October 15, 2019

2306 words 11 mins read

Paper Group NANR 55

Sprucing up the trees – Error detection in treebanks. Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding. Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation. SfSNet: Learning Shape, Reflectance and Illuminance of Faces `in the Wild’. Graph Topological Features via GAN. Neural Metaphor Detecting wi …

Sprucing up the trees – Error detection in treebanks


Title	Sprucing up the trees – Error detection in treebanks
Authors	Ines Rehbein, Josef Ruppenhofer
Abstract	We present a method for detecting annotation errors in manually and automatically annotated dependency parse trees, based on ensemble parsing in combination with Bayesian inference, guided by active learning. We evaluate our method in different scenarios: (i) for error detection in dependency treebanks and (ii) for improving parsing accuracy on in- and out-of-domain data.
Tasks	Active Learning, Bayesian Inference, Domain Adaptation, Named Entity Recognition
Published	2018-08-01
URL	https://www.aclweb.org/anthology/C18-1010/
PDF	https://www.aclweb.org/anthology/C18-1010
PWC	https://paperswithcode.com/paper/sprucing-up-the-trees-a-error-detection-in
Repo
Framework

Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding


Title	Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding
Authors	Hajin Shim, Sung Ju Hwang, Eunho Yang
Abstract	We consider the problem of active feature acquisition where the goal is to sequentially select the subset of features in order to achieve the maximum prediction performance in the most cost-effective way at test time. In this work, we formulate this active feature acquisition as a jointly learning problem of training both the classifier (environment) and the RL agent that decides either to `stop and predict' or` collect a new feature’ at test time, in a cost-sensitive manner. We also introduce a novel encoding scheme to represent acquired subsets of features by proposing an order-invariant set encoding at the feature level, which also significantly reduces the search space for our agent. We evaluate our model on a carefully designed synthetic dataset for the active feature acquisition as well as several medical datasets. Our framework shows meaningful feature acquisition process for diagnosis that complies with human knowledge, and outperforms all baselines in terms of prediction performance as well as feature acquisition cost.
Tasks
Published	2018-12-01
URL	http://papers.nips.cc/paper/7411-joint-active-feature-acquisition-and-classification-with-variable-size-set-encoding
PDF	http://papers.nips.cc/paper/7411-joint-active-feature-acquisition-and-classification-with-variable-size-set-encoding.pdf
PWC	https://paperswithcode.com/paper/joint-active-feature-acquisition-and
Repo
Framework

Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation


Title	Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation
Authors	Zhengming Ding, Sheng Li, Ming Shao, Yun Fu
Abstract	Unsupervised domain adaptation has caught appealing attentions as it facilitates the unlabeled target learning by borrowing existing well-established source domain knowledge. Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain to better solve cross-domain distribution divergences. However, existing approaches separate target label optimization and domain-invariant feature learning as different steps. To address that issue, we develop a novel Graph Adaptive Knowledge Transfer (GAKT) model to jointly optimize target labels and domain-free features in a unified framework. Specifically, semi-supervised knowledge adaptation and label propagation on target data are coupled to benefit each other, and hence the marginal and conditional disparities across different domains will be better alleviated. Experimental evaluation on two cross-domain visual datasets demonstrates the effectiveness of our designed approach on facilitating the unlabeled target task learning, compared to the state-of-the-art domain adaptation approaches.
Tasks	Domain Adaptation, Transfer Learning, Unsupervised Domain Adaptation
Published	2018-09-01
URL	http://openaccess.thecvf.com/content_ECCV_2018/html/Zhengming_Ding_Graph_Adaptive_Knowledge_ECCV_2018_paper.html
PDF	http://openaccess.thecvf.com/content_ECCV_2018/papers/Zhengming_Ding_Graph_Adaptive_Knowledge_ECCV_2018_paper.pdf
PWC	https://paperswithcode.com/paper/graph-adaptive-knowledge-transfer-for
Repo
Framework

SfSNet: Learning Shape, Reflectance and Illuminance of Faces `in the Wild’


Title	SfSNet: Learning Shape, Reflectance and Illuminance of Faces `in the Wild’ \|
Authors	Soumyadip Sengupta, Angjoo Kanazawa, Carlos D. Castillo, David W. Jacobs
Abstract	We present SfSNet, an end-to-end learning framework for producing an accurate decomposition of an unconstrained human face image into shape, reflectance and illuminance. SfSNet is designed to reflect a physical lambertian rendering model. SfSNet learns from a mixture of labeled synthetic and unlabeled real world images. This allows the network to capture low frequency variations from synthetic and high frequency details from real images through the photometric reconstruction loss. SfSNet consists of a new decomposition architecture with residual blocks that learns a complete separation of albedo and normal. This is used along with the original image to predict lighting. SfSNet produces significantly better quantitative and qualitative results than state-of-the-art methods for inverse rendering and independent normal and illumination estimation.
Tasks
Published	2018-06-01
URL	http://openaccess.thecvf.com/content_cvpr_2018/html/Sengupta_SfSNet_Learning_Shape_CVPR_2018_paper.html
PDF	http://openaccess.thecvf.com/content_cvpr_2018/papers/Sengupta_SfSNet_Learning_Shape_CVPR_2018_paper.pdf
PWC	https://paperswithcode.com/paper/sfsnet-learning-shape-reflectance-and
Repo
Framework

Graph Topological Features via GAN


Title	Graph Topological Features via GAN
Authors	Weiyi Liu, Hal Cooper, Min-Hwan Oh
Abstract	Inspired by the success of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic topological features from a single arbitrary input graph via GANs. The hierarchical architecture consisting of multiple GANs preserves both local and global topological features, and automatically partitions the input graph into representative stages for feature learning. The stages facilitate reconstruction and can be used as indicators of the importance of the associated topological structures. Experiments show that our method produces subgraphs retaining a wide range of topological features, even in early reconstruction stages. This paper contains original research on combining the use of GANs and graph topological analysis.
Tasks
Published	2018-01-01
URL	https://openreview.net/forum?id=BJcAWaeCW
PDF	https://openreview.net/pdf?id=BJcAWaeCW
PWC	https://paperswithcode.com/paper/graph-topological-features-via-gan
Repo
Framework

Neural Metaphor Detecting with CNN-LSTM Model


Title	Neural Metaphor Detecting with CNN-LSTM Model
Authors	Chuhan Wu, Fangzhao Wu, Yubo Chen, Sixing Wu, Zhigang Yuan, Yongfeng Huang
Abstract	Metaphors are figurative languages widely used in daily life and literatures. It{'}s an important task to detect the metaphors evoked by texts. Thus, the metaphor shared task is aimed to extract metaphors from plain texts at word level. We propose to use a CNN-LSTM model for this task. Our model combines CNN and LSTM layers to utilize both local and long-range contextual information for identifying metaphorical information. In addition, we compare the performance of the softmax classifier and conditional random field (CRF) for sequential labeling in this task. We also incorporated some additional features such as part of speech (POS) tags and word cluster to improve the performance of model. Our best model achieved 65.06{%} F-score in the all POS testing subtask and 67.15{%} in the verbs testing subtask.
Tasks	Machine Translation, Sentiment Analysis
Published	2018-06-01
URL	https://www.aclweb.org/anthology/W18-0913/
PDF	https://www.aclweb.org/anthology/W18-0913
PWC	https://paperswithcode.com/paper/neural-metaphor-detecting-with-cnn-lstm-model
Repo
Framework

Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation


Title	Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation
Authors	Xuecheng Nie, Jiashi Feng, Shuicheng Yan
Abstract	This paper presents a novel Mutual Learning to Adapt model (MuLA) for joint human parsing and pose estimation. It effectively exploits mutual benefits from both tasks and simultaneously boosts their performance. Different from existing post-processing or multi-task learning based methods, MuLA predicts dynamic task-specific model parameters via recurrently leveraging guidance information from its parallel tasks. Thus MuLA can fast adapt parsing and pose models to provide more powerful representations by incorporating information from their counterparts, giving more robust and accurate results. MuLA is implemented with convolutional neural networks and end-to-end trainable. Comprehensive experiments on benchmarks LIP and extended PASCAL-Person-Part demonstrate the effectiveness of the proposed MuLA model with superior performance to well established baselines.
Tasks	Human Parsing, Multi-Task Learning, Pose Estimation, Semantic Segmentation
Published	2018-09-01
URL	http://openaccess.thecvf.com/content_ECCV_2018/html/Xuecheng_Nie_Mutual_Learning_to_ECCV_2018_paper.html
PDF	http://openaccess.thecvf.com/content_ECCV_2018/papers/Xuecheng_Nie_Mutual_Learning_to_ECCV_2018_paper.pdf
PWC	https://paperswithcode.com/paper/mutual-learning-to-adapt-for-joint-human
Repo
Framework

Cut to the Chase: A Context Zoom-in Network for Reading Comprehension


Title	Cut to the Chase: A Context Zoom-in Network for Reading Comprehension
Authors	Sathish Reddy Indurthi, Seunghak Yu, Seohyun Back, Heriberto Cuay{'a}huitl
Abstract	In recent years many deep neural networks have been proposed to solve Reading Comprehension (RC) tasks. Most of these models suffer from reasoning over long documents and do not trivially generalize to cases where the answer is not present as a span in a given document. We present a novel neural-based architecture that is capable of extracting relevant regions based on a given question-document pair and generating a well-formed answer. To show the effectiveness of our architecture, we conducted several experiments on the recently proposed and challenging RC dataset {`}NarrativeQA{'}. The proposed architecture outperforms state-of-the-art results by 12.62{%} (ROUGE-L) relative improvement. \|
Tasks	Question Answering, Reading Comprehension
Published	2018-10-01
URL	https://www.aclweb.org/anthology/D18-1054/
PDF	https://www.aclweb.org/anthology/D18-1054
PWC	https://paperswithcode.com/paper/cut-to-the-chase-a-context-zoom-in-network
Repo
Framework

Dense Semantic and Topological Correspondence of 3D Faces without Landmarks


Title	Dense Semantic and Topological Correspondence of 3D Faces without Landmarks
Authors	Zhenfeng Fan, Xiyuan Hu, Chen Chen, Silong Peng
Abstract	Many previous literatures use landmarks to guide the cor- respondence of 3D faces. However, these landmarks, either manually or automatically annotated, are hard to define consistently across differ- ent faces in many circumstances. We propose a general framework for dense correspondence of 3D faces without landmarks in this paper. The dense correspondence goal is revisited in two perspectives: semantic and topological correspondence. Starting from a template facial mesh, we sequentially perform global alignment, primary correspondence by tem- plate warping, and contextual mesh refinement, to reach the final cor- respondence result. The semantic correspondence is achieved by a local iterative closest point (ICP) algorithm of kernelized version, allowing accurate matching of local features. Then, robust deformation from the template to the target face is formulated as a minimization problem. Fur- thermore, this problem leads to a well-posed sparse linear system such that the solution is unique and efficient. Finally, a contextual mesh re- fining algorithm is applied to ensure topological correspondence. In the experiment, the proposed method is evaluated both qualitatively and quantitatively on two datasets including a publicly available FRGC v2.0 dataset, demonstrating reasonable and reliable correspondence results.
Tasks
Published	2018-09-01
URL	http://openaccess.thecvf.com/content_ECCV_2018/html/Zhenfeng_Fan_Dense_Semantic_and_ECCV_2018_paper.html
PDF	http://openaccess.thecvf.com/content_ECCV_2018/papers/Zhenfeng_Fan_Dense_Semantic_and_ECCV_2018_paper.pdf
PWC	https://paperswithcode.com/paper/dense-semantic-and-topological-correspondence
Repo
Framework

Towards Single Word Lexical Complexity Prediction


Title	Towards Single Word Lexical Complexity Prediction
Authors	David Alfter, Elena Volodina
Abstract	In this paper we present work-in-progress where we investigate the usefulness of previously created word lists to the task of single-word lexical complexity analysis and prediction of the complexity level for learners of Swedish as a second language. The word lists used map each word to a single CEFR level, and the task consists of predicting CEFR levels for unseen words. In contrast to previous work on word-level lexical complexity, we experiment with topics as additional features and show that linking words to topics significantly increases accuracy of classification.
Tasks
Published	2018-06-01
URL	https://www.aclweb.org/anthology/W18-0508/
PDF	https://www.aclweb.org/anthology/W18-0508
PWC	https://paperswithcode.com/paper/towards-single-word-lexical-complexity
Repo
Framework

On the Vector Representation of Utterances in Dialogue Context


Title	On the Vector Representation of Utterances in Dialogue Context
Authors	Louisa Pragst, Niklas Rach, Wolfgang Minker, Stefan Ultes
Abstract
Tasks	Document Classification, Intent Detection, Machine Translation, Named Entity Recognition, Sentence Embedding, Sentence Embeddings, Sentiment Analysis, Word Embeddings
Published	2018-05-01
URL	https://www.aclweb.org/anthology/L18-1124/
PDF	https://www.aclweb.org/anthology/L18-1124
PWC	https://paperswithcode.com/paper/on-the-vector-representation-of-utterances-in
Repo
Framework

Deep Volumetric Video From Very Sparse Multi-View Performance Capture


Title	Deep Volumetric Video From Very Sparse Multi-View Performance Capture
Authors	Zeng Huang, Tianye Li, Weikai Chen, Yajie Zhao, Jun Xing, Chloe LeGendre, Linjie Luo, Chongyang Ma, Hao Li
Abstract	We present a deep learning-based volumetric capture approach for performance capture using a passive and highly sparse multi-view capture system. We focus on a template-free, per-frame 3D surface reconstruction from as few as three RGB sensors, where conventional visual hull or multi-view stereo methods would fail. State-of-the-art performance capture systems require either pre-scanned actors, large number of cameras or active sensors. We introduce a novel multi-view Convolutional Neural Network (CNN) that maps 2D images to a 3D volumetric field that encodes the probabilistic distribution of surface points of the captured subject. By querying the resulting field, we can instantiate the clothed human body at arbitrary resolutions. Our approach also scales to different numbers of input images, which yield increased reconstruction quality when more views are used. Though only trained on synthetic data, our network can generalize to real captured performances. Since high-quality temporal surface reconstructions are possible, our method is suitable for low-cost full body volumetric capture solutions for consumers, which are gaining popularity for VR and AR content creation. Experimental results demonstrate that our method is significantly more robust and accurate than existing techniques where only very sparse views are available.
Tasks
Published	2018-09-01
URL	http://openaccess.thecvf.com/content_ECCV_2018/html/Zeng_Huang_Deep_Volumetric_Video_ECCV_2018_paper.html
PDF	http://openaccess.thecvf.com/content_ECCV_2018/papers/Zeng_Huang_Deep_Volumetric_Video_ECCV_2018_paper.pdf
PWC	https://paperswithcode.com/paper/deep-volumetric-video-from-very-sparse-multi
Repo
Framework

A Bridging Framework for Model Optimization and Deep Propagation


Title	A Bridging Framework for Model Optimization and Deep Propagation
Authors	Risheng Liu, Shichao Cheng, Xiaokun Liu, Long Ma, Xin Fan, Zhongxuan Luo
Abstract	Optimizing task-related mathematical model is one of the most fundamental methodologies in statistic and learning areas. However, generally designed schematic iterations may hard to investigate complex data distributions in real-world applications. Recently, training deep propagations (i.e., networks) has gained promising performance in some particular tasks. Unfortunately, existing networks are often built in heuristic manners, thus lack of principled interpretations and solid theoretical supports. In this work, we provide a new paradigm, named Propagation and Optimization based Deep Model (PODM), to bridge the gaps between these different mechanisms (i.e., model optimization and deep propagation). On the one hand, we utilize PODM as a deeply trained solver for model optimization. Different from these existing network based iterations, which often lack theoretical investigations, we provide strict convergence analysis for PODM in the challenging nonconvex and nonsmooth scenarios. On the other hand, by relaxing the model constraints and performing end-to-end training, we also develop a PODM based strategy to integrate domain knowledge (formulated as models) and real data distributions (learned by networks), resulting in a generic ensemble framework for challenging real-world applications. Extensive experiments verify our theoretical results and demonstrate the superiority of PODM against these state-of-the-art approaches.
Tasks
Published	2018-12-01
URL	http://papers.nips.cc/paper/7685-a-bridging-framework-for-model-optimization-and-deep-propagation
PDF	http://papers.nips.cc/paper/7685-a-bridging-framework-for-model-optimization-and-deep-propagation.pdf
PWC	https://paperswithcode.com/paper/a-bridging-framework-for-model-optimization
Repo
Framework

Exploring Word Sense Disambiguation Abilities of Neural Machine Translation Systems (Non-archival Extended Abstract)


Title	Exploring Word Sense Disambiguation Abilities of Neural Machine Translation Systems (Non-archival Extended Abstract)
Authors	Rebecca Marvin, Philipp Koehn
Abstract
Tasks	Machine Translation, Word Embeddings, Word Sense Disambiguation
Published	2018-03-01
URL	https://www.aclweb.org/anthology/W18-1812/
PDF	https://www.aclweb.org/anthology/W18-1812
PWC	https://paperswithcode.com/paper/exploring-word-sense-disambiguation-abilities
Repo
Framework

From analysis to modeling of engagement as sequences of multimodal behaviors


Title	From analysis to modeling of engagement as sequences of multimodal behaviors
Authors	Soumia Dermouche, Catherine Pelachaud
Abstract
Tasks
Published	2018-05-01
URL	https://www.aclweb.org/anthology/L18-1126/
PDF	https://www.aclweb.org/anthology/L18-1126
PWC	https://paperswithcode.com/paper/from-analysis-to-modeling-of-engagement-as
Repo
Framework