Paper Group NANR 84
SingleCite: Towards an improved Single Citation Search in PubMed. Identification of Personal Information Shared in Chat-Oriented Dialogue. Villani at SemEval-2018 Task 8: Semantic Extraction from Cybersecurity Reports using Representation Learning. The French-Algerian Code-Switching Triggered audio corpus (FACST). Improve Training Stability of Semi …
SingleCite: Towards an improved Single Citation Search in PubMed
Title | SingleCite: Towards an improved Single Citation Search in PubMed |
Authors | Lana Yeganova, Donald C Comeau, Won Kim, W John Wilbur, Zhiyong Lu |
Abstract | A search that is targeted at finding a specific document in databases is called a Single Citation search. Single citation searches are particularly important for scholarly databases, such as PubMed, because users are frequently searching for a specific publication. In this work we describe SingleCite, a single citation matching system designed to facilitate user{'}s search for a specific document. We report on the progress that has been achieved towards building that functionality. |
Tasks | |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-2318/ |
https://www.aclweb.org/anthology/W18-2318 | |
PWC | https://paperswithcode.com/paper/singlecite-towards-an-improved-single |
Repo | |
Framework | |
Identification of Personal Information Shared in Chat-Oriented Dialogue
Title | Identification of Personal Information Shared in Chat-Oriented Dialogue |
Authors | Sarah Fillwock, David Traum |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1629/ |
https://www.aclweb.org/anthology/L18-1629 | |
PWC | https://paperswithcode.com/paper/identification-of-personal-information-shared |
Repo | |
Framework | |
Villani at SemEval-2018 Task 8: Semantic Extraction from Cybersecurity Reports using Representation Learning
Title | Villani at SemEval-2018 Task 8: Semantic Extraction from Cybersecurity Reports using Representation Learning |
Authors | Pablo Loyola, Kugamoorthy Gajananan, Yuji Watanabe, Fumiko Satoh |
Abstract | In this paper, we describe our proposal for the task of Semantic Extraction from Cybersecurity Reports. The goal is to explore if natural language processing methods can provide relevant and actionable knowledge to contribute to better understand malicious behavior. Our method consists of an attention-based Bi-LSTM which achieved competitive performance of 0.57 for the Subtask 1. In the due process we also present ablation studies across multiple embeddings and their level of representation and also report the strategies we used to mitigate the extreme imbalance between classes. |
Tasks | Representation Learning |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1143/ |
https://www.aclweb.org/anthology/S18-1143 | |
PWC | https://paperswithcode.com/paper/villani-at-semeval-2018-task-8-semantic |
Repo | |
Framework | |
The French-Algerian Code-Switching Triggered audio corpus (FACST)
Title | The French-Algerian Code-Switching Triggered audio corpus (FACST) |
Authors | Amazouz Djegdjiga, Martine Adda-Decker, Lori Lamel |
Abstract | |
Tasks | Language Identification, Transliteration |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1233/ |
https://www.aclweb.org/anthology/L18-1233 | |
PWC | https://paperswithcode.com/paper/the-french-algerian-code-switching-triggered |
Repo | |
Framework | |
Improve Training Stability of Semi-supervised Generative Adversarial Networks with Collaborative Training
Title | Improve Training Stability of Semi-supervised Generative Adversarial Networks with Collaborative Training |
Authors | Dalei Wu, Xiaohua Liu |
Abstract | Improved generative adversarial network (Improved GAN) is a successful method of using generative adversarial models to solve the problem of semi-supervised learning. However, it suffers from the problem of unstable training. In this paper, we found that the instability is mostly due to the vanishing gradients on the generator. To remedy this issue, we propose a new method to use collaborative training to improve the stability of semi-supervised GAN with the combination of Wasserstein GAN. The experiments have shown that our proposed method is more stable than the original Improved GAN and achieves comparable classification accuracy on different data sets. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=ry4SNTe0- |
https://openreview.net/pdf?id=ry4SNTe0- | |
PWC | https://paperswithcode.com/paper/improve-training-stability-of-semi-supervised |
Repo | |
Framework | |
A Geometric Perspective on Structured Light Coding
Title | A Geometric Perspective on Structured Light Coding |
Authors | Mohit Gupta, Nikhil Nakhate |
Abstract | We present a mathematical framework for analysis and design of high performance structured light (SL) coding schemes. Using this framework, we design Hamiltonian SL coding, a novel family of SL coding schemes that can recover 3D shape with extreme precision, with a small number (as few as three) of images. We establish structural similarity between popular discrete (binary) SL coding methods, and Hamiltonian coding, which is a continuous coding approach. Based on this similarity, and by leveraging design principles from several different SL coding families, we propose a general recipe for designing Hamiltonian coding patterns with specific desirable properties, such as patterns with high spatial frequencies for dealing with global illumination. We perform several experiments to evaluate the proposed approach, and demonstrate that Hamiltonian coding based SL approaches outperform existing methods in challenging scenarios, including scenes with dark albedos, strong ambient light, and interreflections. |
Tasks | |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Mohit_Gupta_A_Geometric_Perspective_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Mohit_Gupta_A_Geometric_Perspective_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/a-geometric-perspective-on-structured-light |
Repo | |
Framework | |
Learning Superpixels With Segmentation-Aware Affinity Loss
Title | Learning Superpixels With Segmentation-Aware Affinity Loss |
Authors | Wei-Chih Tu, Ming-Yu Liu, Varun Jampani, Deqing Sun, Shao-Yi Chien, Ming-Hsuan Yang, Jan Kautz |
Abstract | Superpixel segmentation has been widely used in many computer vision tasks. Existing superpixel algorithms are mainly based on hand-crafted features, which often fail to preserve weak object boundaries. In this work, we leverage deep neural networks to facilitate extracting superpixels from images. We show a simple integration of deep features with existing superpixel algorithms does not result in better performance as these features do not model segmentation. Instead, we propose a segmentation-aware affinity learning approach for superpixel segmentation. Specifically, we propose a new loss function that takes the segmentation error into account for affinity learning. We also develop the Pixel Affinity Net for affinity prediction. Extensive experimental results show that the proposed algorithm based on the learned segmentation-aware loss performs favorably against the state-of-the-art methods. We also demonstrate the use of the learned superpixels in numerous vision applications with consistent improvements. |
Tasks | |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Tu_Learning_Superpixels_With_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Tu_Learning_Superpixels_With_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/learning-superpixels-with-segmentation-aware |
Repo | |
Framework | |
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Title | Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis |
Authors | |
Abstract | |
Tasks | |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/W18-6200/ |
https://www.aclweb.org/anthology/W18-6200 | |
PWC | https://paperswithcode.com/paper/proceedings-of-the-9th-workshop-on |
Repo | |
Framework | |
Focus, Segment and Erase: An Efficient Network for Multi-Label Brain Tumor Segmentation
Title | Focus, Segment and Erase: An Efficient Network for Multi-Label Brain Tumor Segmentation |
Authors | Xuan Chen, Jun Hao Liew, Wei Xiong, Chee-Kong Chui, Sim-Heng Ong |
Abstract | In multi-label brain tumor segmentation, class imbalance and inter-class interference are common and challenging problems. In this paper, we propose a novel end-to-end trainable network named FSENet to address the aforementioned issues. The proposed FSENet has a tumor region pooling component to restrict the prediction within the tumor region (focus"), thus mitigating the influence of the dominant non-tumor region. Furthermore, the network decomposes the more challenging multi-label brain tumor segmentation problem into several simpler binary segmentation tasks ( segment”), where each task focuses on a specific tumor tissue. To alleviate inter-class interference, we adopt a simple yet effective idea in our work: we erase the segmented regions before proceeding to further segmentation of tumor tissue (``erase”), thus reduces competition among different tumor classes. Our single-model FSENet ranks 3rd on the multi-modal brain tumor segmentation benchmark 2015 (BraTS 2015) without relying on ensembles or complicated post-processing steps. | |
Tasks | Brain Tumor Segmentation |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Xuan_Chen_Focus_Segment_and_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Xuan_Chen_Focus_Segment_and_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/focus-segment-and-erase-an-efficient-network |
Repo | |
Framework | |
Zero Pronoun Resolution with Attention-based Neural Network
Title | Zero Pronoun Resolution with Attention-based Neural Network |
Authors | Qingyu Yin, Yu Zhang, Weinan Zhang, Ting Liu, William Yang Wang |
Abstract | Recent neural network methods for zero pronoun resolution explore multiple models for generating representation vectors for zero pronouns and their candidate antecedents. Typically, contextual information is utilized to encode the zero pronouns since they are simply gaps that contain no actual content. To better utilize contexts of the zero pronouns, we here introduce the self-attention mechanism for encoding zero pronouns. With the help of the multiple hops of attention, our model is able to focus on some informative parts of the associated texts and therefore produces an efficient way of encoding the zero pronouns. In addition, an attention-based recurrent neural network is proposed for encoding candidate antecedents by their contents. Experiment results are encouraging: our proposed attention-based model gains the best performance on the Chinese portion of the OntoNotes corpus, substantially surpasses existing Chinese zero pronoun resolution baseline systems. |
Tasks | Chinese Zero Pronoun Resolution |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1002/ |
https://www.aclweb.org/anthology/C18-1002 | |
PWC | https://paperswithcode.com/paper/zero-pronoun-resolution-with-attention-based |
Repo | |
Framework | |
Generative modeling for protein structures
Title | Generative modeling for protein structures |
Authors | Namrata Anand, Possu Huang |
Abstract | Analyzing the structure and function of proteins is a key part of understanding biology at the molecular and cellular level. In addition, a major engineering challenge is to design new proteins in a principled and methodical way. Current computational modeling methods for protein design are slow and often require human oversight and intervention. Here, we apply Generative Adversarial Networks (GANs) to the task of generating protein structures, toward application in fast de novo protein design. We encode protein structures in terms of pairwise distances between alpha-carbons on the protein backbone, which eliminates the need for the generative model to learn translational and rotational symmetries. We then introduce a convex formulation of corruption-robust 3D structure recovery to fold the protein structures from generated pairwise distance maps, and solve these problems using the Alternating Direction Method of Multipliers. We test the effectiveness of our models by predicting completions of corrupted protein structures and show that the method is capable of quickly producing structurally plausible solutions. |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7978-generative-modeling-for-protein-structures |
http://papers.nips.cc/paper/7978-generative-modeling-for-protein-structures.pdf | |
PWC | https://paperswithcode.com/paper/generative-modeling-for-protein-structures |
Repo | |
Framework | |
Self-Calibrating Isometric Non-Rigid Structure-from-Motion
Title | Self-Calibrating Isometric Non-Rigid Structure-from-Motion |
Authors | Shaifali Parashar, Adrien Bartoli, Daniel Pizarro |
Abstract | We present self-calibrating isometric non-rigid structure- from-motion (SCIso-NRSfM), the first method to reconstruct a non-rigid object from at least three monocular images with constant but unknown focal length. The majority of NRSfM methods using the perspective cam- era simply assume that the calibration is known. SCIso-NRSfM leverages the recent powerful differential approaches to NRSfM, based on formu- lating local polynomial constraints, where local means correspondence- wise. In NRSfM, the local shape may be solved from these constraints. In SCIso-NRSfM, the difficulty is to also solve for the focal length as a global variable. We propose to eliminate the shape using resultants, obtaining univariate polynomials for the focal length only, whose sum of squares can then be globally minimized. SCIso-NRSfM thus solves for the focal length by integrating the constraints for all correspondences and the whole image set. Once this is done, the local shape is easily re- covered. Our experiments show that its performance is very close to the state-of-the-art methods that use a calibrated camera. |
Tasks | Calibration |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/shaifali_parashar_Self-Calibrating_Isometric__ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/shaifali_parashar_Self-Calibrating_Isometric__ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/self-calibrating-isometric-non-rigid |
Repo | |
Framework | |
探討聲學模型的合併技術與半監督鑑別式訓練於會議語音辨識之研究 (Investigating acoustic model combination and semi-supervised discriminative training for meeting speech recognition) [In Chinese]
Title | 探討聲學模型的合併技術與半監督鑑別式訓練於會議語音辨識之研究 (Investigating acoustic model combination and semi-supervised discriminative training for meeting speech recognition) [In Chinese] |
Authors | Tien-Hong Lo, Berlin Chen |
Abstract | |
Tasks | Speech Recognition |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/O18-1007/ |
https://www.aclweb.org/anthology/O18-1007 | |
PWC | https://paperswithcode.com/paper/e-e2a-acaa12eeacceaa14e-c-14eeae3e34-ea1c-c |
Repo | |
Framework | |
A Co-Attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness
Title | A Co-Attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness |
Authors | Xiangju Li, Kaisong Song, Shi Feng, Daling Wang, Yifei Zhang |
Abstract | Emotion cause analysis has been a key topic in natural language processing. Existing methods ignore the contexts around the emotion word which can provide an emotion cause clue. Meanwhile, the clauses in a document play different roles on stimulating a certain emotion, depending on their content relevance. Therefore, we propose a co-attention neural network model for emotion cause analysis with emotional context awareness. The method encodes the clauses with a co-attention based bi-directional long short-term memory into high-level input representations, which are further fed into a convolutional layer for emotion cause analysis. Experimental results show that our approach outperforms the state-of-the-art baseline methods. |
Tasks | |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1506/ |
https://www.aclweb.org/anthology/D18-1506 | |
PWC | https://paperswithcode.com/paper/a-co-attention-neural-network-model-for |
Repo | |
Framework | |
A Genre-Aware Attention Model to Improve the Likability Prediction of Books
Title | A Genre-Aware Attention Model to Improve the Likability Prediction of Books |
Authors | Suraj Maharjan, Manuel Montes, Fabio A. Gonz{'a}lez, Thamar Solorio |
Abstract | Likability prediction of books has many uses. Readers, writers, as well as the publishing industry, can all benefit from automatic book likability prediction systems. In order to make reliable decisions, these systems need to assimilate information from different aspects of a book in a sensible way. We propose a novel multimodal neural architecture that incorporates genre supervision to assign weights to individual feature types. Our proposed method is capable of dynamically tailoring weights given to feature types based on the characteristics of each book. Our architecture achieves competitive results and even outperforms state-of-the-art for this task. |
Tasks | Feature Importance |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1375/ |
https://www.aclweb.org/anthology/D18-1375 | |
PWC | https://paperswithcode.com/paper/a-genre-aware-attention-model-to-improve-the |
Repo | |
Framework | |