January 28, 2020

3042 words 15 mins read

Paper Group ANR 921

Natural Language Interactions in Autonomous Vehicles: Intent Detection and Slot Filling from Passenger Utterances. Age prediction using a large chest X-ray dataset. Constrained Linear Data-feature Mapping for Image Classification. How Personal is Machine Learning Personalization?. IrisNet: Deep Learning for Automatic and Real-time Tongue Contour Tr …

Natural Language Interactions in Autonomous Vehicles: Intent Detection and Slot Filling from Passenger Utterances


Title	Natural Language Interactions in Autonomous Vehicles: Intent Detection and Slot Filling from Passenger Utterances
Authors	Eda Okur, Shachi H Kumar, Saurav Sahay, Asli Arslan Esme, Lama Nachman
Abstract	Understanding passenger intents and extracting relevant slots are important building blocks towards developing contextual dialogue systems for natural interactions in autonomous vehicles (AV). In this work, we explored AMIE (Automated-vehicle Multi-modal In-cabin Experience), the in-cabin agent responsible for handling certain passenger-vehicle interactions. When the passengers give instructions to AMIE, the agent should parse such commands properly and trigger the appropriate functionality of the AV system. In our current explorations, we focused on AMIE scenarios describing usages around setting or changing the destination and route, updating driving behavior or speed, finishing the trip and other use-cases to support various natural commands. We collected a multi-modal in-cabin dataset with multi-turn dialogues between the passengers and AMIE using a Wizard-of-Oz scheme via a realistic scavenger hunt game activity. After exploring various recent Recurrent Neural Networks (RNN) based techniques, we introduced our own hierarchical joint models to recognize passenger intents along with relevant slots associated with the action to be performed in AV scenarios. Our experimental results outperformed certain competitive baselines and achieved overall F1 scores of 0.91 for utterance-level intent detection and 0.96 for slot filling tasks. In addition, we conducted initial speech-to-text explorations by comparing intent/slot models trained and tested on human transcriptions versus noisy Automatic Speech Recognition (ASR) outputs. Finally, we compared the results with single passenger rides versus the rides with multiple passengers.
Tasks	Autonomous Vehicles, Intent Detection, Slot Filling, Speech Recognition
Published	2019-04-23
URL	http://arxiv.org/abs/1904.10500v1
PDF	http://arxiv.org/pdf/1904.10500v1.pdf
PWC	https://paperswithcode.com/paper/natural-language-interactions-in-autonomous
Repo
Framework

Age prediction using a large chest X-ray dataset


Title	Age prediction using a large chest X-ray dataset
Authors	Alexandros Karargyris, Satyananda Kashyap, Joy T Wu, Arjun Sharma, Mehdi Moradi, Tanveer Syeda-Mahmood
Abstract	Age prediction based on appearances of different anatomies in medical images has been clinically explored for many decades. In this paper, we used deep learning to predict a persons age on Chest X-Rays. Specifically, we trained a CNN in regression fashion on a large publicly available dataset. Moreover, for interpretability, we explored activation maps to identify which areas of a CXR image are important for the machine (i.e. CNN) to predict a patients age, offering insight. Overall, amongst correctly predicted CXRs, we see areas near the clavicles, shoulders, spine, and mediastinum being most activated for age prediction, as one would expect biologically. Amongst incorrectly predicted CXRs, we have qualitatively identified disease patterns that could possibly make the anatomies appear older or younger than expected. A further technical and clinical evaluation would improve this work. As CXR is the most commonly requested imaging exam, a potential use case for estimating age may be found in the preventative counseling of patient health status compared to their age-expected average, particularly when there is a large discrepancy between predicted age and the real patient age.
Tasks
Published	2019-03-09
URL	http://arxiv.org/abs/1903.06542v1
PDF	http://arxiv.org/pdf/1903.06542v1.pdf
PWC	https://paperswithcode.com/paper/age-prediction-using-a-large-chest-x-ray
Repo
Framework

Constrained Linear Data-feature Mapping for Image Classification


Title	Constrained Linear Data-feature Mapping for Image Classification
Authors	Juncai He, Yuyan Chen, Jinchao Xu
Abstract	In this paper, we propose a constrained linear data-feature mapping model as an interpretable mathematical model for image classification using convolutional neural network (CNN) such as the ResNet. From this viewpoint, we establish the detailed connections in a technical level between the traditional iterative schemes for constrained linear system and the architecture for the basic block of ResNet. Under these connections, we propose some natural modifications of ResNet type models which will have less parameters but can keep almost the same accuracy as these original models. Some numerical experiments are shown to demonstrate the validity of this constrained learning data-feature mapping assumption.
Tasks	Image Classification
Published	2019-11-23
URL	https://arxiv.org/abs/1911.10428v1
PDF	https://arxiv.org/pdf/1911.10428v1.pdf
PWC	https://paperswithcode.com/paper/constrained-linear-data-feature-mapping-for
Repo
Framework

How Personal is Machine Learning Personalization?


Title	How Personal is Machine Learning Personalization?
Authors	Travis Greene, Galit Shmueli
Abstract	Though used extensively, the concept and process of machine learning (ML) personalization have generally received little attention from academics, practitioners, and the general public. We describe the ML approach as relying on the metaphor of the person as a feature vector and contrast this with humanistic views of the person. In light of the recent calls by the IEEE to consider the effects of ML on human well-being, we ask whether ML personalization can be reconciled with these humanistic views of the person, which highlight the importance of moral and social identity. As human behavior increasingly becomes digitized, analyzed, and predicted, to what extent do our subsequent decisions about what to choose, buy, or do, made both by us and others, reflect who we are as persons? This paper first explicates the term personalization by considering ML personalization and highlights its relation to humanistic conceptions of the person, then proposes several dimensions for evaluating the degree of personalization of ML personalized scores. By doing so, we hope to contribute to current debate on the issues of algorithmic bias, transparency, and fairness in machine learning.
Tasks
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07938v2
PDF	https://arxiv.org/pdf/1912.07938v2.pdf
PWC	https://paperswithcode.com/paper/how-personal-is-machine-learning
Repo
Framework

IrisNet: Deep Learning for Automatic and Real-time Tongue Contour Tracking in Ultrasound Video Data using Peripheral Vision


Title	IrisNet: Deep Learning for Automatic and Real-time Tongue Contour Tracking in Ultrasound Video Data using Peripheral Vision
Authors	M. Hamed Mozaffari, Md. Aminur Rab Ratul, Won-Sook Lee
Abstract	The progress of deep convolutional neural networks has been successfully exploited in various real-time computer vision tasks such as image classification and segmentation. Owing to the development of computational units, availability of digital datasets, and improved performance of deep learning models, fully automatic and accurate tracking of tongue contours in real-time ultrasound data became practical only in recent years. Recent studies have shown that the performance of deep learning techniques is significant in the tracking of ultrasound tongue contours in real-time applications such as pronunciation training using multimodal ultrasound-enhanced approaches. Due to the high correlation between ultrasound tongue datasets, it is feasible to have a general model that accomplishes automatic tongue tracking for almost all datasets. In this paper, we proposed a deep learning model comprises of a convolutional module mimicking the peripheral vision ability of the human eye to handle real-time, accurate, and fully automatic tongue contour tracking tasks, applicable for almost all primary ultrasound tongue datasets. Qualitative and quantitative assessment of IrisNet on different ultrasound tongue datasets and PASCAL VOC2012 revealed its outstanding generalization achievement in compare with similar techniques.
Tasks	Image Classification
Published	2019-11-10
URL	https://arxiv.org/abs/1911.03972v1
PDF	https://arxiv.org/pdf/1911.03972v1.pdf
PWC	https://paperswithcode.com/paper/irisnet-deep-learning-for-automatic-and-real
Repo
Framework

Fiction Sentence Expansion and Enhancement via Focused Objective and Novelty Curve Sampling


Title	Fiction Sentence Expansion and Enhancement via Focused Objective and Novelty Curve Sampling
Authors	Yuri Safovich, Amos Azaria
Abstract	We describe the task of sentence expansion and enhancement, in which a sentence provided by a human is expanded in some creative way. The expansion should be understandable, believably grammatical, and optimally meaning-preserving. Sentence expansion and enhancement may serve as an authoring tool, or integrate in dynamic media, conversational agents, or variegated advertising. We implement a neural sentence expander trained on sentence compressions generated from a corpus of modern fiction. We modify an MLE objective to support the task by focusing on new words, and decode at test time with controlled curve-like novelty sampling. We run our sentence expander on sentences provided by human subjects and have humans evaluate these expansions. We show that, although the generation methods are inferior to professional human writers, they are comparable to, and as well liked as, our subjects’ original input sentences, and preferred over baselines.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00698v2
PDF	https://arxiv.org/pdf/1912.00698v2.pdf
PWC	https://paperswithcode.com/paper/fiction-sentence-expansion-and-enhancement
Repo
Framework

Generalization of machine-learned turbulent heat flux models applied to film cooling flows


Title	Generalization of machine-learned turbulent heat flux models applied to film cooling flows
Authors	Pedro M. Milani, Julia Ling, John K. Eaton
Abstract	The design of film cooling systems relies heavily on Reynolds-Averaged Navier-Stokes (RANS) simulations, which solve for mean quantities and model all turbulent scales. Most turbulent heat flux models, which are based on isotropic diffusion with a fixed turbulent Prandtl number ($Pr_t$), fail to accurately predict heat transfer in film cooling flows. In the present work, machine learning models are trained to predict a non-uniform $Pr_t$ field, using various datasets as training sets. The ability of these models to generalize beyond the flows on which they were trained is explored. Furthermore, visualization techniques are employed to compare distinct datasets and to help explain the cross-validation results.
Tasks
Published	2019-10-07
URL	https://arxiv.org/abs/1910.03097v1
PDF	https://arxiv.org/pdf/1910.03097v1.pdf
PWC	https://paperswithcode.com/paper/generalization-of-machine-learned-turbulent
Repo
Framework

Stochastic Online Learning with Probabilistic Graph Feedback


Title	Stochastic Online Learning with Probabilistic Graph Feedback
Authors	Shuai Li, Wei Chen, Zheng Wen, Kwong-Sak Leung
Abstract	We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability $p_{ij}$. Two cases are covered. (a) The one-step case, where after playing arm $i$ the learner observes a sample reward feedback of arm $j$ with independent probability $p_{ij}$. (b) The cascade case where after playing arm $i$ the learner observes feedback of all arms $j$ in a probabilistic cascade starting from $i$ – for each $(i,j)$ with probability $p_{ij}$, if arm $i$ is played or observed, then a reward sample of arm $j$ would be observed with independent probability $p_{ij}$. Previous works mainly focus on deterministic graphs which corresponds to one-step case with $p_{ij} \in {0,1}$, an adversarial sequence of graphs with certain topology guarantees, or a specific type of random graphs. We analyze the asymptotic lower bounds and design algorithms in both cases. The regret upper bounds of the algorithms match the lower bounds with high probability.
Tasks
Published	2019-03-04
URL	https://arxiv.org/abs/1903.01083v2
PDF	https://arxiv.org/pdf/1903.01083v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-online-learning-with-probabilistic
Repo
Framework

Simultaneous Iris and Periocular Region Detection Using Coarse Annotations


Title	Simultaneous Iris and Periocular Region Detection Using Coarse Annotations
Authors	Diego R. Lucio, Rayson Laroca, Luiz A. Zanlorensi, Gladston Moreira, David Menotti
Abstract	In this work, we propose to detect the iris and periocular regions simultaneously using coarse annotations and two well-known object detectors: YOLOv2 and Faster R-CNN. We believe coarse annotations can be used in recognition systems based on the iris and periocular regions, given the much smaller engineering effort required to manually annotate the training images. We manually made coarse annotations of the iris and periocular regions (122K images from the visible (VIS) spectrum and 38K images from the near-infrared (NIR) spectrum). The iris annotations in the NIR databases were generated semi-automatically by first applying an iris segmentation CNN and then performing a manual inspection. These annotations were made for 11 well-known public databases (3 NIR and 8 VIS) designed for the iris-based recognition problem and are publicly available to the research community. Experimenting our proposal on these databases, we highlight two results. First, the Faster R-CNN + Feature Pyramid Network (FPN) model reported an Intersection over Union (IoU) higher than YOLOv2 (91.86% vs 85.30%). Second, the detection of the iris and periocular regions being performed simultaneously is as accurate as performed separately, but with a lower computational cost, i.e., two tasks were carried out at the cost of one.
Tasks	Iris Segmentation
Published	2019-07-31
URL	https://arxiv.org/abs/1908.00069v1
PDF	https://arxiv.org/pdf/1908.00069v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-iris-and-periocular-region
Repo
Framework

Gender Classification from Iris Texture Images Using a New Set of Binary Statistical Image Features


Title	Gender Classification from Iris Texture Images Using a New Set of Binary Statistical Image Features
Authors	Juan Tapia, Claudia Arellano
Abstract	Soft biometric information such as gender can contribute to many applications like as identification and security. This paper explores the use of a Binary Statistical Features (BSIF) algorithm for classifying gender from iris texture images captured with NIR sensors. It uses the same pipeline for iris recognition systems consisting of iris segmentation, normalisation and then classification. Experiments show that applying BSIF is not straightforward since it can create artificial textures causing misclassification. In order to overcome this limitation, a new set of filters was trained from eye images and different sized filters with padding bands were tested on a subject-disjoint database. A Modified-BSIF (MBSIF) method was implemented. The latter achieved better gender classification results (94.6% and 91.33% for the left and right eye respectively). These results are competitive with the state of the art in gender classification. In an additional contribution, a novel gender labelled database was created and it will be available upon request.
Tasks	Iris Recognition, Iris Segmentation
Published	2019-05-01
URL	http://arxiv.org/abs/1905.00372v1
PDF	http://arxiv.org/pdf/1905.00372v1.pdf
PWC	https://paperswithcode.com/paper/gender-classification-from-iris-texture
Repo
Framework

The University of Helsinki submissions to the WMT19 news translation task


Title	The University of Helsinki submissions to the WMT19 news translation task
Authors	Aarne Talman, Umut Sulubacak, Raúl Vázquez, Yves Scherrer, Sami Virpioja, Alessandro Raganato, Arvi Hurskainen, Jörg Tiedemann
Abstract	In this paper, we present the University of Helsinki submissions to the WMT 2019 shared task on news translation in three language pairs: English-German, English-Finnish and Finnish-English. This year, we focused first on cleaning and filtering the training data using multiple data-filtering approaches, resulting in much smaller and cleaner training sets. For English-German, we trained both sentence-level transformer models and compared different document-level translation approaches. For Finnish-English and English-Finnish we focused on different segmentation approaches, and we also included a rule-based system for English-Finnish.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.04040v1
PDF	https://arxiv.org/pdf/1906.04040v1.pdf
PWC	https://paperswithcode.com/paper/the-university-of-helsinki-submissions-to-the-1
Repo
Framework

Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement


Title	Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement
Authors	Zi-Yi Dou, Zhaopeng Tu, Xing Wang, Longyue Wang, Shuming Shi, Tong Zhang
Abstract	With the promising progress of deep neural networks, layer aggregation has been used to fuse information across layers in various fields, such as computer vision and machine translation. However, most of the previous methods combine layers in a static fashion in that their aggregation strategy is independent of specific hidden states. Inspired by recent progress on capsule networks, in this paper we propose to use routing-by-agreement strategies to aggregate layers dynamically. Specifically, the algorithm learns the probability of a part (individual layer representations) assigned to a whole (aggregated representations) in an iterative way and combines parts accordingly. We implement our algorithm on top of the state-of-the-art neural machine translation model TRANSFORMER and conduct experiments on the widely-used WMT14 English-German and WMT17 Chinese-English translation datasets. Experimental results across language pairs show that the proposed approach consistently outperforms the strong baseline model and a representative static aggregation model.
Tasks	Machine Translation
Published	2019-02-15
URL	http://arxiv.org/abs/1902.05770v1
PDF	http://arxiv.org/pdf/1902.05770v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-layer-aggregation-for-neural-machine
Repo
Framework

Regional Tree Regularization for Interpretability in Black Box Models


Title	Regional Tree Regularization for Interpretability in Black Box Models
Authors	Mike Wu, Sonali Parbhoo, Michael Hughes, Ryan Kindle, Leo Celi, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez
Abstract	The lack of interpretability remains a barrier to the adoption of deep neural networks. Recently, tree regularization has been proposed to encourage deep neural networks to resemble compact, axis-aligned decision trees without significant compromises in accuracy. However, it may be unreasonable to expect that a single tree can predict well across all possible inputs. In this work, we propose regional tree regularization, which encourages a deep model to be well-approximated by several separate decision trees specific to predefined regions of the input space. Practitioners can define regions based on domain knowledge of contexts where different decision-making logic is needed. Across many datasets, our approach delivers more accurate predictions than simply training separate decision trees for each region, while producing simpler explanations than other neural net regularization schemes without sacrificing predictive power. Two healthcare case studies in critical care and HIV demonstrate how experts can improve understanding of deep models via our approach.
Tasks	Decision Making
Published	2019-08-13
URL	https://arxiv.org/abs/1908.04494v3
PDF	https://arxiv.org/pdf/1908.04494v3.pdf
PWC	https://paperswithcode.com/paper/regional-tree-regularization-for
Repo
Framework

DeepIrisNet2: Learning Deep-IrisCodes from Scratch for Segmentation-Robust Visible Wavelength and Near Infrared Iris Recognition


Title	DeepIrisNet2: Learning Deep-IrisCodes from Scratch for Segmentation-Robust Visible Wavelength and Near Infrared Iris Recognition
Authors	Abhishek Gangwar, Akanksha Joshi, Padmaja Joshi, R. Raghavendra
Abstract	We first, introduce a deep learning based framework named as DeepIrisNet2 for visible spectrum and NIR Iris representation. The framework can work without classical iris normalization step or very accurate iris segmentation; allowing to work under non-ideal situation. The framework contains spatial transformer layers to handle deformation and supervision branches after certain intermediate layers to mitigate overfitting. In addition, we present a dual CNN iris segmentation pipeline comprising of a iris/pupil bounding boxes detection network and a semantic pixel-wise segmentation network. Furthermore, to get compact templates, we present a strategy to generate binary iris codes using DeepIrisNet2. Since, no ground truth dataset are available for CNN training for iris segmentation, We build large scale hand labeled datasets and make them public; i) iris, pupil bounding boxes, ii) labeled iris texture. The networks are evaluated on challenging ND-IRIS-0405, UBIRIS.v2, MICHE-I, and CASIA v4 Interval datasets. Proposed approach significantly improves the state-of-the-art and achieve outstanding performance surpassing all previous methods.
Tasks	Iris Recognition, Iris Segmentation
Published	2019-02-06
URL	http://arxiv.org/abs/1902.05390v1
PDF	http://arxiv.org/pdf/1902.05390v1.pdf
PWC	https://paperswithcode.com/paper/deepirisnet2-learning-deep-iriscodes-from
Repo
Framework

Domain Adaptive Training BERT for Response Selection


Title	Domain Adaptive Training BERT for Response Selection
Authors	Taesun Whang, Dongyub Lee, Chanhee Lee, Kisu Yang, Dongsuk Oh, HeuiSeok Lim
Abstract	We focus on multi-turn response selection in a retrieval-based dialog system. In this paper, we utilize the powerful pre-trained language model Bi-directional Encoder Representations from Transformer (BERT) for a multi-turn dialog system and propose a highly effective post-training method on domain-specific corpus. Although BERT is easily adopted to various NLP tasks and outperforms previous baselines of each task, it still has limitations if a task corpus is too focused on a certain domain. Post-training on domain-specific corpus (e.g., Ubuntu Corpus) helps the model to train contextualized representations and words that do not appear in general corpus (e.g.,English Wikipedia). Experiment results show that our approach achieves new state-of-the-art on two response selection benchmark datasets (i.e.,Ubuntu Corpus V1, Advising Corpus) performance improvement by 5.9% and 6% on Recall@1.
Tasks	Language Modelling
Published	2019-08-13
URL	https://arxiv.org/abs/1908.04812v1
PDF	https://arxiv.org/pdf/1908.04812v1.pdf
PWC	https://paperswithcode.com/paper/domain-adaptive-training-bert-for-response
Repo
Framework