Paper Group NANR 115
Spanish HPSG Treebank based on the AnCora Corpus. A comparison of second-order methods for deep convolutional neural networks. Learning from Group Comparisons: Exploiting Higher Order Interactions. Automated EEG-based Screening of Depression Using Deep Convolutional Neural Network. Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Sh …
Spanish HPSG Treebank based on the AnCora Corpus
| Title | Spanish HPSG Treebank based on the AnCora Corpus |
| Authors | Luis Chiruzzo, Dina Wonsever |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1349/ |
| https://www.aclweb.org/anthology/L18-1349 | |
| PWC | https://paperswithcode.com/paper/spanish-hpsg-treebank-based-on-the-ancora |
| Repo | |
| Framework | |
A comparison of second-order methods for deep convolutional neural networks
| Title | A comparison of second-order methods for deep convolutional neural networks |
| Authors | Patrick H. Chen, Cho-jui Hsieh |
| Abstract | Despite many second-order methods have been proposed to train neural networks, most of the results were done on smaller single layer fully connected networks, so we still cannot conclude whether it’s useful in training deep convolutional networks. In this study, we conduct extensive experiments to answer the question “whether second-order method is useful for deep learning?". In our analysis, we find out although currently second-order methods are too slow to be applied in practice, it can reduce training loss in fewer number of iterations compared with SGD. In addition, we have the following interesting findings: (1) When using a large batch size, inexact-Newton methods will converge much faster than SGD. Therefore inexact-Newton method could be a better choice in distributed training of deep networks. (2) Quasi-newton methods are competitive with SGD even when using ReLu activation function (which has no curvature) on residual networks. However, current methods are too sensitive to parameters and not easy to tune for different settings. Therefore, quasi-newton methods with more self-adjusting mechanisms might be more useful than SGD in training deeper networks. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HJYoqzbC- |
| https://openreview.net/pdf?id=HJYoqzbC- | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-second-order-methods-for-deep |
| Repo | |
| Framework | |
Learning from Group Comparisons: Exploiting Higher Order Interactions
| Title | Learning from Group Comparisons: Exploiting Higher Order Interactions |
| Authors | Yao Li, Minhao Cheng, Kevin Fujii, Fushing Hsieh, Cho-Jui Hsieh |
| Abstract | We study the problem of learning from group comparisons, with applications in predicting outcomes of sports and online games. Most of the previous works in this area focus on learning individual effects—they assume each player has an underlying score, and the ‘‘ability’’ of the team is modeled by the sum of team members’ scores. Therefore, all the current approaches cannot model deeper interaction between team members: some players perform much better if they play together, and some players perform poorly together. In this paper, we propose a new model that takes the player-interaction effects into consideration. However, under certain circumstances, the total number of individuals can be very large, and number of player interactions grows quadratically, which makes learning intractable. In this case, we propose a latent factor model, and show that the sample complexity of our model is bounded under mild assumptions. Finally, we show that our proposed models have much better prediction power on several E-sports datasets, and furthermore can be used to reveal interesting patterns that cannot be discovered by previous methods. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7746-learning-from-group-comparisons-exploiting-higher-order-interactions |
| http://papers.nips.cc/paper/7746-learning-from-group-comparisons-exploiting-higher-order-interactions.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-group-comparisons-exploiting |
| Repo | |
| Framework | |
Automated EEG-based Screening of Depression Using Deep Convolutional Neural Network
| Title | Automated EEG-based Screening of Depression Using Deep Convolutional Neural Network |
| Authors | U Rajendra Acharyaa, b, c, *, Shu Lih Oha, Yuki Hagiwaraa, Jen Hong Tana, Hojjat Adelid, D P Subhae |
| Abstract | In recent years, advanced neurocomputing and machine learning techniques have been used for Electroencephalogram (EEG)-based diagnosis of various neurological disorders. In this paper, a novel computer model is presented for EEG-based screening of depression using a deep neural network machine learning approach, known as Convolutional Neural Network (CNN). The proposed technique does not require a semi-manually-selected set of features to be fed into a classifier for classification. It learns automatically and adaptively from the input EEG signals to differentiate EEGs obtained from depressive and normal subjects. The model was tested using EEGs obtained from 15 normal and 15 depressed patients. The algorithm attained accuracies of 93.5% and 96.0% using EEG signals from the left and right hemisphere, respectively. It was discovered in this research that the EEG signals from the right hemisphere are more distinctive in depression than those from the left hemisphere. This discovery is consistent with recent research and revelation that the depression is associated with a hyperactive right hemisphere. An exciting extension of this research would be diagnosis of different stages and severity of depression and development of a Depression Severity Index (DSI). |
| Tasks | EEG |
| Published | 2018-04-17 |
| URL | https://www.sciencedirect.com/science/article/pii/S0169260718301494 |
| https://www.sciencedirect.com/science/article/pii/S0169260718301494 | |
| PWC | https://paperswithcode.com/paper/automated-eeg-based-screening-of-depression |
| Repo | |
| Framework | |
Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape From Images
| Title | Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape From Images |
| Authors | Silvia Zuffi, Angjoo Kanazawa, Michael J. Black |
| Abstract | Animals are widespread in nature and the analysis of their shape and motion is important in many fields and industries. Modeling 3D animal shape, however, is difficult because the 3D scanning methods used to capture human shape are not applicable to wild animals or natural settings. Consequently, we propose a method to capture the detailed 3D shape of animals from images alone. The articulated and deformable nature of animals makes this problem extremely challenging, particularly in unconstrained environments with moving and uncalibrated cameras. To make this possible, we use a strong prior model of articulated animal shape that we fit to the image data. We then deform the animal shape in a canonical reference pose such that it matches image evidence when articulated and projected into multiple images. Our method extracts significantly more 3D shape detail than previous methods and is able to model new species, including the shape of an extinct animal, using only a few video frames. Additionally, the projected 3D shapes are accurate enough to facilitate the extraction of a realistic texture map from multiple frames. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zuffi_Lions_and_Tigers_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zuffi_Lions_and_Tigers_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/lions-and-tigers-and-bears-capturing-non |
| Repo | |
| Framework | |
Improving homograph disambiguation with supervised machine learning
| Title | Improving homograph disambiguation with supervised machine learning |
| Authors | Kyle Gorman, Gleb Mazovetskiy, Vitaly Nikolaev |
| Abstract | |
| Tasks | Speech Synthesis, Text-To-Speech Synthesis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1215/ |
| https://www.aclweb.org/anthology/L18-1215 | |
| PWC | https://paperswithcode.com/paper/improving-homograph-disambiguation-with |
| Repo | |
| Framework | |
Semi-supervised Outlier Detection using Generative And Adversary Framework
| Title | Semi-supervised Outlier Detection using Generative And Adversary Framework |
| Authors | Jindong Gu, Matthias Schubert, Volker Tresp |
| Abstract | In a conventional binary/multi-class classification task, the decision boundary is supported by data from two or more classes. However, in one-class classification task, only data from one class are available. To build an robust outlier detector using only data from a positive class, we propose a corrupted GAN(CorGAN), a deep convolutional Generative Adversary Network requiring no convergence during training. In the adversarial process of training CorGAN, the Generator is supposed to generate outlier samples for negative class, and the Discriminator as an one-class classifier is trained to distinguish data from training datasets (i.e. positive class) and generated data from the Generator (i.e. negative class). To improve the performance of the Discriminator (one-class classifier), we also propose a lot of techniques to improve the performance of the model. The proposed model outperforms the traditional method PCA + PSVM and the solution based on Autoencoder. |
| Tasks | One-class classifier, Outlier Detection |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BkS3fnl0W |
| https://openreview.net/pdf?id=BkS3fnl0W | |
| PWC | https://paperswithcode.com/paper/semi-supervised-outlier-detection-using |
| Repo | |
| Framework | |
PAWS: A Multi-lingual Parallel Treebank with Anaphoric Relations
| Title | PAWS: A Multi-lingual Parallel Treebank with Anaphoric Relations |
| Authors | Anna Nedoluzhko, Michal Nov{'a}k, Maciej Ogrodniczuk |
| Abstract | We present PAWS, a multi-lingual parallel treebank with coreference annotation. It consists of English texts from the Wall Street Journal translated into Czech, Russian and Polish. In addition, the texts are syntactically parsed and word-aligned. PAWS is based on PCEDT 2.0 and continues the tradition of multilingual treebanks with coreference annotation. The paper focuses on the coreference annotation in PAWS and its language-specific differences. PAWS offers linguistic material that can be further leveraged in cross-lingual studies, especially on coreference. |
| Tasks | Coreference Resolution, Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0708/ |
| https://www.aclweb.org/anthology/W18-0708 | |
| PWC | https://paperswithcode.com/paper/paws-a-multi-lingual-parallel-treebank-with |
| Repo | |
| Framework | |
The 2018 Shared Task on Extrinsic Parser Evaluation: On the Downstream Utility of English Universal Dependency Parsers
| Title | The 2018 Shared Task on Extrinsic Parser Evaluation: On the Downstream Utility of English Universal Dependency Parsers |
| Authors | Murhaf Fares, Stephan Oepen, Lilja {\O}vrelid, Jari Bj{"o}rne, Richard Johansson |
| Abstract | We summarize empirical results and tentative conclusions from the Second Extrinsic Parser Evaluation Initiative (EPE 2018). We review the basic task setup, downstream applications involved, and end-to-end results for seventeen participating teams. Based on in-depth quantitative and qualitative analysis, we correlate intrinsic evaluation results at different layers of morph-syntactic analysis with observed downstream behavior. |
| Tasks | Fine-Grained Opinion Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-2002/ |
| https://www.aclweb.org/anthology/K18-2002 | |
| PWC | https://paperswithcode.com/paper/the-2018-shared-task-on-extrinsic-parser |
| Repo | |
| Framework | |
Modeling Brain Activity Associated with Pronoun Resolution in English and Chinese
| Title | Modeling Brain Activity Associated with Pronoun Resolution in English and Chinese |
| Authors | Jixing Li, Murielle Fabre, Wen-Ming Luh, John Hale |
| Abstract | Typological differences between English and Chinese suggest stronger reliance on salience of the antecedent during pronoun resolution in Chinese. We examined this hypothesis by correlating a difficulty measure of pronoun resolution derived by the activation-based ACT-R model with the brain activity of English and Chinese participants listening to a same audiobook during fMRI recording. The ACT-R model predicts higher overall difficulty for English speakers, which is supported at the brain level in left Broca{'}s area. More generally, it confirms that computational modeling approach is able to dissociate different dimensions that are involved in the complex process of pronoun resolution in the brain. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0710/ |
| https://www.aclweb.org/anthology/W18-0710 | |
| PWC | https://paperswithcode.com/paper/modeling-brain-activity-associated-with |
| Repo | |
| Framework | |
Role play-based question-answering by real users for building chatbots with consistent personalities
| Title | Role play-based question-answering by real users for building chatbots with consistent personalities |
| Authors | Ryuichiro Higashinaka, Masahiro Mizukami, Hidetoshi Kawabata, Emi Yamaguchi, Noritake Adachi, Junji Tomita |
| Abstract | Having consistent personalities is important for chatbots if we want them to be believable. Typically, many question-answer pairs are prepared by hand for achieving consistent responses; however, the creation of such pairs is costly. In this study, our goal is to collect a large number of question-answer pairs for a particular character by using role play-based question-answering in which multiple users play the roles of certain characters and respond to questions by online users. Focusing on two famous characters, we conducted a large-scale experiment to collect question-answer pairs by using real users. We evaluated the effectiveness of role play-based question-answering and found that, by using our proposed method, the collected pairs lead to good-quality chatbots that exhibit consistent personalities. |
| Tasks | Chatbot, Question Answering |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5031/ |
| https://www.aclweb.org/anthology/W18-5031 | |
| PWC | https://paperswithcode.com/paper/role-play-based-question-answering-by-real |
| Repo | |
| Framework | |
Interactive Structure Learning with Structural Query-by-Committee
| Title | Interactive Structure Learning with Structural Query-by-Committee |
| Authors | Christopher Tosh, Sanjoy Dasgupta |
| Abstract | In this work, we introduce interactive structure learning, a framework that unifies many different interactive learning tasks. We present a generalization of the query-by-committee active learning algorithm for this setting, and we study its consistency and rate of convergence, both theoretically and empirically, with and without noise. |
| Tasks | Active Learning |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7389-interactive-structure-learning-with-structural-query-by-committee |
| http://papers.nips.cc/paper/7389-interactive-structure-learning-with-structural-query-by-committee.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-structure-learning-with |
| Repo | |
| Framework | |
Incorporating Deep Visual Features into Multiobjective based Multi-view Search Results Clustering
| Title | Incorporating Deep Visual Features into Multiobjective based Multi-view Search Results Clustering |
| Authors | Sayantan Mitra, Mohammed Hasanuzzaman, Sriparna Saha, Andy Way |
| Abstract | Current paper explores the use of multi-view learning for search result clustering. A web-snippet can be represented using multiple views. Apart from textual view cued by both the semantic and syntactic information, a complimentary view extracted from images contained in the web-snippets is also utilized in the current framework. A single consensus partitioning is finally obtained after consulting these two individual views by the deployment of a multiobjective based clustering technique. Several objective functions including the values of a cluster quality measure measuring the goodness of partitionings obtained using different views and an agreement-disagreement index, quantifying the amount of oneness among multiple views in generating partitionings are optimized simultaneously using AMOSA. In order to detect the number of clusters automatically, concepts of variable length solutions and a vast range of permutation operators are introduced in the clustering process. Finally, a set of alternative partitioning are obtained on the final Pareto front by the proposed multi-view based multiobjective technique. Experimental results by the proposed approach on several benchmark test datasets of SRC with respect to different performance metrics evidently establish the power of visual and text-based views in achieving better search result clustering. |
| Tasks | Image Captioning, Multiobjective Optimization, MULTI-VIEW LEARNING, Sentiment Analysis |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1321/ |
| https://www.aclweb.org/anthology/C18-1321 | |
| PWC | https://paperswithcode.com/paper/incorporating-deep-visual-features-into |
| Repo | |
| Framework | |
Proceedings of the 2nd Workshop on Neural Machine Translation and Generation
| Title | Proceedings of the 2nd Workshop on Neural Machine Translation and Generation |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2700/ |
| https://www.aclweb.org/anthology/W18-2700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-neural |
| Repo | |
| Framework | |
Improving Machine Translation of Educational Content via Crowdsourcing
| Title | Improving Machine Translation of Educational Content via Crowdsourcing |
| Authors | Maximiliana Behnke, Antonio Valerio Miceli Barone, Rico Sennrich, Vilelmini Sosoni, Thanasis Naskos, Eirini Takoulidou, Maria Stasimioti, Menno van Zaanen, Sheila Castilho, Federico Gaspari, Panayota Georgakopoulou, Valia Kordoni, Markus Egg, Katia Lida Kermanidis |
| Abstract | |
| Tasks | Machine Translation, Transfer Learning |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1528/ |
| https://www.aclweb.org/anthology/L18-1528 | |
| PWC | https://paperswithcode.com/paper/improving-machine-translation-of-educational |
| Repo | |
| Framework | |
