Paper Group NANR 8
Pronunciation Dictionaries for the Alsatian Dialects to Analyze Spelling and Phonetic Variation. Differentiating Phrase Structure Parsing and Memory Retrieval in the Brain. A bidirectional mapping between English and CNF-based reasoners. Shape Reconstruction Using Volume Sweeping and Learned Photoconsistency. Entity-Centric Joint Modeling of Japane …
Pronunciation Dictionaries for the Alsatian Dialects to Analyze Spelling and Phonetic Variation
| Title | Pronunciation Dictionaries for the Alsatian Dialects to Analyze Spelling and Phonetic Variation |
| Authors | Lucie Steibl{'e}, Delphine Bernhard |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1654/ |
| https://www.aclweb.org/anthology/L18-1654 | |
| PWC | https://paperswithcode.com/paper/pronunciation-dictionaries-for-the-alsatian |
| Repo | |
| Framework | |
Differentiating Phrase Structure Parsing and Memory Retrieval in the Brain
| Title | Differentiating Phrase Structure Parsing and Memory Retrieval in the Brain |
| Authors | Shohini Bhattasali, John Hale, Christophe Pallier, Jonathan Brennan, Wen-Ming Luh, R. Nathan Spreng |
| Abstract | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0308/ |
| https://www.aclweb.org/anthology/W18-0308 | |
| PWC | https://paperswithcode.com/paper/differentiating-phrase-structure-parsing-and |
| Repo | |
| Framework | |
A bidirectional mapping between English and CNF-based reasoners
| Title | A bidirectional mapping between English and CNF-based reasoners |
| Authors | Steven Abney |
| Abstract | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0306/ |
| https://www.aclweb.org/anthology/W18-0306 | |
| PWC | https://paperswithcode.com/paper/a-bidirectional-mapping-between-english-and |
| Repo | |
| Framework | |
Shape Reconstruction Using Volume Sweeping and Learned Photoconsistency
| Title | Shape Reconstruction Using Volume Sweeping and Learned Photoconsistency |
| Authors | Vincent Leroy, Jean-Sebastien Franco, Edmond Boyer |
| Abstract | The rise of virtual and augmented reality fuels an increased need for content suitable to these new technologies including 3D contents obtained from real scenes. We consider in this paper the problem of 3D shape reconstruction from multi-view RGB images. We investigate the ability of learning-based strategies to effectively benefit the reconstruction of arbitrary shapes with improved precision and robustness. We especially target real life performance capture, containing complex surface details that are difficult to recover with existing approaches. A key step in the multi-view reconstruction pipeline lies in the search for matching features between viewpoints in order to infer depth information. We propose to cast the matching on a 3D receptive field along viewing lines and to learn a multi-view photoconsistency measure for that purpose. The intuition is that deep networks have the ability to learn local photometric configurations in a broad way, even with respect to different orientations along various viewing lines of the same surface point. Our results demonstrate this ability, showing that a CNN, trained on a standard static dataset, can help recover surface details on dynamic scenes that are not perceived by traditional 2D feature based methods. Our evaluation also shows that our solution compares on par to state-of-the-art-reconstruction pipelines on standard evaluation datasets, while yielding significantly better results and generalization with realistic performance capture data. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Vincent_Leroy_Shape_Reconstruction_Using_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Vincent_Leroy_Shape_Reconstruction_Using_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/shape-reconstruction-using-volume-sweeping |
| Repo | |
| Framework | |
Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis
| Title | Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis |
| Authors | Tomohide Shibata, Sadao Kurohashi |
| Abstract | Predicate argument structure analysis is a task of identifying structured events. To improve this field, we need to identify a salient entity, which cannot be identified without performing coreference resolution and predicate argument structure analysis simultaneously. This paper presents an entity-centric joint model for Japanese coreference resolution and predicate argument structure analysis. Each entity is assigned an embedding, and when the result of both analyses refers to an entity, the entity embedding is updated. The analyses take the entity embedding into consideration to access the global information of entities. Our experimental results demonstrate the proposed method can improve the performance of the inter-sentential zero anaphora resolution drastically, which is a notoriously difficult task in predicate argument structure analysis. |
| Tasks | Coreference Resolution, Reading Comprehension |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1054/ |
| https://www.aclweb.org/anthology/P18-1054 | |
| PWC | https://paperswithcode.com/paper/entity-centric-joint-modeling-of-japanese |
| Repo | |
| Framework | |
SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation
| Title | SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation |
| Authors | Gwangmo Song, Heesoo Myeong, Kyoung Mu Lee |
| Abstract | In this paper, we propose an automatic seed generation technique with deep reinforcement learning to solve the interactive segmentation problem. One of the main issues of the interactive segmentation problem is robust and consistent object extraction with less human effort. Most of the existing algorithms highly depend on the distribution of inputs, which differs from one user to another and hence need sequential user interactions to achieve adequate performance. In our system, when a user first specifies a point on the desired object and a point in the background, a sequence of artificial user input is automatically generated for precisely segmenting the desired object. The proposed system allows the user to reduce the number of input significantly. This problem is difficult to cast as a supervised learning problem because it is not possible to define globally optimal user input at some stage of the interactive segmentation task. Hence, we formulate automatic seed generation problem as Markov Decision Process (MDP) and then optimize it by reinforcement learning with Deep Q-Network (DQN). We train our network on the MSRA10K dataset and show that the network achieves notable performance improvement from inaccurate initial segmentation on both seen and unseen datasets. |
| Tasks | Interactive Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Song_SeedNet_Automatic_Seed_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Song_SeedNet_Automatic_Seed_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/seednet-automatic-seed-generation-with-deep |
| Repo | |
| Framework | |
Wolves at SemEval-2018 Task 10: Semantic Discrimination based on Knowledge and Association
| Title | Wolves at SemEval-2018 Task 10: Semantic Discrimination based on Knowledge and Association |
| Authors | Shiva Taslimipoor, Omid Rohanian, Le An Ha, Gloria Corpas Pastor, Ruslan Mitkov |
| Abstract | This paper describes the system submitted to SemEval 2018 shared task 10 {`}Capturing Dicriminative Attributes{'}. We use a combination of knowledge-based and co-occurrence features to capture the semantic difference between two words in relation to an attribute. We define scores based on association measures, ngram counts, word similarity, and ConceptNet relations. The system is ranked 4th (joint) on the official leaderboard of the task. | |
| Tasks | Semantic Textual Similarity |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1160/ |
| https://www.aclweb.org/anthology/S18-1160 | |
| PWC | https://paperswithcode.com/paper/wolves-at-semeval-2018-task-10-semantic |
| Repo | |
| Framework | |
Personalizing Lexical Simplification
| Title | Personalizing Lexical Simplification |
| Authors | John Lee, Chak Yan Yeung |
| Abstract | A lexical simplification (LS) system aims to substitute complex words with simple words in a text, while preserving its meaning and grammaticality. Despite individual users{'} differences in vocabulary knowledge, current systems do not consider these variations; rather, they are trained to find one optimal substitution or ranked list of substitutions for all users. We evaluate the performance of a state-of-the-art LS system on individual learners of English at different proficiency levels, and measure the benefits of using complex word identification (CWI) models to personalize the system. Experimental results show that even a simple personalized CWI model, based on graded vocabulary lists, can help the system avoid some unnecessary simplifications and produce more readable output. |
| Tasks | Complex Word Identification, Lexical Simplification |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1019/ |
| https://www.aclweb.org/anthology/C18-1019 | |
| PWC | https://paperswithcode.com/paper/personalizing-lexical-simplification |
| Repo | |
| Framework | |
Transductive Semi-Supervised Deep Learning using Min-Max Features
| Title | Transductive Semi-Supervised Deep Learning using Min-Max Features |
| Authors | Weiwei Shi, Yihong Gong, Chris Ding, Zhiheng MaXiaoyu Tao, Nanning Zheng |
| Abstract | In this paper, we propose Transductive Semi-Supervised Deep Learning (TSSDL) method that is effective for training Deep Convolutional Neural Network (DCNN) models. The method applies transductive learning principle to DCNN training, introduces confidence levels on unlabeled image samples to overcome unreliable label estimates on outliers and uncertain samples, and develops the Min-Max Feature (MMF) regularization that encourages DCNN to learn feature descriptors with better between-class separability and within-class compactness. TSSDL method is independent of any DCNN architectures and complementary to the latest Semi-Supervised Learning (SSL) methods. Comprehensive experiments on the benchmark datasets CIFAR10 and SVHN have shown that the DCNN model trained by the proposed TSSDL method can produce image classification accuracies compatible to the state-of-the-art SSL methods, and that combining TSSDL with the Mean Teacher method can produce the best classification accuracies on the two benchmark datasets. |
| Tasks | Image Classification |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Weiwei_Shi_Transductive_Semi-Supervised_Deep_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Weiwei_Shi_Transductive_Semi-Supervised_Deep_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/transductive-semi-supervised-deep-learning |
| Repo | |
| Framework | |
Automatically Detecting the Position and Type of Psychiatric Evaluation Report Sections
| Title | Automatically Detecting the Position and Type of Psychiatric Evaluation Report Sections |
| Authors | Deya Banisakher, Naphtali Rishe, Mark A. Finlayson |
| Abstract | Psychiatric evaluation reports represent a rich and still mostly-untapped source of information for developing systems for automatic diagnosis and treatment of mental health problems. These reports contain free-text structured within sections using a convention of headings. We present a model for automatically detecting the position and type of different psychiatric evaluation report sections. We developed this model using a corpus of 150 sample reports that we gathered from the Web, and used sentences as a processing unit while section headings were used as labels of section type. From these labels we generated a unified hierarchy of labels of section types, and then learned n-gram models of the language found in each section. To model conventions for section order, we integrated these n-gram models with a Hierarchical Hidden Markov Model (HHMM) representing the probabilities of observed section orders found in the corpus, and then used this HHMM n-gram model in a decoding framework to infer the most likely section boundaries and section types for documents with their section labels removed. We evaluated our model over two tasks, namely, identifying section boundaries and identifying section types and orders. Our model significantly outperformed baselines for each task with an F1 of 0.88 for identifying section types, and a 0.26 WindowDiff (Wd) and 0.20 and (Pk) scores, respectively, for identifying section boundaries. |
| Tasks | Semantic Parsing |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5612/ |
| https://www.aclweb.org/anthology/W18-5612 | |
| PWC | https://paperswithcode.com/paper/automatically-detecting-the-position-and-type |
| Repo | |
| Framework | |
Efficient Sliding Window Computation for NN-Based Template Matching
| Title | Efficient Sliding Window Computation for NN-Based Template Matching |
| Authors | Lior Talker, Yael Moses, Ilan Shimshoni |
| Abstract | Template matching is a fundamental problem in computer vision, with many applications. Existing methods use sliding window computation for choosing an image-window that best matches the tem- plate. For classic algorithms based on SSD, SAD and normalized cross- correlation, efficient algorithms have been developed allowing them to run in real-time. Current state of the art algorithms are based on nearest neighbor (NN) matching of small patches within the template to patches in the image. These algorithms yield state-of-the-art results since they can deal better with changes in appearance, viewpoint, illumination, non- rigid transformations, and occlusion. However, NN-based algorithms are relatively slow not only due to NN computation for each image patch, but also since their sliding window computation is inecient. We there- fore propose in this paper an efficient NN-based algorithm. Its accuracy is similar (in some cases slightly better) than the existing algorithms and its running time is 44-200 times faster depending on the sizes of the images and templates used. The main contribution of our method is an algorithm for incrementally computing the score of each image window based on the score computed for the previous window. This is in con- trast to computing the score for each image window independently, as in previous NN-based methods. The complexity of our method is there- fore O(I) instead of O(IT), where I and T are the image and the template respectively. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Lior_Talker_Efficient_Sliding_Window_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Lior_Talker_Efficient_Sliding_Window_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-sliding-window-computation-for-nn |
| Repo | |
| Framework | |
Single Image Dehazing via Conditional Generative Adversarial Network
| Title | Single Image Dehazing via Conditional Generative Adversarial Network |
| Authors | Runde Li, Jinshan Pan, Zechao Li, Jinhui Tang |
| Abstract | In this paper, we present an algorithm to directly restore a clear image from a hazy image. This problem is highly ill-posed and most existing algorithms often use hand-crafted features, e.g., dark channel, color disparity, maximum contrast, to estimate transmission maps and then atmospheric lights. In contrast, we solve this problem based on a conditional generative adversarial network (cGAN), where the clear image is estimated by an end-to-end trainable neural network. Different from the generative network in basic cGAN, we propose an encoder and decoder architecture so that it can generate better results. To generate realistic clear images, we further modify the basic cGAN formulation by introducing the VGG features and a L_1-regularized gradient prior. We also synthesize a hazy dataset including indoor and outdoor scenes to train and evaluate the proposed algorithm. Extensive experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods on both synthetic dataset and real world hazy images. |
| Tasks | Image Dehazing, Single Image Dehazing |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Li_Single_Image_Dehazing_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Single_Image_Dehazing_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/single-image-dehazing-via-conditional |
| Repo | |
| Framework | |
Document Modeling with External Attention for Sentence Extraction
| Title | Document Modeling with External Attention for Sentence Extraction |
| Authors | Shashi Narayan, Ronald Cardenas, Nikos Papasarantopoulos, Shay B. Cohen, Mirella Lapata, Jiangsheng Yu, Yi Chang |
| Abstract | Document modeling is essential to a variety of natural language understanding tasks. We propose to use external information to improve document modeling for problems that can be framed as sentence extraction. We develop a framework composed of a hierarchical document encoder and an attention-based extractor with attention over external information. We evaluate our model on extractive document summarization (where the external information is image captions and the title of the document) and answer selection (where the external information is a question). We show that our model consistently outperforms strong baselines, in terms of both informativeness and fluency (for CNN document summarization) and achieves state-of-the-art results for answer selection on WikiQA and NewsQA. |
| Tasks | Answer Selection, Document Summarization, Extractive Document Summarization, Image Captioning, Language Modelling, Machine Reading Comprehension, Reading Comprehension |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1188/ |
| https://www.aclweb.org/anthology/P18-1188 | |
| PWC | https://paperswithcode.com/paper/document-modeling-with-external-attention-for |
| Repo | |
| Framework | |
EmoNLP at IEST 2018: An Ensemble of Deep Learning Models and Gradient Boosting Regression Tree for Implicit Emotion Prediction in Tweets
| Title | EmoNLP at IEST 2018: An Ensemble of Deep Learning Models and Gradient Boosting Regression Tree for Implicit Emotion Prediction in Tweets |
| Authors | Man Liu |
| Abstract | This paper describes our system submitted to IEST 2018, a shared task (Klinger et al., 2018) to predict the emotion types. Six emotion types are involved: anger, joy, fear, surprise, disgust and sad. We perform three different approaches: feed forward neural network (FFNN), convolutional BLSTM (ConBLSTM) and Gradient Boosting Regression Tree Method (GBM). Word embeddings used in convolutional BLSTM are pre-trained on 470 million tweets which are filtered using the emotional words and emojis. In addition, broad sets of features (i.e. syntactic features, lexicon features, cluster features) are adopted to train GBM and FFNN. The three approaches are finally ensembled by the weighted average of predicted probabilities of each emotion label. |
| Tasks | Tokenization, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6228/ |
| https://www.aclweb.org/anthology/W18-6228 | |
| PWC | https://paperswithcode.com/paper/emonlp-at-iest-2018-an-ensemble-of-deep |
| Repo | |
| Framework | |
Deep Mean Field Theory: Layerwise Variance and Width Variation as Methods to Control Gradient Explosion
| Title | Deep Mean Field Theory: Layerwise Variance and Width Variation as Methods to Control Gradient Explosion |
| Authors | Greg Yang, Sam S. Schoenholz |
| Abstract | A recent line of work has studied the statistical properties of neural networks to great success from a {\it mean field theory} perspective, making and verifying very precise predictions of neural network behavior and test time performance. In this paper, we build upon these works to explore two methods for taming the behaviors of random residual networks (with only fully connected layers and no batchnorm). The first method is {\it width variation (WV)}, i.e. varying the widths of layers as a function of depth. We show that width decay reduces gradient explosion without affecting the mean forward dynamics of the random network. The second method is {\it variance variation (VV)}, i.e. changing the initialization variances of weights and biases over depth. We show VV, used appropriately, can reduce gradient explosion of tanh and ReLU resnets from $\exp(\Theta(\sqrt L))$ and $\exp(\Theta(L))$ respectively to constant $\Theta(1)$. A complete phase-diagram is derived for how variance decay affects different dynamics, such as those of gradient and activation norms. In particular, we show the existence of many phase transitions where these dynamics switch between exponential, polynomial, logarithmic, and even constant behaviors. Using the obtained mean field theory, we are able to track surprisingly well how VV at initialization time affects training and test time performance on MNIST after a set number of epochs: the level sets of test/train set accuracies coincide with the level sets of the expectations of certain gradient norms or of metric expressivity (as defined in \cite{yang_meanfield_2017}), a measure of expansion in a random neural network. Based on insights from past works in deep mean field theory and information geometry, we also provide a new perspective on the gradient explosion/vanishing problems: they lead to ill-conditioning of the Fisher information matrix, causing optimization troubles. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rJGY8GbR- |
| https://openreview.net/pdf?id=rJGY8GbR- | |
| PWC | https://paperswithcode.com/paper/deep-mean-field-theory-layerwise-variance-and |
| Repo | |
| Framework | |
