October 15, 2019

2141 words 11 mins read

Paper Group NANR 259

Paper Group NANR 259

Learning to Act in Decentralized Partially Observable MDPs. Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources. Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields. Sentence Suggestion of Japanese Functional Expressions for Chinese-speaking Learners. Enabling Efficient Verifiable …

Learning to Act in Decentralized Partially Observable MDPs

Title Learning to Act in Decentralized Partially Observable MDPs
Authors Jilles Dibangoye, Olivier Buffet
Abstract We address a long-standing open problem of reinforcement learning in decentralized partially observable Markov decision processes. Previous attempts focussed on different forms of generalized policy iteration, which at best led to local optima. In this paper, we restrict attention to plans, which are simpler to store and update than policies. We derive, under certain conditions, the first near-optimal cooperative multi-agent reinforcement learning algorithm. To achieve significant scalability gains, we replace the greedy maximization by mixed-integer linear programming. Experiments show our approach can learn to act near-optimally in many finite domains from the literature.
Tasks Multi-agent Reinforcement Learning
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2278
PDF http://proceedings.mlr.press/v80/dibangoye18a/dibangoye18a.pdf
PWC https://paperswithcode.com/paper/learning-to-act-in-decentralized-partially
Repo
Framework

Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources

Title Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources
Authors Stefano Melacci, Achille Globo, Leonardo Rigutini
Abstract
Tasks Word Embeddings, Word Sense Disambiguation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1163/
PDF https://www.aclweb.org/anthology/L18-1163
PWC https://paperswithcode.com/paper/enhancing-modern-supervised-word-sense
Repo
Framework

Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields

Title Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields
Authors Kejie Li, Trung Pham, Huangying Zhan, Ian Reid
Abstract Most existing CNN-based methods for single-view 3D object reconstruction represent a 3D object as either a 3D voxel occupancy grid or multiple depth-mask image pairs. However, these representations are inefficient since empty voxels or background pixels are wasteful. We propose a novel approach that addresses this limitation by replacing masks with ‘‘deformation-fields’'. Given a single image at an arbitrary viewpoint, a CNN predicts multiple surfaces, each in a canonical location relative to the object. Each surface comprises a depth-map and corresponding deformation-field that ensures every pixel-depth pair in the depth-map lies on the object surface. These surfaces are then fused to form the full 3D shape. During training, we use a combination of per-view and multi-view losses. The novel multi-view loss encourages the 3D points back-projected from a particular view to be consistent across views. Extensive experiments demonstrate the efficiency and efficacy of our method on single-view 3D object reconstruction.
Tasks 3D Object Reconstruction, Object Reconstruction
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Kejie_Li_Efficient_Dense_Point_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Kejie_Li_Efficient_Dense_Point_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/efficient-dense-point-cloud-object
Repo
Framework

Sentence Suggestion of Japanese Functional Expressions for Chinese-speaking Learners

Title Sentence Suggestion of Japanese Functional Expressions for Chinese-speaking Learners
Authors Jun Liu, Hiroyuki Shindo, Yuji Matsumoto
Abstract We present a computer-assisted learning system, Jastudy, which is particularly designed for Chinese-speaking learners of Japanese as a second language (JSL) to learn Japanese functional expressions with suggestion of appropriate example sentences. The system automatically recognizes Japanese functional expressions using a free Japanese morphological analyzer MeCab, which is retrained on a new Conditional Random Fields (CRF) model. In order to select appropriate example sentences, we apply a pairwise-based machine learning tool, Support Vector Machine for Ranking (SVMrank) to estimate the complexity of the example sentences using Japanese{–}Chinese homographs as an important feature. In addition, we cluster the example sentences that contain Japanese functional expressions with two or more meanings and usages, based on part-of-speech, conjugation forms of verbs and semantic attributes, using the K-means clustering algorithm in Scikit-Learn. Experimental results demonstrate the effectiveness of our approach.
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-4010/
PDF https://www.aclweb.org/anthology/P18-4010
PWC https://paperswithcode.com/paper/sentence-suggestion-of-japanese-functional
Repo
Framework

Enabling Efficient Verifiable Fuzzy Keyword Search Over Encrypted Data in Cloud Computing

Title Enabling Efficient Verifiable Fuzzy Keyword Search Over Encrypted Data in Cloud Computing
Authors XINRUI GE, JIA YU, CHENGYU HU, HANLIN ZHANG, AND RONG HAO
Abstract Searchable encryption can support data user to selectively retrieve the cipher documents over encrypted cloud data by keyword-based search. Most of the existing searchable encryption schemes only focus on the exact keyword search. When data user makes spelling errors, these schemes fail to return the result of interest. In searchable encryption, the cloud server might return the invalid result to data user for saving the computation cost or other reasons. Therefore, these exact keyword search schemes find little practical significance in real-world applications. In order to address these issues, we propose a novel verifiable fuzzy keyword search scheme over encrypted cloud data. For the purpose of introducing this scheme, we first propose a verifiable exact keyword search scheme and then extend this scheme to the fuzzy keyword search scheme. In the fuzzy keyword search scheme, we employ the linked list as our secure index to achieve the efficient storage. We construct a linked list with three nodes for each exact keyword and generate a fuzzy keyword set for it. To reduce the computation cost and the storage space, we generate one index vector for each fuzzy keyword set, rather than each fuzzy keyword. To resist malicious behaviors of the cloud server, we generate an authentication label for each fuzzy keyword to verify the authenticity of the returned ciphertexts. Through security analysis and experiment evaluation, we show that our proposed schemes are secure and efficient.
Tasks
Published 2018-08-17
URL https://ieeexplore.ieee.org/document/8438878
PDF https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8438878
PWC https://paperswithcode.com/paper/enabling-efficient-verifiable-fuzzy-keyword
Repo
Framework

Scalable Visualisation of Sentiment and Stance

Title Scalable Visualisation of Sentiment and Stance
Authors Jon Chamberlain, Udo Kruschwitz, Orl Hoeber,
Abstract
Tasks Information Retrieval, Opinion Mining, Time Series
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1660/
PDF https://www.aclweb.org/anthology/L18-1660
PWC https://paperswithcode.com/paper/scalable-visualisation-of-sentiment-and
Repo
Framework

Building Named Entity Recognition Taggers via Parallel Corpora

Title Building Named Entity Recognition Taggers via Parallel Corpora
Authors Rodrigo Agerri, Yiling Chung, Itziar Aldabe, Nora Aranberri, Gorka Labaka, German Rigau
Abstract
Tasks Machine Translation, Named Entity Recognition, Word Alignment, Word Sense Disambiguation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1557/
PDF https://www.aclweb.org/anthology/L18-1557
PWC https://paperswithcode.com/paper/building-named-entity-recognition-taggers-via
Repo
Framework

Automatically Inferring Data Quality for Spatiotemporal Forecasting

Title Automatically Inferring Data Quality for Spatiotemporal Forecasting
Authors Sungyong Seo, Arash Mohegh, George Ban-Weiss, Yan Liu
Abstract Spatiotemporal forecasting has become an increasingly important prediction task in machine learning and statistics due to its vast applications, such as climate modeling, traffic prediction, video caching predictions, and so on. While numerous studies have been conducted, most existing works assume that the data from different sources or across different locations are equally reliable. Due to cost, accessibility, or other factors, it is inevitable that the data quality could vary, which introduces significant biases into the model and leads to unreliable prediction results. The problem could be exacerbated in black-box prediction models, such as deep neural networks. In this paper, we propose a novel solution that can automatically infer data quality levels of different sources through local variations of spatiotemporal signals without explicit labels. Furthermore, we integrate the estimate of data quality level with graph convolutional networks to exploit their efficient structures. We evaluate our proposed method on forecasting temperatures in Los Angeles.
Tasks Traffic Prediction
Published 2018-01-01
URL https://openreview.net/forum?id=ByJIWUnpW
PDF https://openreview.net/pdf?id=ByJIWUnpW
PWC https://paperswithcode.com/paper/automatically-inferring-data-quality-for
Repo
Framework

A Neural Network Model for Part-Of-Speech Tagging of Social Media Texts

Title A Neural Network Model for Part-Of-Speech Tagging of Social Media Texts
Authors Sara Meftah, Nasredine Semmar
Abstract
Tasks Part-Of-Speech Tagging, Transfer Learning
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1446/
PDF https://www.aclweb.org/anthology/L18-1446
PWC https://paperswithcode.com/paper/a-neural-network-model-for-part-of-speech
Repo
Framework

De-identifying Free Text of Japanese Dummy Electronic Health Records

Title De-identifying Free Text of Japanese Dummy Electronic Health Records
Authors Kohei Kajiyama, Hiromasa Horiguchi, Takashi Okumura, Mizuki Morita, Yoshinobu Kano
Abstract A new law was established in Japan to promote utilization of EHRs for research and developments, while de-identification is required to use EHRs. However, studies of automatic de-identification in the healthcare domain is not active for Japanese language, no de-identification tool available in practical performance for Japanese medical domains, as far as we know. Previous work shows that rule-based methods are still effective, while deep learning methods are reported to be better recently. In order to implement and evaluate a de-identification tool in a practical level, we implemented three methods, rule-based, CRF, and LSTM. We prepared three datasets of pseudo EHRs with de-identification tags manually annotated. These datasets are derived from shared task data to compare with previous work, and our new data to increase training data. Our result shows that our LSTM-based method is better and robust, which leads to our future work that plans to apply our system to actual de-identification tasks in hospitals.
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5608/
PDF https://www.aclweb.org/anthology/W18-5608
PWC https://paperswithcode.com/paper/de-identifying-free-text-of-japanese-dummy
Repo
Framework

Similar but not the Same: Word Sense Disambiguation Improves Event Detection via Neural Representation Matching

Title Similar but not the Same: Word Sense Disambiguation Improves Event Detection via Neural Representation Matching
Authors Weiyi Lu, Thien Huu Nguyen
Abstract Event detection (ED) and word sense disambiguation (WSD) are two similar tasks in that they both involve identifying the classes (i.e. event types or word senses) of some word in a given sentence. It is thus possible to extract the knowledge hidden in the data for WSD, and utilize it to improve the performance on ED. In this work, we propose a method to transfer the knowledge learned on WSD to ED by matching the neural representations learned for the two tasks. Our experiments on two widely used datasets for ED demonstrate the effectiveness of the proposed method.
Tasks Word Sense Disambiguation
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1517/
PDF https://www.aclweb.org/anthology/D18-1517
PWC https://paperswithcode.com/paper/similar-but-not-the-same-word-sense
Repo
Framework

Learning How to Actively Learn: A Deep Imitation Learning Approach

Title Learning How to Actively Learn: A Deep Imitation Learning Approach
Authors Ming Liu, Wray Buntine, Gholamreza Haffari
Abstract Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary. We introduce a method that learns an AL {}policy{''} using {}imitation learning{''} (IL). Our IL-based approach makes use of an efficient and effective {``}algorithmic expert{''}, which provides the policy learner with good actions in the encountered AL situations. The AL strategy is then learned with a feedforward network, mapping situations to most informative query datapoints. We evaluate our method on two different tasks: text classification and named entity recognition. Experimental results show that our IL-based AL strategy is more effective than strong previous methods using heuristics and reinforcement learning. |
Tasks Active Learning, Imitation Learning, Named Entity Recognition, Text Classification
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1174/
PDF https://www.aclweb.org/anthology/P18-1174
PWC https://paperswithcode.com/paper/learning-how-to-actively-learn-a-deep
Repo
Framework

Counterfactual Image Networks

Title Counterfactual Image Networks
Authors Deniz Oktay, Carl Vondrick, Antonio Torralba
Abstract We capitalize on the natural compositional structure of images in order to learn object segmentation with weakly labeled images. The intuition behind our approach is that removing objects from images will yield natural images, however removing random patches will yield unnatural images. We leverage this signal to develop a generative model that decomposes an image into layers, and when all layers are combined, it reconstructs the input image. However, when a layer is removed, the model learns to produce a different image that still looks natural to an adversary, which is possible by removing objects. Experiments and visualizations suggest that this model automatically learns object segmentation on images labeled only by scene better than baselines.
Tasks Semantic Segmentation
Published 2018-01-01
URL https://openreview.net/forum?id=SyYYPdg0-
PDF https://openreview.net/pdf?id=SyYYPdg0-
PWC https://paperswithcode.com/paper/counterfactual-image-networks
Repo
Framework

Parallel Bayesian Network Structure Learning

Title Parallel Bayesian Network Structure Learning
Authors Tian Gao, Dennis Wei
Abstract Recent advances in Bayesian Network (BN) structure learning have focused on local-to-global learning, where the graph structure is learned via one local subgraph at a time. As a natural progression, we investigate parallel learning of BN structures via multiple learning agents simultaneously, where each agent learns one local subgraph at a time. We find that parallel learning can reduce the number of subgraphs requiring structure learning by storing previously queried results and communicating (even partial) results among agents. More specifically, by using novel rules on query subset and superset inference, many subgraph structures can be inferred without learning. We provide a sound and complete parallel structure learning (PSL) algorithm, and demonstrate its improved efficiency over state-of-the-art single-thread learning algorithms.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=1918
PDF http://proceedings.mlr.press/v80/gao18b/gao18b.pdf
PWC https://paperswithcode.com/paper/parallel-bayesian-network-structure-learning
Repo
Framework

Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning

Title Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning
Authors Sotiris Lamprinidis, Daniel Hardt, Dirk Hovy
Abstract Newspapers need to attract readers with headlines, anticipating their readers{'} preferences. These preferences rely on topical, structural, and lexical factors. We model each of these factors in a multi-task GRU network to predict headline popularity. We find that pre-trained word embeddings provide significant improvements over untrained embeddings, as do the combination of two auxiliary tasks, news-section prediction and part-of-speech tagging. However, we also find that performance is very similar to that of a simple Logistic Regression model over character n-grams. Feature analysis reveals structural patterns of headline popularity, including the use of forward-looking deictic expressions and second person pronouns.
Tasks Multi-Task Learning, Part-Of-Speech Tagging, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1068/
PDF https://www.aclweb.org/anthology/D18-1068
PWC https://paperswithcode.com/paper/predicting-news-headline-popularity-with
Repo
Framework
comments powered by Disqus