a topic model to include a supervisory signal, to incorporate pre-trained word embedding vectors and to include a nonlinear output function is not an easy task because one has to resort to a highly intricate approximate inference procedure. The present paper shows that topic modeling with pre-trained word embedding vectors can be viewed as implementing a neighborhood aggregation algorithm where messages are passed through a network defined over words. From the network view of topic models, nodes correspond to words in a document and edges correspond to either a relationship describing co-occurring words in a document or a relationship describing the same word in the corpus. The network view allows us to extend the model to include supervisory signals, incorporate pre-trained word embedding vectors and include a nonlinear output function in a simple manner. In experiments, we show that our approach outperforms the state-of-the-art supervised Latent Dirichlet Allocation implementation in terms of held-out document classification tasks.
Tasks	Document Classification, Topic Models
Published	2018-02-22
URL	https://arxiv.org/abs/1802.08012v6
PDF	https://arxiv.org/pdf/1802.08012v6.pdf
PWC	https://paperswithcode.com/paper/learning-topic-models-by-neighborhood
Repo
Framework

Large-Scale Validation of Hypothesis Generation Systems via Candidate Ranking


Title	Large-Scale Validation of Hypothesis Generation Systems via Candidate Ranking
Authors	Justin Sybrandt, Michael Shtutman, Ilya Safro
Abstract	The first step of many research projects is to define and rank a short list of candidates for study. In the modern rapidity of scientific progress, some turn to automated hypothesis generation (HG) systems to aid this process. These systems can identify implicit or overlooked connections within a large scientific corpus, and while their importance grows alongside the pace of science, they lack thorough validation. Without any standard numerical evaluation method, many validate general-purpose HG systems by rediscovering a handful of historical findings, and some wishing to be more thorough may run laboratory experiments based on automatic suggestions. These methods are expensive, time consuming, and cannot scale. Thus, we present a numerical evaluation framework for the purpose of validating HG systems that leverages thousands of validation hypotheses. This method evaluates a HG system by its ability to rank hypotheses by plausibility; a process reminiscent of human candidate selection. Because HG systems do not produce a ranking criteria, specifically those that produce topic models, we additionally present novel metrics to quantify the plausibility of hypotheses given topic model system output. Finally, we demonstrate that our proposed validation method aligns with real-world research goals by deploying our method within Moliere, our recent topic-driven HG system, in order to automatically generate a set of candidate genes related to HIV-associated neurodegenerative disease (HAND). By performing laboratory experiments based on this candidate set, we discover a new connection between HAND and Dead Box RNA Helicase 3 (DDX3). Reproducibility: code, validation data, and results can be found at sybrandt.com/2018/validation.
Tasks	Topic Models
Published	2018-02-11
URL	http://arxiv.org/abs/1802.03793v4
PDF	http://arxiv.org/pdf/1802.03793v4.pdf
PWC	https://paperswithcode.com/paper/large-scale-validation-of-hypothesis
Repo
Framework