检索结果-内蒙古大学图书馆

Addressing word-order divergence in multilingual neural machine translation for extremely low resource languages

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Rudra Murthy, V. Kunchukuttan, Anoop Bhattacharyya, Pushpak Department of Computer Science and Engineering IIT Bombay India Microsoft AI & Research Hyderabad India

Transfer learning approaches for Neural Machine Translation (NMT) trains a NMT model on an assisting language-target language pair (parent model) which is later fine-tuned for the source language-target language pair of interest (child model), with the target language being the same. In many cases, the assisting language has a different word order from the source language. We show that divergent word order adversely limits the benefits from transfer learning when little to no parallel corpus between the source and target language is available. To bridge this divergence, we propose to pre-order the assisting language sentences to match the word order of the source language and train the parent model. Our experiments on many language pairs show that bridging the word order gap leads to major improvements in the translation quality in extremely low-resource scenarios. Copyright © 2018, The Authors. All rights reserved.

关键词： Neural machine translation

GenSense: A generalized sense retrofitting model 27

学校读者我要写书评

暂无评论

GenSense: A generalized sense retrofitting model

27th International Conference on Computational Linguistics, COLING 2018

作者： Lee, Yang-Yin Yen, Ting-Yu Huang, Hen-Hsen Shiue, Yow-Ting Chen, Hsin-Hsi Department of Computer Science and Information Engineering National Taiwan University No. 1 Sec. 4 Roosevelt Road Taipei10617 Taiwan MOST Joint Research Center for AI Technology All Vista Healthcare Taiwan

ISBN: (纸本)9781948087506

With the aid of recently proposed word embedding algorithms, the study of semantic similarity has progressed and advanced rapidly. However, many natural language processing tasks need sense level representation. To address this issue, some researches propose sense embedding learning algorithms. In this paper, we present a generalized model from the existing sense retrofitting model. The generalization takes three major components: semantic relations between the senses, the relation strength and the semantic strength. In the experiments, we show that the generalized model outperforms the previous approaches in three aspects: semantic relatedness, contextual word similarity and semantic difference. © 2018 COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings. All rights reserved.

关键词： Retrofitting

Flow-based sampling for multimodal and extended-mode distributions in lattice field theory

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hackett, Daniel C. Hsieh, Chung-Chun Pontula, Sahil Albergo, Michael S. Boyda, Denis Chen, Jiunn-Wei Chen, Kai-Feng Cranmer, Kyle Kanwar, Gurtej Shanahan, Phiala E. Center for Theoretical Physics Massachusetts Institute of Technology CambridgeMA02139 United States The NSF AI Institute for Artificial Intelligence and Fundamental Interactions United States Fermi National Accelerator Laboratory BataviaIL60510 United States Department of Physics Center for Theoretical Physics National Taiwan University Taipei106 Taiwan Department of Physics University of Maryland College ParkMD20742 United States Maryland Center for Fundamental Physics University of Maryland College ParkMD20742 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Society of Fellows Harvard University CambridgeMA02138 United States Physics Division National Center for Theoretical Sciences Taipei10617 Taiwan Leung Center for Cosmology and Particle Astrophysics National Taiwan University Taipei106 Taiwan Department of Physics Data Science Institute University of Wisconsin–Madison MadisonWI53706 United States Higgs Centre for Theoretical Physics University of Edinburgh EdinburghEH9 3FD United Kingdom

Recent results have demonstrated that samplers constructed with flow-based generative models are a promising new approach for configuration generation in lattice field theory. In this paper, we present a set of training- and architecture-based methods to construct flow models for targets with multiple separated modes (i.e. vacua) as well as targets with extended/continuous modes. We demonstrate the application of these methods to modeling two-dimensional real and complex scalar field theories in their symmetry-broken phases. In this context we investigate different flow-based sampling algorithms, including a composite sampling algorithm where flow-based proposals are occasionally augmented by applying updates using traditional algorithms like HMC. Copyright © 2021, The Authors. All rights reserved.

关键词： Lattice theory

Improving the improved training of wasserstein gans: A consistency term and its dual effect 6

学校读者我要写书评

暂无评论

Improving the improved training of wasserstein gans: A consi...

6th International Conference on Learning Representations, ICLR 2018

作者： Wei, Xiang Gong, Boqing Liu, Zixia Lu, Wei Wang, Liqiang Department of Computer Science University of Central Florida OrlandoFL32816 United States School of Software Engineering Beijing Jiaotong University Beijing100044 China Tencent AI Lab BellevueWA98004 United States

Despite being impactful on a variety of problems and applications, the generative adversarial nets (GANs) are remarkably difficult to train. This issue is formally analyzed by Arjovsky & Bottou (2017), who also propose an alternative direction to avoid the caveats in the minmax two-player training of GANs. The corresponding algorithm, called Wasserstein GAN (WGAN), hinges on the 1-Lipschitz continuity of the discriminator. In this paper, we propose a novel approach to enforcing the Lipschitz continuity in the training procedure of WGANs. Our approach seamlessly connects WGAN with one of the recent semi-supervised learning methods. As a result, it gives rise to not only better photo-realistic samples than the previous methods but also state-of-the-art semi-supervised learning results. In particular, our approach gives rise to the inception score of more than 5.0 with only 1,000 CIFAR-10 images and is the first that exceeds the accuracy of 90% on the CIFAR-10 dataset using only 4,000 labeled images, to the best of our knowledge. © 2018 International Conference on Learning Representations, ICLR. All rights reserved.

关键词： Generative adversarial networks

Memorizing all for implicit discourse relation recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Bai, Hongxiao Zhao, Hai Zhao, Junhan Department of Computer Science and Engineering Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence Ai Institute Shanghai Jiao Tong University Computer Graphics Technology Purdue University West LafayetteIN United States

Implicit discourse relation recognition is a challenging task due to the absence of the nec-essary informative clue from explicit connec-tives. The prediction of relations requires a deep understanding of the semantic meanings of sentence pairs. As implicit discourse relation recognizer has to carefully tackle the se-mantic similarity of the given sentence pairs and the severe data sparsity issue exists in the meantime, it is supposed to be beneficial from mastering the entire training data. Thus in this paper, we propose a novel memory mecha-nism to tackle the challenges for further performance improvement. The memory mecha-nism is adequately memorizing information by pairing representations and discourse relations of all training instances, which right fills the slot of the data-hungry issue in the current im-plicit discourse relation recognizer. Our experiments show that our full model with memo-rizing the entire training set reaches new state-of-the-art against strong baselines, which es-pecially for the first time exceeds the milestone of 60% accuracy in the 4-way task. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

Latent dirichlet allocation for internet price war

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Chenchen Yan, Xiang Deng, Xiaotie Qi, Yuan Chu, Wei Song, Le Qiao, Junlong He, Jianshan Xiong, Junwu AI Department Ant Financial Services Group Department of Computer Science Shanghai Jiao Tong University School of Electronics Engineering and Computer Science Peking University

Internet market makers are always facing intense competitive environment, where personalized price reductions or discounted coupons are provided for attracting more customers. Participants in such a price war scenario have to invest a lot to catch up with other competitors. However, such a huge cost of money may not always lead to an improvement of market share. This is mainly due to a lack of information about others' strategies or customers' willingness when participants develop their strategies. In order to obtain this hidden information through observable data, we study the relationship between companies and customers in the Internet price war. Theoretically, we provide a formalization of the problem as a stochastic game with imperfect and incomplete information. Then we develop a variant of Latent Dirichlet Allocation (LDA) to infer latent variables under the current market environment, which represents the preferences of customers and strategies of competitors. To our best knowledge, it is the first time that LDA is applied to game scenario. We conduct simulated experiments where our LDA model exhibits a significant improvement on finding strategies in the Internet price war by including all available market information of the market maker's competitors. And the model is applied to an open dataset for real business. Through comparisons on the likelihood of prediction for users' behavior and distribution distance between inferred opponent's strategy and the real one, our model is shown to be able to provide a better understanding for the market environment. Our work marks a successful learning method to infer latent information in the environment of price war by the LDA modeling, and sets an example for related competitive applications to follow. Copyright © 2018, The Authors. All rights reserved.

关键词： Competition

Reinforcement Learning for Uplift Modeling

学校读者我要写书评

暂无评论

arXiv 2018年

Uplift modeling aims to directly model the incremental impact of a treatment on an individual response. In this work, we address the problem from a new angle and reformulate it as a Markov Decision Process (MDP). We conducted extensive experiments on both a synthetic dataset and real-world scenarios, and showed that our method can achieve significant improvement over previous methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Markov processes

Named entity recognition only from word embeddings

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Luo, Ying Zhao, Hai Zhan, Junlang Department of Computer Science and Engineering Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence Ai Institute Shanghai Jiao Tong University Shanghai China

Deep neural network models have helped named entity (NE) recognition achieve amaz-ing performance without handcrafting features. However, existing systems require large amounts of human annotated training data. Ef-forts have been made to replace human annota-tions with external knowledge (e.g., NE dictio-nary, part-of-speech tags), while it is another challenge to obtain such effective resources. In this work, we propose a fully unsupervised NE recognition model which only needs to take informative clues from pre-trained word embeddings. We first apply Gaussian Hid-den Markov Model and Deep Autoencoding Gaussian Mixture Model on word embeddings for entity span detection and type prediction, and then further design an instance selec-tor based on reinforcement learning to distin-guish positive sentences from noisy sentences and refine these coarse-grained annotations through neural networks. Extensive experiments on CoNLL benchmark datasets demon-strate that our proposed light NE recognition model achieves remarkable performance with-out using any annotated lexicon or corpus. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

Data analytics for fog computing by distributed online learning with asynchronous update

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Guangxia Zhao, Peilin Lu, Xiao Liu, Jia Shen, Yulong Shaanxi Key Laboratory of Network and System Security Xidian University China State Key Laboratory of Integrated Service Networks Xidian University China School of Computer Science and Technology Xidian University China Tencent AI Lab Tencent Inc. China Department of Electrical and Computer Engineering University of Alberta Canada

—Fog computing extends the cloud computing paradigm by allocating substantial portions of computations and services towards the edge of a network, and is, therefore, particularly suitable for large-scale, geo-distributed, and data-intensive applications. As the popularity of fog applications increases, there is a demand for the development of smart data analytic tools, which can process massive data streams in an efficient manner. To satisfy such requirements, we propose a system in which data streams generated from distributed sources are digested almost locally, whereas a relatively small amount of distilled information is converged to a center. The center extracts knowledge from the collected information, and shares it across all subordinates to boost their performances. Upon the proposed system, we devise a distributed machine learning algorithm using the online learning approach, which is well known for its high efficiency and innate ability to cope with streaming data. An asynchronous update strategy with rigorous theoretical support is applied to enhance the system robustness. Experimental results demonstrate that the proposed method is comparable with a model trained over a centralized platform in terms of the classification accuracy, whereas the efficiency and scalability of the overall system are improved. Copyright © 2019, The Authors. All rights reserved.

关键词： Fog computing