Paper Group NANR 92
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn’s Algorithm. Learning to Capture Light Fields through a Coded Aperture Camera. A Structured Review of the Validity of BLEU. GeCoTagger: Annotation of German Verb Complements with Conditional Random Fields. Epitran: Precision G2P for Many Languages …
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn’s Algorithm
| Title | Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn’s Algorithm |
| Authors | Pavel Dvurechensky, Alexander Gasnikov, Alexey Kroshnin |
| Abstract | We analyze two algorithms for approximating the general optimal transport (OT) distance between two discrete distributions of size $n$, up to accuracy $\varepsilon$. For the first algorithm, which is based on the celebrated Sinkhorn’s algorithm, we prove the complexity bound $\widetilde{O}\left(\frac{n^2}{\varepsilon^2}\right)$ arithmetic operations ($\widetilde{O}$ hides polylogarithmic factors $(\ln n)^c$, $c>0$). For the second one, which is based on our novel Adaptive Primal-Dual Accelerated Gradient Descent (APDAGD) algorithm, we prove the complexity bound $\widetilde{O}\left(\min\left{\frac{n^{9/4}}{\varepsilon}, \frac{n^{2}}{\varepsilon^2} \right}\right)$ arithmetic operations. Both bounds have better dependence on $\varepsilon$ than the state-of-the-art result given by $\widetilde{O}\left(\frac{n^2}{\varepsilon^3}\right)$. Our second algorithm not only has better dependence on $\varepsilon$ in the complexity bound, but also is not specific to entropic regularization and can solve the OT problem with different regularizers. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2468 |
| http://proceedings.mlr.press/v80/dvurechensky18a/dvurechensky18a.pdf | |
| PWC | https://paperswithcode.com/paper/computational-optimal-transport-complexity-by |
| Repo | |
| Framework | |
Learning to Capture Light Fields through a Coded Aperture Camera
| Title | Learning to Capture Light Fields through a Coded Aperture Camera |
| Authors | Yasutaka Inagaki, Yuto Kobayashi, Keita Takahashi, Toshiaki Fujii, Hajime Nagahara |
| Abstract | We propose a learning-based framework for acquiring a light field through a coded aperture camera. Acquiring a light field is a challenging task due to the amount of data. To make the acquisition process efficient, coded aperture cameras were successfully adopted; using these cameras, a light field is computationally reconstructed from several images that are acquired with different aperture patterns. However, it is still difficult to reconstruct a high-quality light field from only a few acquired images. To tackle this limitation, we formulated the entire pipeline of light field acquisition from the perspective of an auto-encoder. This auto-encoder was implemented as a stack of fully convolutional layers and was trained end-to-end by using a collection of training samples. We experimentally show that our method can successfully learn good image-acquisition and reconstruction strategies. With our method, light fields consisting of 5 x 5 or 8 x 8 images can be successfully reconstructed only from a few acquired images. Moreover, our method achieved superior performance over several state-of-the-art methods. We also applied our method to a real prototype camera to show that it is capable of capturing a real 3-D scene. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yasutaka_Inagaki_Learning_to_Capture_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yasutaka_Inagaki_Learning_to_Capture_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-capture-light-fields-through-a |
| Repo | |
| Framework | |
A Structured Review of the Validity of BLEU
| Title | A Structured Review of the Validity of BLEU |
| Authors | Ehud Reiter |
| Abstract | The BLEU metric has been widely used in NLP for over 15 years to evaluate NLP systems, especially in machine translation and natural language generation. I present a structured review of the evidence on whether BLEU is a valid evaluation technique{—}in other words, whether BLEU scores correlate with real-world utility and user-satisfaction of NLP systems; this review covers 284 correlations reported in 34 papers. Overall, the evidence supports using BLEU for diagnostic evaluation of MT systems (which is what it was originally proposed for), but does not support using BLEU outside of MT, for evaluation of individual texts, or for scientific hypothesis testing. |
| Tasks | Machine Translation, Text Generation |
| Published | 2018-09-01 |
| URL | https://www.aclweb.org/anthology/J18-3002/ |
| https://www.aclweb.org/anthology/J18-3002 | |
| PWC | https://paperswithcode.com/paper/a-structured-review-of-the-validity-of-bleu |
| Repo | |
| Framework | |
GeCoTagger: Annotation of German Verb Complements with Conditional Random Fields
| Title | GeCoTagger: Annotation of German Verb Complements with Conditional Random Fields |
| Authors | Roman Schneider, Monica F{"u}rbacher |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1342/ |
| https://www.aclweb.org/anthology/L18-1342 | |
| PWC | https://paperswithcode.com/paper/gecotagger-annotation-of-german-verb |
| Repo | |
| Framework | |
Epitran: Precision G2P for Many Languages
| Title | Epitran: Precision G2P for Many Languages |
| Authors | David R. Mortensen, Siddharth Dalmia, Patrick Littell |
| Abstract | |
| Tasks | Entity Linking |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1429/ |
| https://www.aclweb.org/anthology/L18-1429 | |
| PWC | https://paperswithcode.com/paper/epitran-precision-g2p-for-many-languages |
| Repo | |
| Framework | |
Learning Latent Opinions for Aspect-Level Sentiment Classification
| Title | Learning Latent Opinions for Aspect-Level Sentiment Classification |
| Authors | Bailin Wang, Wei Lu |
| Abstract | Aspect-level sentiment classification aims at detecting the sentiment expressed towards a particular target in a sentence. Based on the observation that the sentiment polarity is often related to specific spans in the given sentence, it is possible to make use of such information for better classification. On the other hand, such information can also serve as justifications associated with the predictions.We propose a segmentation attention based LSTM model which can effectively capture the structural dependencies between the target and the sentiment expressions with a linear-chain conditional random field (CRF) layer. The model simulates human’s process of inferring sentiment information when reading: when given a target, humans tend to search for surrounding relevant text spans in the sentence before making an informed decision on the underlying sentiment information.We perform sentiment classification tasks on publicly available datasets on online reviews across different languages from SemEval tasks and social comments from Twitter. Extensive experiments show that our model achieves the state-of-the-art performance while extracting interpretable sentiment expressions. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2018-04-01 |
| URL | https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17327 |
| https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/download/17327/16110 | |
| PWC | https://paperswithcode.com/paper/learning-latent-opinions-for-aspect-level |
| Repo | |
| Framework | |
The Set Autoencoder: Unsupervised Representation Learning for Sets
| Title | The Set Autoencoder: Unsupervised Representation Learning for Sets |
| Authors | Malte Probst |
| Abstract | We propose the set autoencoder, a model for unsupervised representation learning for sets of elements. It is closely related to sequence-to-sequence models, which learn fixed-sized latent representations for sequences, and have been applied to a number of challenging supervised sequence tasks such as machine translation, as well as unsupervised representation learning for sequences. In contrast to sequences, sets are permutation invariant. The proposed set autoencoder considers this fact, both with respect to the input as well as the output of the model. On the input side, we adapt a recently-introduced recurrent neural architecture using a content-based attention mechanism. On the output side, we use a stable marriage algorithm to align predictions to labels in the learning phase. We train the model on synthetic data sets of point clouds and show that the learned representations change smoothly with translations in the inputs, preserve distances in the inputs, and that the set size is represented directly. We apply the model to supervised tasks on the point clouds using the fixed-size latent representation. For a number of difficult classification problems, the results are better than those of a model that does not consider the permutation invariance. Especially for small training sets, the set-aware model benefits from unsupervised pretraining. |
| Tasks | Machine Translation, Representation Learning, Unsupervised Representation Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=r1tJKuyRZ |
| https://openreview.net/pdf?id=r1tJKuyRZ | |
| PWC | https://paperswithcode.com/paper/the-set-autoencoder-unsupervised |
| Repo | |
| Framework | |
A Simple yet Effective Joint Training Method for Cross-Lingual Universal Dependency Parsing
| Title | A Simple yet Effective Joint Training Method for Cross-Lingual Universal Dependency Parsing |
| Authors | Danlu Chen, Mengxiao Lin, Zhifeng Hu, Xipeng Qiu |
| Abstract | This paper describes Fudan{'}s submission to CoNLL 2018{'}s shared task Universal Dependency Parsing. We jointly train models when two languages are similar according to linguistic typology and then ensemble the models using a simple re-parse algorithm. We outperform the baseline method by 4.4{%} (2.1{%}) on average on development (test) set in CoNLL 2018 UD Shared Task. |
| Tasks | Dependency Parsing, Tokenization, Transfer Learning |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-2026/ |
| https://www.aclweb.org/anthology/K18-2026 | |
| PWC | https://paperswithcode.com/paper/a-simple-yet-effective-joint-training-method |
| Repo | |
| Framework | |
Demystifying overcomplete nonlinear auto-encoders: fast SGD convergence towards sparse representation from random initialization
| Title | Demystifying overcomplete nonlinear auto-encoders: fast SGD convergence towards sparse representation from random initialization |
| Authors | Cheng Tang, Claire Monteleoni |
| Abstract | Auto-encoders are commonly used for unsupervised representation learning and for pre-training deeper neural networks. When its activation function is linear and the encoding dimension (width of hidden layer) is smaller than the input dimension, it is well known that auto-encoder is optimized to learn the principal components of the data distribution (Oja1982). However, when the activation is nonlinear and when the width is larger than the input dimension (overcomplete), auto-encoder behaves differently from PCA, and in fact is known to perform well empirically for sparse coding problems. We provide a theoretical explanation for this empirically observed phenomenon, when rectified-linear unit (ReLu) is adopted as the activation function and the hidden-layer width is set to be large. In this case, we show that, with significant probability, initializing the weight matrix of an auto-encoder by sampling from a spherical Gaussian distribution followed by stochastic gradient descent (SGD) training converges towards the ground-truth representation for a class of sparse dictionary learning models. In addition, we can show that, conditioning on convergence, the expected convergence rate is O(1/t), where t is the number of updates. Our analysis quantifies how increasing hidden layer width helps the training performance when random initialization is used, and how the norm of network weights influence the speed of SGD convergence. |
| Tasks | Dictionary Learning, Representation Learning, Unsupervised Representation Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HyiRazbRb |
| https://openreview.net/pdf?id=HyiRazbRb | |
| PWC | https://paperswithcode.com/paper/demystifying-overcomplete-nonlinear-auto |
| Repo | |
| Framework | |
BME-HAS System for CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection
| Title | BME-HAS System for CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection |
| Authors | Judit {'A}cs |
| Abstract | |
| Tasks | Morphological Inflection |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-3016/ |
| https://www.aclweb.org/anthology/K18-3016 | |
| PWC | https://paperswithcode.com/paper/bme-has-system-for-conllasigmorphon-2018 |
| Repo | |
| Framework | |
Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)
| Title | Proceedings of the Second Workshop on Universal Dependencies (UDW 2018) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6000/ |
| https://www.aclweb.org/anthology/W18-6000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-second-workshop-on-2 |
| Repo | |
| Framework | |
DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks
| Title | DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks |
| Authors | Shuang Ma, Jianlong Fu, Chang Wen Chen, Tao Mei |
| Abstract | Unsupervised image translation, which aims in translating two independent sets of images, is challenging in discovering the correct correspondences without paired data. Existing works build upon Generative Adversarial Networks (GANs) such that the distribution of the translated images are indistinguishable from the distribution of the target set. However, such set-level constraints cannot learn the instance-level correspondences (e.g. aligned semantic parts in object transfiguration task). This limitation often results in false positives (e.g. geometric or semantic artifacts), and further leads to mode collapse problem. To address the above issues, we propose a novel framework for instance-level image translation by Deep Attention GAN (DA-GAN). Such a design enables DA-GAN to decompose the task of translating samples from two sets into translating instances in a highly-structured latent space. Specifically, we jointly learn a deep attention encoder, and the instance-level correspondences could be consequently discovered through attending on the learned instances. Therefore, the constraints could be exploited on both set-level and instance-level. Comparisons against several state-of-the- arts demonstrate the superiority of our approach, and the broad application capability, e.g, pose morphing, data augmentation, etc., pushes the margin of domain translation problem. |
| Tasks | Data Augmentation, Deep Attention |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Ma_DA-GAN_Instance-Level_Image_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Ma_DA-GAN_Instance-Level_Image_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/da-gan-instance-level-image-translation-by-1 |
| Repo | |
| Framework | |
Medical Entity Corpus with PICO elements and Sentiment Analysis
| Title | Medical Entity Corpus with PICO elements and Sentiment Analysis |
| Authors | Markus Zlabinger, Linda Andersson, Allan Hanbury, Michael Andersson, Vanessa Quasnik, Jon Brassey |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1044/ |
| https://www.aclweb.org/anthology/L18-1044 | |
| PWC | https://paperswithcode.com/paper/medical-entity-corpus-with-pico-elements-and |
| Repo | |
| Framework | |
Discovering Order in Unordered Datasets: Generative Markov Networks
| Title | Discovering Order in Unordered Datasets: Generative Markov Networks |
| Authors | Yao-Hung Hubert Tsai, Han Zhao, Nebojsa Jojic, Ruslan Salakhutdinov |
| Abstract | The assumption that data samples are independently identically distributed is the backbone of many learning algorithms. Nevertheless, datasets often exhibit rich structures in practice, and we argue that there exist some unknown orders within the data instances. Aiming to find such orders, we introduce a novel Generative Markov Network (GMN) which we use to extract the order of data instances automatically. Specifically, we assume that the instances are sampled from a Markov chain. Our goal is to learn the transitional operator of the chain as well as the generation order by maximizing the generation probability under all possible data permutations. One of our key ideas is to use neural networks as a soft lookup table for approximating the possibly huge, but discrete transition matrix. This strategy allows us to amortize the space complexity with a single model and make the transitional operator generalizable to unseen instances. To ensure the learned Markov chain is ergodic, we propose a greedy batch-wise permutation scheme that allows fast training. Empirically, we evaluate the learned Markov chain by showing that GMNs are able to discover orders among data instances and also perform comparably well to state-of-the-art methods on the one-shot recognition benchmark task. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rJ695PxRW |
| https://openreview.net/pdf?id=rJ695PxRW | |
| PWC | https://paperswithcode.com/paper/discovering-order-in-unordered-datasets |
| Repo | |
| Framework | |
Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning
| Title | Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning |
| Authors | Chuang Gan, Boqing Gong, Kun Liu, Hao Su, Leonidas J. Guibas |
| Abstract | It is often laborious and costly to manually annotate videos for training high-quality video recognition models, so there has been some work and interest in exploring alternative, cheap, and yet often noisy and indirect, training signals for learning the video representations. However, these signals are still coarse, supplying supervision at the whole video frame level, and subtle, sometimes enforcing the learning agent to solve problems that are even hard for humans. In this paper, we instead explore geometry, a grand new type of auxiliary supervision for the self-supervised learning of video representations. In particular, we extract pixel-wise geometry information as flow fields and disparity maps from synthetic imagery and real 3D movies. Although the geometry and high-level semantics are seemingly distant topics, surprisingly, we find that the convolutional neural networks pre-trained by the geometry cues can be effectively adapted to semantic video understanding tasks. In addition, we also find that a progressive training strategy can foster a better neural network for the video recognition task than blindly pooling the distinct sources of geometry cues together. Extensive results on video dynamic scene recognition and action recognition tasks show that our geometry guided networks significantly outperform the competing methods that are trained with other types of labeling-free supervision signals. |
| Tasks | Representation Learning, Scene Recognition, Temporal Action Localization, Video Recognition, Video Understanding |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Gan_Geometry_Guided_Convolutional_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Gan_Geometry_Guided_Convolutional_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-guided-convolutional-neural-networks |
| Repo | |
| Framework | |
