Paper Group ANR 247
Quantifying Human Behavior on the Block Design Test Through Automated Multi-Level Analysis of Overhead Video. Card-660: Cambridge Rare Word Dataset - a Reliable Benchmark for Infrequent Word Representation Models. Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks. Semantically-aware population health risk analys …
Quantifying Human Behavior on the Block Design Test Through Automated Multi-Level Analysis of Overhead Video
| Title | Quantifying Human Behavior on the Block Design Test Through Automated Multi-Level Analysis of Overhead Video |
| Authors | Seunghwan Cha, James Ainooson, Maithilee Kunda |
| Abstract | The block design test is a standardized, widely used neuropsychological assessment of visuospatial reasoning that involves a person recreating a series of given designs out of a set of colored blocks. In current testing procedures, an expert neuropsychologist observes a person’s accuracy and completion time as well as overall impressions of the person’s problem-solving procedures, errors, etc., thus obtaining a holistic though subjective and often qualitative view of the person’s cognitive processes. We propose a new framework that combines room sensors and AI techniques to augment the information available to neuropsychologists from block design and similar tabletop assessments. In particular, a ceiling-mounted camera captures an overhead view of the table surface. From this video, we demonstrate how automated classification using machine learning can produce a frame-level description of the state of the block task and the person’s actions over the course of each test problem. We also show how a sequence-comparison algorithm can classify one individual’s problem-solving strategy relative to a database of simulated strategies, and how these quantitative results can be visualized for use by neuropsychologists. |
| Tasks | |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07488v1 |
| http://arxiv.org/pdf/1811.07488v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantifying-human-behavior-on-the-block |
| Repo | |
| Framework | |
Card-660: Cambridge Rare Word Dataset - a Reliable Benchmark for Infrequent Word Representation Models
| Title | Card-660: Cambridge Rare Word Dataset - a Reliable Benchmark for Infrequent Word Representation Models |
| Authors | Mohammad Taher Pilehvar, Dimitri Kartsaklis, Victor Prokhorov, Nigel Collier |
| Abstract | Rare word representation has recently enjoyed a surge of interest, owing to the crucial role that effective handling of infrequent words can play in accurate semantic understanding. However, there is a paucity of reliable benchmarks for evaluation and comparison of these techniques. We show in this paper that the only existing benchmark (the Stanford Rare Word dataset) suffers from low-confidence annotations and limited vocabulary; hence, it does not constitute a solid comparison framework. In order to fill this evaluation gap, we propose CAmbridge Rare word Dataset (Card-660), an expert-annotated word similarity dataset which provides a highly reliable, yet challenging, benchmark for rare word representation techniques. Through a set of experiments we show that even the best mainstream word embeddings, with millions of words in their vocabularies, are unable to achieve performances higher than 0.43 (Pearson correlation) on the dataset, compared to a human-level upperbound of 0.90. We release the dataset and the annotation materials at https://pilehvar.github.io/card-660/. |
| Tasks | Word Embeddings |
| Published | 2018-08-28 |
| URL | http://arxiv.org/abs/1808.09308v1 |
| http://arxiv.org/pdf/1808.09308v1.pdf | |
| PWC | https://paperswithcode.com/paper/card-660-cambridge-rare-word-dataset-a |
| Repo | |
| Framework | |
Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks
| Title | Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks |
| Authors | Salman Ul Hassan Dar, Mahmut Yurt, Levent Karacan, Aykut Erdem, Erkut Erdem, Tolga Çukur |
| Abstract | Acquiring images of the same anatomy with multiple different contrasts increases the diversity of diagnostic information available in an MR exam. Yet, scan time limitations may prohibit acquisition of certain contrasts, and images for some contrast may be corrupted by noise and artifacts. In such cases, the ability to synthesize unacquired or corrupted contrasts from remaining contrasts can improve diagnostic utility. For multi-contrast synthesis, current methods learn a nonlinear intensity transformation between the source and target images, either via nonlinear regression or deterministic neural networks. These methods can in turn suffer from loss of high-spatial-frequency information in synthesized images. Here we propose a new approach for multi-contrast MRI synthesis based on conditional generative adversarial networks. The proposed approach preserves high-frequency details via an adversarial loss; and it offers enhanced synthesis performance via a pixel-wise loss for registered multi-contrast images and a cycle-consistency loss for unregistered images. Information from neighboring cross-sections are utilized to further improved synthesis quality. Demonstrations on T1- and T2-weighted images from healthy subjects and patients clearly indicate the superior performance of the proposed approach compared to previous state-of-the-art methods. Our synthesis approach can help improve quality and versatility of multi-contrast MRI exams without the need for prolonged examinations. |
| Tasks | Image Generation |
| Published | 2018-02-05 |
| URL | http://arxiv.org/abs/1802.01221v1 |
| http://arxiv.org/pdf/1802.01221v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-synthesis-in-multi-contrast-mri-with |
| Repo | |
| Framework | |
Semantically-aware population health risk analyses
| Title | Semantically-aware population health risk analyses |
| Authors | Alexander New, Sabbir M. Rashid, John S. Erickson, Deborah L. McGuinness, Kristin P. Bennett |
| Abstract | One primary task of population health analysis is the identification of risk factors that, for some subpopulation, have a significant association with some health condition. Examples include finding lifestyle factors associated with chronic diseases and finding genetic mutations associated with diseases in precision health. We develop a combined semantic and machine learning system that uses a health risk ontology and knowledge graph (KG) to dynamically discover risk factors and their associated subpopulations. Semantics and the novel supervised cadre model make our system explainable. Future population health studies are easily performed and documented with provenance by specifying additional input and output KG cartridges. |
| Tasks | |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.11190v1 |
| http://arxiv.org/pdf/1811.11190v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantically-aware-population-health-risk |
| Repo | |
| Framework | |
Markov Chain Neural Networks
| Title | Markov Chain Neural Networks |
| Authors | Maren Awiszus, Bodo Rosenhahn |
| Abstract | In this work we present a modified neural network model which is capable to simulate Markov Chains. We show how to express and train such a network, how to ensure given statistical properties reflected in the training data and we demonstrate several applications where the network produces non-deterministic outcomes. One example is a random walker model, e.g. useful for simulation of Brownian motions or a natural Tic-Tac-Toe network which ensures non-deterministic game behavior. |
| Tasks | |
| Published | 2018-05-02 |
| URL | http://arxiv.org/abs/1805.00784v1 |
| http://arxiv.org/pdf/1805.00784v1.pdf | |
| PWC | https://paperswithcode.com/paper/markov-chain-neural-networks |
| Repo | |
| Framework | |
Multiple Causal Inference with Latent Confounding
| Title | Multiple Causal Inference with Latent Confounding |
| Authors | Rajesh Ranganath, Adler Perotte |
| Abstract | Causal inference from observational data requires assumptions. These assumptions range from measuring confounders to identifying instruments. Traditionally, causal inference assumptions have focused on estimation of effects for a single treatment. In this work, we construct techniques for estimation with multiple treatments in the presence of unobserved confounding. We develop two assumptions based on shared confounding between treatments and independence of treatments given the confounder. Together, these assumptions lead to a confounder estimator regularized by mutual information. For this estimator, we develop a tractable lower bound. To recover treatment effects, we use the residual information in the treatments independent of the confounder. We validate on simulations and an example from clinical medicine. |
| Tasks | Causal Inference |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.08273v3 |
| http://arxiv.org/pdf/1805.08273v3.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-causal-inference-with-latent |
| Repo | |
| Framework | |
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing
| Title | NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing |
| Authors | Dinghan Shen, Qinliang Su, Paidamoyo Chapfuwa, Wenlin Wang, Guoyin Wang, Lawrence Carin, Ricardo Henao |
| Abstract | Semantic hashing has become a powerful paradigm for fast similarity search in many information retrieval systems. While fairly successful, previous techniques generally require two-stage training, and the binary constraints are handled ad-hoc. In this paper, we present an end-to-end Neural Architecture for Semantic Hashing (NASH), where the binary hashing codes are treated as Bernoulli latent variables. A neural variational inference framework is proposed for training, where gradients are directly back-propagated through the discrete latent variable to optimize the hash function. We also draw connections between proposed method and rate-distortion theory, which provides a theoretical foundation for the effectiveness of the proposed framework. Experimental results on three public datasets demonstrate that our method significantly outperforms several state-of-the-art models on both unsupervised and supervised scenarios. |
| Tasks | Information Retrieval |
| Published | 2018-05-14 |
| URL | http://arxiv.org/abs/1805.05361v1 |
| http://arxiv.org/pdf/1805.05361v1.pdf | |
| PWC | https://paperswithcode.com/paper/nash-toward-end-to-end-neural-architecture |
| Repo | |
| Framework | |
Syntactic Patterns Improve Information Extraction for Medical Search
| Title | Syntactic Patterns Improve Information Extraction for Medical Search |
| Authors | Roma Patel, Yinfei Yang, Iain Marshall, Ani Nenkova, Byron Wallace |
| Abstract | Medical professionals search the published literature by specifying the type of patients, the medical intervention(s) and the outcome measure(s) of interest. In this paper we demonstrate how features encoding syntactic patterns improve the performance of state-of-the-art sequence tagging models (both linear and neural) for information extraction of these medically relevant categories. We present an analysis of the type of patterns exploited, and the semantic space induced for these, i.e., the distributed representations learned for identified multi-token patterns. We show that these learned representations differ substantially from those of the constituent unigrams, suggesting that the patterns capture contextual information that is otherwise lost. |
| Tasks | |
| Published | 2018-04-30 |
| URL | http://arxiv.org/abs/1805.00097v1 |
| http://arxiv.org/pdf/1805.00097v1.pdf | |
| PWC | https://paperswithcode.com/paper/syntactic-patterns-improve-information |
| Repo | |
| Framework | |
Improving Neural Text Simplification Model with Simplified Corpora
| Title | Improving Neural Text Simplification Model with Simplified Corpora |
| Authors | Jipeng Qiang |
| Abstract | Text simplification (TS) can be viewed as monolingual translation task, translating between text variations within a single language. Recent neural TS models draw on insights from neural machine translation to learn lexical simplification and content reduction using encoder-decoder model. But different from neural machine translation, we cannot obtain enough ordinary and simplified sentence pairs for TS, which are expensive and time-consuming to build. Target-side simplified sentences plays an important role in boosting fluency for statistical TS, and we investigate the use of simplified sentences to train, with no changes to the network architecture. We propose to pair simple training sentence with a synthetic ordinary sentence via back-translation, and treating this synthetic data as additional training data. We train encoder-decoder model using synthetic sentence pairs and original sentence pairs, which can obtain substantial improvements on the available WikiLarge data and WikiSmall data compared with the state-of-the-art methods. |
| Tasks | Lexical Simplification, Machine Translation, Text Simplification |
| Published | 2018-10-10 |
| URL | http://arxiv.org/abs/1810.04428v1 |
| http://arxiv.org/pdf/1810.04428v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-neural-text-simplification-model |
| Repo | |
| Framework | |
Adversarial Learning of Task-Oriented Neural Dialog Models
| Title | Adversarial Learning of Task-Oriented Neural Dialog Models |
| Authors | Bing Liu, Ian Lane |
| Abstract | In this work, we propose an adversarial learning method for reward estimation in reinforcement learning (RL) based task-oriented dialog models. Most of the current RL based task-oriented dialog systems require the access to a reward signal from either user feedback or user ratings. Such user ratings, however, may not always be consistent or available in practice. Furthermore, online dialog policy learning with RL typically requires a large number of queries to users, suffering from sample efficiency problem. To address these challenges, we propose an adversarial learning method to learn dialog rewards directly from dialog samples. Such rewards are further used to optimize the dialog policy with policy gradient based RL. In the evaluation in a restaurant search domain, we show that the proposed adversarial dialog learning method achieves advanced dialog success rate comparing to strong baseline methods. We further discuss the covariate shift problem in online adversarial dialog learning and show how we can address that with partial access to user feedback. |
| Tasks | Dialog Learning |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.11762v1 |
| http://arxiv.org/pdf/1805.11762v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-learning-of-task-oriented-neural |
| Repo | |
| Framework | |
Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos
| Title | Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos |
| Authors | Armine Vardazaryan, Didier Mutter, Jacques Marescaux, Nicolas Padoy |
| Abstract | Surgical tool localization is an essential task for the automatic analysis of endoscopic videos. In the literature, existing methods for tool localization, tracking and segmentation require training data that is fully annotated, thereby limiting the size of the datasets that can be used and the generalization of the approaches. In this work, we propose to circumvent the lack of annotated data with weak supervision. We propose a deep architecture, trained solely on image level annotations, that can be used for both tool presence detection and localization in surgical videos. Our architecture relies on a fully convolutional neural network, trained end-to-end, enabling us to localize surgical tools without explicit spatial annotations. We demonstrate the benefits of our approach on a large public dataset, Cholec80, which is fully annotated with binary tool presence information and of which 5 videos have been fully annotated with bounding boxes and tool centers for the evaluation. |
| Tasks | |
| Published | 2018-06-14 |
| URL | http://arxiv.org/abs/1806.05573v2 |
| http://arxiv.org/pdf/1806.05573v2.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-learning-for-tool |
| Repo | |
| Framework | |
Exploring Shared Structures and Hierarchies for Multiple NLP Tasks
| Title | Exploring Shared Structures and Hierarchies for Multiple NLP Tasks |
| Authors | Junkun Chen, Kaiyu Chen, Xinchi Chen, Xipeng Qiu, Xuanjing Huang |
| Abstract | Designing shared neural architecture plays an important role in multi-task learning. The challenge is that finding an optimal sharing scheme heavily relies on the expert knowledge and is not scalable to a large number of diverse tasks. Inspired by the promising work of neural architecture search (NAS), we apply reinforcement learning to automatically find possible shared architecture for multi-task learning. Specifically, we use a controller to select from a set of shareable modules and assemble a task-specific architecture, and repeat the same procedure for other tasks. The controller is trained with reinforcement learning to maximize the expected accuracies for all tasks. We conduct extensive experiments on two types of tasks, text classification and sequence labeling, which demonstrate the benefits of our approach. |
| Tasks | Multi-Task Learning, Neural Architecture Search, Text Classification |
| Published | 2018-08-23 |
| URL | http://arxiv.org/abs/1808.07658v1 |
| http://arxiv.org/pdf/1808.07658v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-shared-structures-and-hierarchies |
| Repo | |
| Framework | |
Towards computational fluorescence microscopy: Machine learning-based integrated prediction of morphological and molecular tumor profiles
| Title | Towards computational fluorescence microscopy: Machine learning-based integrated prediction of morphological and molecular tumor profiles |
| Authors | Alexander Binder, Michael Bockmayr, Miriam Hägele, Stephan Wienert, Daniel Heim, Katharina Hellweg, Albrecht Stenzinger, Laura Parlow, Jan Budczies, Benjamin Goeppert, Denise Treue, Manato Kotani, Masaru Ishii, Manfred Dietel, Andreas Hocke, Carsten Denkert, Klaus-Robert Müller, Frederick Klauschen |
| Abstract | Recent advances in cancer research largely rely on new developments in microscopic or molecular profiling techniques offering high level of detail with respect to either spatial or molecular features, but usually not both. Here, we present a novel machine learning-based computational approach that allows for the identification of morphological tissue features and the prediction of molecular properties from breast cancer imaging data. This integration of microanatomic information of tumors with complex molecular profiling data, including protein or gene expression, copy number variation, gene methylation and somatic mutations, provides a novel means to computationally score molecular markers with respect to their relevance to cancer and their spatial associations within the tumor microenvironment. |
| Tasks | |
| Published | 2018-05-28 |
| URL | http://arxiv.org/abs/1805.11178v1 |
| http://arxiv.org/pdf/1805.11178v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-computational-fluorescence-microscopy |
| Repo | |
| Framework | |
Monolingual sentence matching for text simplification
| Title | Monolingual sentence matching for text simplification |
| Authors | Yonghui Huang, Yunhui Li, Yi Luan |
| Abstract | This work improves monolingual sentence alignment for text simplification, specifically for text in standard and simple Wikipedia. We introduce a convolutional neural network structure to model similarity between two sentences. Due to the limitation of available parallel corpora, the model is trained in a semi-supervised way, by using the output of a knowledge-based high performance aligning system. We apply the resulting similarity score to rescore the knowledge-based output, and adapt the model by a small hand-aligned dataset. Experiments show that both rescoring and adaptation improve the performance of knowledge-based method. |
| Tasks | Text Simplification |
| Published | 2018-09-19 |
| URL | http://arxiv.org/abs/1809.08703v1 |
| http://arxiv.org/pdf/1809.08703v1.pdf | |
| PWC | https://paperswithcode.com/paper/monolingual-sentence-matching-for-text |
| Repo | |
| Framework | |
Exploiting Numerical Sparsity for Efficient Learning : Faster Eigenvector Computation and Regression
| Title | Exploiting Numerical Sparsity for Efficient Learning : Faster Eigenvector Computation and Regression |
| Authors | Neha Gupta, Aaron Sidford |
| Abstract | In this paper, we obtain improved running times for regression and top eigenvector computation for numerically sparse matrices. Given a data matrix $A \in \mathbb{R}^{n \times d}$ where every row $a \in \mathbb{R}^d$ has $\a_2^2 \leq L$ and numerical sparsity at most $s$, i.e. $\a_1^2 / \a_2^2 \leq s$, we provide faster algorithms for these problems in many parameter settings. For top eigenvector computation, we obtain a running time of $\tilde{O}(nd + r(s + \sqrt{r s}) / \mathrm{gap}^2)$ where $\mathrm{gap} > 0$ is the relative gap between the top two eigenvectors of $A^\top A$ and $r$ is the stable rank of $A$. This running time improves upon the previous best unaccelerated running time of $O(nd + r d / \mathrm{gap}^2)$ as it is always the case that $r \leq d$ and $s \leq d$. For regression, we obtain a running time of $\tilde{O}(nd + (nL / \mu) \sqrt{s nL / \mu})$ where $\mu > 0$ is the smallest eigenvalue of $A^\top A$. This running time improves upon the previous best unaccelerated running time of $\tilde{O}(nd + n L d / \mu)$. This result expands the regimes where regression can be solved in nearly linear time from when $L/\mu = \tilde{O}(1)$ to when $L / \mu = \tilde{O}(d^{2/3} / (sn)^{1/3})$. Furthermore, we obtain similar improvements even when row norms and numerical sparsities are non-uniform and we show how to achieve even faster running times by accelerating using approximate proximal point [Frostig et. al. 2015] / catalyst [Lin et. al. 2015]. Our running times depend only on the size of the input and natural numerical measures of the matrix, i.e. eigenvalues and $\ell_p$ norms, making progress on a key open problem regarding optimal running times for efficient large-scale learning. |
| Tasks | |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.10866v1 |
| http://arxiv.org/pdf/1811.10866v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-numerical-sparsity-for-efficient |
| Repo | |
| Framework | |
