October 15, 2019

1878 words 9 mins read

Paper Group NANR 131

Paper Group NANR 131

Distributed Multi-Player Bandits - a Game of Thrones Approach. Finite-state morphological analysis for Gagauz. Building Parallel Monolingual Gan Chinese Dialects Corpus. Deep Learning for Musculoskeletal Force Prediction. Document-Level Information as Side Constraints for Improved Neural Patent Translation. Large-scale spectral clustering using dif …

Distributed Multi-Player Bandits - a Game of Thrones Approach

Title Distributed Multi-Player Bandits - a Game of Thrones Approach
Authors Ilai Bistritz, Amir Leshem
Abstract We consider a multi-armed bandit game where N players compete for K arms for T turns. Each player has different expected rewards for the arms, and the instantaneous rewards are independent and identically distributed. Performance is measured using the expected sum of regrets, compared to the optimal assignment of arms to players. We assume that each player only knows her actions and the reward she received each turn. Players cannot observe the actions of other players, and no communication between players is possible. We present a distributed algorithm and prove that it achieves an expected sum of regrets of near-O\left(\log^{2}T\right). This is the first algorithm to achieve a poly-logarithmic regret in this fully distributed scenario. All other works have assumed that either all players have the same vector of expected rewards or that communication between players is possible.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7952-distributed-multi-player-bandits-a-game-of-thrones-approach
PDF http://papers.nips.cc/paper/7952-distributed-multi-player-bandits-a-game-of-thrones-approach.pdf
PWC https://paperswithcode.com/paper/distributed-multi-player-bandits-a-game-of
Repo
Framework

Finite-state morphological analysis for Gagauz

Title Finite-state morphological analysis for Gagauz
Authors Francis Tyers, Sevilay Bayatli, G{"u}ll{"u} Karanfil, Memduh G{"o}k{\i}rmak, Francis M. Tyers
Abstract
Tasks Morphological Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1411/
PDF https://www.aclweb.org/anthology/L18-1411
PWC https://paperswithcode.com/paper/finite-state-morphological-analysis-for
Repo
Framework

Building Parallel Monolingual Gan Chinese Dialects Corpus

Title Building Parallel Monolingual Gan Chinese Dialects Corpus
Authors Fan Xu, Mingwen Wang, Maoxi Li
Abstract
Tasks Language Identification
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1036/
PDF https://www.aclweb.org/anthology/L18-1036
PWC https://paperswithcode.com/paper/building-parallel-monolingual-gan-chinese
Repo
Framework

Deep Learning for Musculoskeletal Force Prediction

Title Deep Learning for Musculoskeletal Force Prediction
Authors Lance Rane, Ziyun Ding, Alison H. McGregor, Anthony M. J. Bull
Abstract Musculoskeletal models permit the determination of internal forces acting during dynamic movement, which is clinically useful, but traditional methods may suffer from slowness and a need for extensive input data. Recently, there has been interest in the use of supervised learning to build approximate models for computationally demanding processes, with benefits in speed and flexibility. Here, we use a deep neural network to learn the mapping from movement space to muscle space. Trained on a set of kinematic, kinetic and electromyographic measurements from 156 subjects during gait, the network’s predictions of internal force magnitudes show good concordance with those derived by musculoskeletal modelling. In a separate set of experiments, training on data from the most widely known benchmarks of modelling performance, the international Grand Challenge competitions, generates predictions that better those of the winning submissions in four of the six competitions. Computational speedup facilitates incorporation into a lab-based system permitting real-time estimation of forces, and interrogation of the trained neural networks provides novel insights into population-level relationships between kinematic and kinetic factors.
Tasks Electromyography (EMG), EMG Signal Prediction, Medial knee JRF Prediction, Muscle Force Prediction
Published 2018-12-13
URL https://doi.org/10.1007/s10439-018-02190-0
PDF https://link.springer.com/content/pdf/10.1007%2Fs10439-018-02190-0.pdf
PWC https://paperswithcode.com/paper/deep-learning-for-musculoskeletal-force
Repo
Framework

Document-Level Information as Side Constraints for Improved Neural Patent Translation

Title Document-Level Information as Side Constraints for Improved Neural Patent Translation
Authors Laura Jehl, Stefan Riezler
Abstract
Tasks Machine Translation
Published 2018-03-01
URL https://www.aclweb.org/anthology/W18-1802/
PDF https://www.aclweb.org/anthology/W18-1802
PWC https://paperswithcode.com/paper/document-level-information-as-side
Repo
Framework

Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs

Title Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs
Authors Khiem Pham, Guangliang Chen
Abstract Spectral clustering has received a lot of attention due to its ability to separate nonconvex, non-intersecting manifolds, but its high computational complexity has significantly limited its applicability. Motivated by the document-term co-clustering framework by Dhillon (2001), we propose a landmark-based scalable spectral clustering approach in which we first use the selected landmark set and the given data to form a bipartite graph and then run a diffusion process on it to obtain a family of diffusion coordinates for clustering. We show that our proposed algorithm can be implemented based on very efficient operations on the affinity matrix between the given data and selected landmarks, thus capable of handling large data. Finally, we demonstrate the excellent performance of our method by comparing with the state-of-the-art scalable algorithms on several benchmark data sets.
Tasks Semantic Segmentation
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-1705/
PDF https://www.aclweb.org/anthology/W18-1705
PWC https://paperswithcode.com/paper/large-scale-spectral-clustering-using
Repo
Framework

ELiRF-UPV at SemEval-2018 Tasks 1 and 3: Affect and Irony Detection in Tweets

Title ELiRF-UPV at SemEval-2018 Tasks 1 and 3: Affect and Irony Detection in Tweets
Authors Jos{'e}-{'A}ngel Gonz{'a}lez, Llu{'\i}s-F. Hurtado, Ferran Pla
Abstract This paper describes the participation of ELiRF-UPV team at tasks 1 and 3 of Semeval-2018. We present a deep learning based system that assembles Convolutional Neural Networks and Long Short-Term Memory neural networks. This system has been used with slight modifications for the two tasks addressed both for English and Spanish. Finally, the results obtained in the competition are reported and discussed.
Tasks Emotion Classification, Sentiment Analysis
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1092/
PDF https://www.aclweb.org/anthology/S18-1092
PWC https://paperswithcode.com/paper/elirf-upv-at-semeval-2018-tasks-1-and-3
Repo
Framework

What Action Causes This? Towards Naive Physical Action-Effect Prediction

Title What Action Causes This? Towards Naive Physical Action-Effect Prediction
Authors Qiaozi Gao, Shaohua Yang, Joyce Chai, V, Lucy erwende
Abstract Despite recent advances in knowledge representation, automated reasoning, and machine learning, artificial agents still lack the ability to understand basic action-effect relations regarding the physical world, for example, the action of cutting a cucumber most likely leads to the state where the cucumber is broken apart into smaller pieces. If artificial agents (e.g., robots) ever become our partners in joint tasks, it is critical to empower them with such action-effect understanding so that they can reason about the state of the world and plan for actions. Towards this goal, this paper introduces a new task on naive physical action-effect prediction, which addresses the relations between concrete actions (expressed in the form of verb-noun pairs) and their effects on the state of the physical world as depicted by images. We collected a dataset for this task and developed an approach that harnesses web image data through distant supervision to facilitate learning for action-effect prediction. Our empirical results have shown that web data can be used to complement a small number of seed examples (e.g., three examples for each action) for model learning. This opens up possibilities for agents to learn physical action-effect relations for tasks at hand through communication with humans with a few examples.
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1086/
PDF https://www.aclweb.org/anthology/P18-1086
PWC https://paperswithcode.com/paper/what-action-causes-this-towards-naive
Repo
Framework

Improving Topic Quality by Promoting Named Entities in Topic Modeling

Title Improving Topic Quality by Promoting Named Entities in Topic Modeling
Authors Katsiaryna Krasnashchok, Salim Jouili
Abstract News related content has been extensively studied in both topic modeling research and named entity recognition. However, expressive power of named entities and their potential for improving the quality of discovered topics has not received much attention. In this paper we use named entities as domain-specific terms for news-centric content and present a new weighting model for Latent Dirichlet Allocation. Our experimental results indicate that involving more named entities in topic descriptors positively influences the overall quality of topics, improving their interpretability, specificity and diversity.
Tasks Named Entity Recognition
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-2040/
PDF https://www.aclweb.org/anthology/P18-2040
PWC https://paperswithcode.com/paper/improving-topic-quality-by-promoting-named
Repo
Framework

Conversational Image Editing: Incremental Intent Identification in a New Dialogue Task

Title Conversational Image Editing: Incremental Intent Identification in a New Dialogue Task
Authors Ramesh Manuvinakurike, Trung Bui, Walter Chang, Kallirroi Georgila
Abstract We present {``}conversational image editing{''}, a novel real-world application domain combining dialogue, visual information, and the use of computer vision. We discuss the importance of dialogue incrementality in this task, and build various models for incremental intent identification based on deep learning and traditional classification algorithms. We show how our model based on convolutional neural networks outperforms models based on random forests, long short term memory networks, and conditional random fields. By training embeddings based on image-related dialogue corpora, we outperform pre-trained out-of-the-box embeddings, for intention identification tasks. Our experiments also provide evidence that incremental intent processing may be more efficient for the user and could save time in accomplishing tasks. |
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5033/
PDF https://www.aclweb.org/anthology/W18-5033
PWC https://paperswithcode.com/paper/conversational-image-editing-incremental
Repo
Framework

Coreference and Focus in Reading Times

Title Coreference and Focus in Reading Times
Authors Evan Jaffe, Cory Shain, William Schuler
Abstract
Tasks Coreference Resolution
Published 2018-01-01
URL https://www.aclweb.org/anthology/W18-0101/
PDF https://www.aclweb.org/anthology/W18-0101
PWC https://paperswithcode.com/paper/coreference-and-focus-in-reading-times
Repo
Framework

Deep Continuous Fusion for Multi-Sensor 3D Object Detection

Title Deep Continuous Fusion for Multi-Sensor 3D Object Detection
Authors Ming Liang, Bin Yang, Shenlong Wang, Raquel Urtasun
Abstract In this paper, we propose a novel 3D object detector that can exploit both LIDAR as well as cameras to perform very accurate localization. Towards this goal, we design an end-to-end learnable architecture that exploits continuous convolutions to fuse image and LIDAR feature maps at different levels of resolution. Our proposed continuous fusion layer encode both discrete-state image features as well as continuous geometric information. This enables us to design a novel, reliable and efficient end-to-end learnable 3D object detector based on multiple sensors. Our experimental evaluation on both KITTI as well as a large scale 3D object detection benchmark shows significant improvements over the state of the art.
Tasks 3D Object Detection, Object Detection
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Ming_Liang_Deep_Continuous_Fusion_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Ming_Liang_Deep_Continuous_Fusion_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/deep-continuous-fusion-for-multi-sensor-3d
Repo
Framework

Affordances in Grounded Language Learning

Title Affordances in Grounded Language Learning
Authors Stephen McGregor, KyungTae Lim
Abstract We present a novel methodology involving mappings between different modes of semantic representation. We propose distributional semantic models as a mechanism for representing the kind of world knowledge inherent in the system of abstract symbols characteristic of a sophisticated community of language users. Then, motivated by insight from ecological psychology, we describe a model approximating affordances, by which we mean a language learner{'}s direct perception of opportunities for action in an environment. We present a preliminary experiment involving mapping between these two representational modalities, and propose that our methodology can become the basis for a cognitively inspired model of grounded language learning.
Tasks Question Answering
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2806/
PDF https://www.aclweb.org/anthology/W18-2806
PWC https://paperswithcode.com/paper/affordances-in-grounded-language-learning
Repo
Framework

Landmark based localization in urban environment

Title Landmark based localization in urban environment
Authors Xiaozhi Qu, Bahman Soheilian, Nicolas Paparoditis
Abstract A landmark based localization with uncertainty analysis based on cameras and geo-referenced landmarks is presented in this paper. The system is developed to adapt different camera configurations for six degree-of-freedom pose estimation. Local bundle adjustment is applied for optimization and the geo- referenced landmarks are integrated to reduce the drift. In particular, the uncertainty analysis is taken into account. On the one hand, we estimate the uncertainties of poses to predict the precision of localiza- tion. On the other hand, uncertainty propagation is considered for matching, tracking and landmark reg- istering. The proposed method is evaluated on both KITTI benchmark and the data acquired by a mobile mapping system. In our experiments, decimeter level accuracy can be reached.
Tasks Pose Estimation
Published 2018-01-01
URL https://www.sciencedirect.com/science/article/abs/pii/S0924271617302228
PDF https://pan.baidu.com/s/1xx4mfpMkZVyj9bRtmiTLRg
PWC https://paperswithcode.com/paper/landmark-based-localization-in-urban
Repo
Framework

Errator: a Tool to Help Detect Annotation Errors in the Universal Dependencies Project

Title Errator: a Tool to Help Detect Annotation Errors in the Universal Dependencies Project
Authors Guillaume Wisniewski
Abstract
Tasks Cross-Lingual Transfer, Machine Translation, Tokenization
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1711/
PDF https://www.aclweb.org/anthology/L18-1711
PWC https://paperswithcode.com/paper/errator-a-tool-to-help-detect-annotation
Repo
Framework
comments powered by Disqus