Paper Group NANR 122
Exploring the Hidden Dimension in Accelerating Convolutional Neural Networks. Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models. Synthetically Supervised Feature Learning for Scene Text Recognition. Transferred Embeddings for Igbo Similarity, Analogy, and Diacritic Restoration Tasks. Pulling Actions out of Context: E …
Exploring the Hidden Dimension in Accelerating Convolutional Neural Networks
| Title | Exploring the Hidden Dimension in Accelerating Convolutional Neural Networks |
| Authors | Zhihao Jia, Sina Lin, Charles R. Qi, Alex Aiken |
| Abstract | DeePa is a deep learning framework that explores parallelism in all parallelizable dimensions to accelerate the training process of convolutional neural networks. DeePa optimizes parallelism at the granularity of each individual layer in the network. We present an elimination-based algorithm that finds an optimal parallelism configuration for every layer. Our evaluation shows that DeePa achieves up to 6.5× speedup compared to state-of-the-art deep learning frameworks and reduces data transfers by up to 23×. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SJCPLLpaW |
| https://openreview.net/pdf?id=SJCPLLpaW | |
| PWC | https://paperswithcode.com/paper/exploring-the-hidden-dimension-in |
| Repo | |
| Framework | |
Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models
| Title | Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models |
| Authors | Thanapon Noraset, Doug Downey, Lidong Bing |
| Abstract | Recurrent neural network language models (RNNLMs) are the current standard-bearer for statistical language modeling. However, RNNLMs only estimate probabilities for complete sequences of text, whereas some applications require context-independent phrase probabilities instead. In this paper, we study how to compute an RNNLM{'}s em marginal probability: the probability that the model assigns to a short sequence of text when the preceding context is not known. We introduce a simple method of altering the RNNLM training to make the model more accurate at marginal estimation. Our experiments demonstrate that the technique is effective compared to baselines including the traditional RNNLM probability and an importance sampling approach. Finally, we show how we can use the marginal estimation to improve an RNNLM by training the marginals to match n-gram probabilities from a larger corpus. |
| Tasks | Language Modelling, Machine Translation, Speech Recognition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1322/ |
| https://www.aclweb.org/anthology/D18-1322 | |
| PWC | https://paperswithcode.com/paper/estimating-marginal-probabilities-of-n-grams |
| Repo | |
| Framework | |
Synthetically Supervised Feature Learning for Scene Text Recognition
| Title | Synthetically Supervised Feature Learning for Scene Text Recognition |
| Authors | Yang Liu, Zhaowen Wang, Hailin Jin, Ian Wassell |
| Abstract | We address the problem of image feature learning for scene text recognition. The image features in the state-of-the-art methods are learned from large-scale synthetic image datasets. However, most methods only rely on outputs of the synthetic data generation process, namely realistically looking images, and completely ignore the rest of the process. We propose to leverage the parameters that lead to the output images to improve image feature learning. Specifically, for every image out of the data generation process, we obtain the associated parameters and render another “clean” image that is free of select distortion factors that are applied to the output image. Because of the absence of distortion factors, the clean image tends to be easier to recognize than the original image. We design a multi-task network with an encoder-discriminator-generator architecture to guide the feature of the original image toward that of the clean image. The experiments show that our method significantly outperforms the state-of-the-art methods on standard scene text recognition benchmarks. Furthermore, we show that without explicitly handling, our method works on challenging cases where input images contain severe geometric distortion, such as text on a curved path. |
| Tasks | Scene Text Recognition, Synthetic Data Generation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yang_Liu_Synthetically_Supervised_Feature_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yang_Liu_Synthetically_Supervised_Feature_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/synthetically-supervised-feature-learning-for |
| Repo | |
| Framework | |
Transferred Embeddings for Igbo Similarity, Analogy, and Diacritic Restoration Tasks
| Title | Transferred Embeddings for Igbo Similarity, Analogy, and Diacritic Restoration Tasks |
| Authors | Ignatius Ezeani, Ikechukwu Onyenwe, Mark Hepple |
| Abstract | Existing NLP models are mostly trained with data from well-resourced languages. Most minority languages face the challenge of lack of resources - data and technologies - for NLP research. Building these resources from scratch for each minority language will be very expensive, time-consuming and amount largely to unnecessarily re-inventing the wheel. In this paper, we applied transfer learning techniques to create Igbo word embeddings from a variety of existing English trained embeddings. Transfer learning methods were also used to build standard datasets for Igbo word similarity and analogy tasks for intrinsic evaluation of embeddings. These projected embeddings were also applied to diacritic restoration task. Our results indicate that the projected models not only outperform the trained ones on the semantic-based tasks of analogy, word-similarity, and odd-word identifying, but they also achieve enhanced performance on the diacritic restoration with learned diacritic embeddings. |
| Tasks | Transfer Learning, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4004/ |
| https://www.aclweb.org/anthology/W18-4004 | |
| PWC | https://paperswithcode.com/paper/transferred-embeddings-for-igbo-similarity |
| Repo | |
| Framework | |
Pulling Actions out of Context: Explicit Separation for Effective Combination
| Title | Pulling Actions out of Context: Explicit Separation for Effective Combination |
| Authors | Yang Wang, Minh Hoai |
| Abstract | The ability to recognize human actions in video has many potential applications. Human action recognition, however, is tremendously challenging for computers due to the complexity of video data and the subtlety of human actions. Most current recognition systems flounder on the inability to separate human actions from co-occurring factors that usually dominate subtle human actions. In this paper, we propose a novel approach for training a human action recognizer, one that can: (1) explicitly factorize human actions from the co-occurring factors; (2) deliberately build a model for human actions and a separate model for all correlated contextual elements; and (3) effectively combine the models for human action recognition. Our approach exploits the benefits of conjugate samples of human actions, which are video clips that are contextually similar to human action samples, but do not contain the action. Experiments on ActionThread, PASCAL VOC, UCF101, and Hollywood2 datasets demonstrate the ability to separate action from context of the proposed approach. |
| Tasks | Temporal Action Localization |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Pulling_Actions_out_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Pulling_Actions_out_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pulling-actions-out-of-context-explicit |
| Repo | |
| Framework | |
Manually Annotated Corpus of Polish Texts Published between 1830 and 1918
| Title | Manually Annotated Corpus of Polish Texts Published between 1830 and 1918 |
| Authors | Witold Kiera{'s}, Marcin Woli{'n}ski |
| Abstract | |
| Tasks | Transliteration |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1609/ |
| https://www.aclweb.org/anthology/L18-1609 | |
| PWC | https://paperswithcode.com/paper/manually-annotated-corpus-of-polish-texts |
| Repo | |
| Framework | |
Answerable or Not: Devising a Dataset for Extending Machine Reading Comprehension
| Title | Answerable or Not: Devising a Dataset for Extending Machine Reading Comprehension |
| Authors | Mao Nakanishi, Tetsunori Kobayashi, Yoshihiko Hayashi |
| Abstract | Machine-reading comprehension (MRC) has recently attracted attention in the fields of natural language processing and machine learning. One of the problematic presumptions with current MRC technologies is that each question is assumed to be answerable by looking at a given text passage. However, to realize human-like language comprehension ability, a machine should also be able to distinguish not-answerable questions (NAQs) from answerable questions. To develop this functionality, a dataset incorporating hard-to-detect NAQs is vital; however, its manual construction would be expensive. This paper proposes a dataset creation method that alters an existing MRC dataset, the Stanford Question Answering Dataset, and describes the resulting dataset. The value of this dataset is likely to increase if each NAQ in the dataset is properly classified with the difficulty of identifying it as an NAQ. This difficulty level would allow researchers to evaluate a machine{'}s NAQ detection performance more precisely. Therefore, we propose a method for automatically assigning difficulty level labels, which measures the similarity between a question and the target text passage. Our NAQ detection experiments demonstrate that the resulting dataset, having difficulty level annotations, is valid and potentially useful in the development of advanced MRC models. |
| Tasks | Machine Reading Comprehension, Question Answering, Reading Comprehension |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1083/ |
| https://www.aclweb.org/anthology/C18-1083 | |
| PWC | https://paperswithcode.com/paper/answerable-or-not-devising-a-dataset-for |
| Repo | |
| Framework | |
Pose-Guided Photorealistic Face Rotation
| Title | Pose-Guided Photorealistic Face Rotation |
| Authors | Yibo Hu, Xiang Wu, Bing Yu, Ran He, Zhenan Sun |
| Abstract | Face rotation provides an effective and cheap way for data augmentation and representation learning of face recognition. It is a challenging generative learning problem due to the large pose discrepancy between two face images. This work focuses on flexible face rotation of arbitrary head poses, including extreme profile views. We propose a novel Couple-Agent Pose-Guided Generative Adversarial Network (CAPG-GAN) to generate both neutral and profile head pose face images. The head pose information is encoded by facial landmark heatmaps. It not only forms a mask image to guide the generator in learning process but also provides a flexible controllable condition during inference. A couple-agent discriminator is introduced to reinforce on the realism of synthetic arbitrary view faces. Besides the generator and conditional adversarial loss, CAPG-GAN further employs identity preserving loss and total variation regularization to preserve identity information and refine local textures respectively. Quantitative and qualitative experimental results on the Multi-PIE and LFW databases consistently show the superiority of our face rotation method over the state-of-the-art. |
| Tasks | Data Augmentation, Face Recognition, Representation Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Hu_Pose-Guided_Photorealistic_Face_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Pose-Guided_Photorealistic_Face_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pose-guided-photorealistic-face-rotation |
| Repo | |
| Framework | |
Towards Provable Control for Unknown Linear Dynamical Systems
| Title | Towards Provable Control for Unknown Linear Dynamical Systems |
| Authors | Sanjeev Arora, Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang |
| Abstract | We study the control of symmetric linear dynamical systems with unknown dynamics and a hidden state. Using a recent spectral filtering technique for concisely representing such systems in a linear basis, we formulate optimal control in this setting as a convex program. This approach eliminates the need to solve the non-convex problem of explicit identification of the system and its latent state, and allows for provable optimality guarantees for the control signal. We give the first efficient algorithm for finding the optimal control signal with an arbitrary time horizon T, with sample complexity (number of training rollouts) polynomial only in log(T) and other relevant parameters. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BygpQlbA- |
| https://openreview.net/pdf?id=BygpQlbA- | |
| PWC | https://paperswithcode.com/paper/towards-provable-control-for-unknown-linear |
| Repo | |
| Framework | |
The Importance of Sampling inMeta-Reinforcement Learning
| Title | The Importance of Sampling inMeta-Reinforcement Learning |
| Authors | Bradly Stadie, Ge Yang, Rein Houthooft, Peter Chen, Yan Duan, Yuhuai Wu, Pieter Abbeel, Ilya Sutskever |
| Abstract | We interpret meta-reinforcement learning as the problem of learning how to quickly find a good sampling distribution in a new environment. This interpretation leads to the development of two new meta-reinforcement learning algorithms: E-MAML and E-$\text{RL}^2$. Results are presented on a new environment we call `Krazy World’: a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning. Further results are presented on a set of maze environments. We show E-MAML and E-$\text{RL}^2$ deliver better performance than baseline algorithms on both tasks. | |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8140-the-importance-of-sampling-inmeta-reinforcement-learning |
| http://papers.nips.cc/paper/8140-the-importance-of-sampling-inmeta-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/the-importance-of-sampling-inmeta |
| Repo | |
| Framework | |
Discriminative Graph Autoencoder
| Title | Discriminative Graph Autoencoder |
| Authors | Haifeng Jin, Qingquan Song, Xia Hu |
| Abstract | With the abundance of graph-structured data in various applications, graph representation learning has become an effective computational tool for seeking informative vector representations for graphs. Traditional graph kernel approaches are usually frequency-based. Each dimension of a learned vector representation for a graph is the frequency of a certain type of substructure. They encounter high computational cost for counting the occurrence of predefined substructures. The learned vector representations are very sparse, which prohibit the use of inner products. Moreover, the learned vector representations are not in a smooth space since the values can only be integers. The state-of-the-art approaches tackle the challenges by changing kernel functions instead of producing better vector representations. They can only produce kernel matrices for kernel-based methods and not compatible with methods requiring vector representations. Effectively learning smooth vector representations for graphs of various structures and sizes remains a challenging task. Motivated by the recent advances in deep autoencoders, in this paper, we explore the capability of autoencoder on learning representations for graphs. Unlike videos or images, the graphs are usually of various sizes and are not readily prepared for autoencoder. Therefore, a novel framework, namely discriminative graph autoencoder (DGA), is proposed to learn low-dimensional vector representations for graphs. The algorithm decomposes the large graphs into small subgraphs, from which the structural information is sampled. The DGA produces smooth and informative vector representations of graphs efficiently while preserving the discriminative information according to their labels. Extensive experiments have been conducted to evaluate DGA. The experimental results demonstrate the efficiency and effectiveness of DGA comparing with traditional and state-of-the-art approaches on various real-world datasets and applications, e.g.,… |
| Tasks | Graph Classification, Graph Representation Learning, Representation Learning |
| Published | 2018-11-17 |
| URL | https://doi.org/10.1109/ICBK.2018.00033 |
| https://www.researchgate.net/publication/329955907_Discriminative_Graph_Autoencoder | |
| PWC | https://paperswithcode.com/paper/discriminative-graph-autoencoder |
| Repo | |
| Framework | |
A Short Answer Grading System in Chinese by Support Vector Approach
| Title | A Short Answer Grading System in Chinese by Support Vector Approach |
| Authors | Shih-Hung Wu, Wen-Feng Shih |
| Abstract | In this paper, we report a short answer grading system in Chinese. We build a system based on standard machine learning approaches and test it with translated corpus from two publicly available corpus in English. The experiment results show similar results on two different corpus as in English. |
| Tasks | Semantic Textual Similarity |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3718/ |
| https://www.aclweb.org/anthology/W18-3718 | |
| PWC | https://paperswithcode.com/paper/a-short-answer-grading-system-in-chinese-by |
| Repo | |
| Framework | |
Incremental Multi-graph Matching via Diversity and Randomness based Graph Clustering
| Title | Incremental Multi-graph Matching via Diversity and Randomness based Graph Clustering |
| Authors | Tianshu Yu, Junchi Yan, Wei Liu, Baoxin Li |
| Abstract | Multi-graph matching refers to finding correspondences across graphs, which are traditionally solved by matching all the graphs in a single batch. However in real-world applications, graphs are often collected incrementally, rather than once for all. In this paper, we present an incremental multi-graph matching approach, which deals with the arriving graph utilizing the previous matching results under the global consistency constraint. When a new graph arrives, rather than re-optimizing over all graphs, we propose to partition graphs into subsets with certain topological structure and conduct optimization within each subset. The partitioning procedure is guided by the diversity within partitions and randomness over iterations, and we present an interpretation showing why these two factors are essential. The final matching results are calculated over all subsets via an intersection graph. Extensive experimental results on synthetic and real image datasets show that our algorithm notably improves the efficiency without sacrificing the accuracy. |
| Tasks | Graph Clustering, Graph Matching |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Tianshu_Yu_Incremental_Multi-graph_Matching_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Tianshu_Yu_Incremental_Multi-graph_Matching_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-multi-graph-matching-via |
| Repo | |
| Framework | |
Error Analysis of Uyghur Name Tagging: Language-specific Techniques and Remaining Challenges
| Title | Error Analysis of Uyghur Name Tagging: Language-specific Techniques and Remaining Challenges |
| Authors | Halidanmu Abudukelimu, Abudoukelimu Abulizi, Boliang Zhang, Xiaoman Pan, Di Lu, Heng Ji, Yang Liu |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1700/ |
| https://www.aclweb.org/anthology/L18-1700 | |
| PWC | https://paperswithcode.com/paper/error-analysis-of-uyghur-name-tagging |
| Repo | |
| Framework | |
Modeling with Recurrent Neural Networks for Open Vocabulary Slots
| Title | Modeling with Recurrent Neural Networks for Open Vocabulary Slots |
| Authors | Jun-Seong Kim, Junghoe Kim, SeungUn Park, Kwangyong Lee, Yoonju Lee |
| Abstract | Dealing with {}open-vocabulary{'} slots has been among the challenges in the natural language area. While recent studies on attention-based recurrent neural network (RNN) models have performed well in completing several language related tasks such as spoken language understanding and dialogue systems, there has been a lack of attempts to address filling slots that take on values from a virtually unlimited set. In this paper, we propose a new RNN model that can capture the vital concept: Understanding the role of a word may vary according to how long a reader focuses on a particular part of a sentence. The proposed model utilizes a long-term aware attention structure, positional encoding primarily considering the relative distance between words, and multi-task learning of a character-based language model and an intent detection model. We show that the model outperforms the existing RNN models with respect to discovering {}open-vocabulary{'} slots without any external information, such as a named entity database or knowledge base. In particular, we confirm that it performs better with a greater number of slots in a dataset, including unknown words, by evaluating the models on a dataset of several domains. In addition, the proposed model also demonstrates superior performance with regard to intent detection. |
| Tasks | Goal-Oriented Dialogue Systems, Intent Detection, Language Modelling, Multi-Task Learning, Slot Filling, Spoken Dialogue Systems, Spoken Language Understanding, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1235/ |
| https://www.aclweb.org/anthology/C18-1235 | |
| PWC | https://paperswithcode.com/paper/modeling-with-recurrent-neural-networks-for |
| Repo | |
| Framework | |
