Paper Group NANR 63
On the Adaptability of Unsupervised CNN-Based Deformable Image Registration to Unseen Image Domains. A Parallel Corpus of Arabic-Japanese News Articles. Heuristically Informed Unsupervised Idiom Usage Recognition. Coming to Your Senses: on Controls and Evaluation Sets in Polysemy Research. Lyb3b at SemEval-2018 Task 11: Machine Comprehension Task u …
On the Adaptability of Unsupervised CNN-Based Deformable Image Registration to Unseen Image Domains
Title | On the Adaptability of Unsupervised CNN-Based Deformable Image Registration to Unseen Image Domains |
Authors | Ferrante, E., Oktay, O., Glocker, B., and Milone, D. H. |
Abstract | Deformable image registration is a fundamental problem in medical image analysis. During the last years, several methods based on deep convolutional neural networks (CNN) proved to be highly accurate to perform this task. These models achieved state-of-the-art accuracy while drastically reducing the required computational time, but mainly focusing on images of specific organs and modalities. To date, no work has reported on how these models adapt across different domains. In this work, we ask the question: can we use CNN-based registration models to spatially align images coming from a domain different than the one/s used at training time? We explore the adaptability of CNN-based image registration to different organs/modalities. We employ a fully convolutional architecture trained following an unsupervised approach. We consider a simple transfer learning strategy to study the generalisation of such model to unseen target domains, and devise a one-shot learning scheme taking advantage of the unsupervised nature of the proposed method. Evaluation on two publicly available datasets of X-Ray lung images and cardiac cine magnetic resonance sequences is provided. Our experiments suggest that models learned in different domains can be transferred at the expense of a decrease in performance, and that oneshot learning in the context of unsupervised CNN-based registration is a valid alternative to achieve consistent registration performance when only a pair of images from the target domain is available. |
Tasks | Image Registration, One-Shot Learning, Transfer Learning |
Published | 2018-09-01 |
URL | https://spiral.imperial.ac.uk/bitstream/10044/1/62670/2/ferrante2018mlmi.pdf |
https://spiral.imperial.ac.uk/bitstream/10044/1/62670/2/ferrante2018mlmi.pdf | |
PWC | https://paperswithcode.com/paper/on-the-adaptability-of-unsupervised-cnn-based |
Repo | |
Framework | |
A Parallel Corpus of Arabic-Japanese News Articles
Title | A Parallel Corpus of Arabic-Japanese News Articles |
Authors | Go Inoue, Nizar Habash, Yuji Matsumoto, Hiroyuki Aoyama |
Abstract | |
Tasks | Machine Translation |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1147/ |
https://www.aclweb.org/anthology/L18-1147 | |
PWC | https://paperswithcode.com/paper/a-parallel-corpus-of-arabic-japanese-news |
Repo | |
Framework | |
Heuristically Informed Unsupervised Idiom Usage Recognition
Title | Heuristically Informed Unsupervised Idiom Usage Recognition |
Authors | Changsheng Liu, Rebecca Hwa |
Abstract | Many idiomatic expressions can be interpreted figuratively or literally depending on their contexts. This paper proposes an unsupervised learning method for recognizing the intended usages of idioms. We treat the usages as a latent variable in probabilistic models and train them in a linguistically motivated feature space. Crucially, we show that distributional semantics is a helpful heuristic for distinguishing the literal usage of idioms, giving us a way to formulate a literal usage metric to estimate the likelihood that the idiom is intended literally. This information then serves as a form of distant supervision to guide the unsupervised training process for the probabilistic models. Experiments show that our overall model performs competitively against supervised methods. |
Tasks | Machine Translation, Sentiment Analysis |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1199/ |
https://www.aclweb.org/anthology/D18-1199 | |
PWC | https://paperswithcode.com/paper/heuristically-informed-unsupervised-idiom |
Repo | |
Framework | |
Coming to Your Senses: on Controls and Evaluation Sets in Polysemy Research
Title | Coming to Your Senses: on Controls and Evaluation Sets in Polysemy Research |
Authors | Haim Dubossarsky, Eitan Grossman, Daphna Weinshall |
Abstract | The point of departure of this article is the claim that sense-specific vectors provide an advantage over normal vectors due to the polysemy that they presumably represent. This claim is based on performance gains observed in gold standard evaluation tests such as word similarity tasks. We demonstrate that this claim, at least as it is instantiated in prior art, is unfounded in two ways. Furthermore, we provide empirical data and an analytic discussion that may account for the previously reported improved performance. First, we show that ground-truth polysemy degrades performance in word similarity tasks. Therefore word similarity tasks are not suitable as an evaluation test for polysemy representation. Second, random assignment of words to senses is shown to improve performance in the same task. This and additional results point to the conclusion that performance gains as reported in previous work may be an artifact of random sense assignment, which is equivalent to sub-sampling and multiple estimation of word vector representations. Theoretical analysis shows that this may on its own be beneficial for the estimation of word similarity, by reducing the bias in the estimation of the cosine distance. |
Tasks | Word Embeddings |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1200/ |
https://www.aclweb.org/anthology/D18-1200 | |
PWC | https://paperswithcode.com/paper/coming-to-your-senses-on-controls-and |
Repo | |
Framework | |
Lyb3b at SemEval-2018 Task 11: Machine Comprehension Task using Deep Learning Models
Title | Lyb3b at SemEval-2018 Task 11: Machine Comprehension Task using Deep Learning Models |
Authors | Yongbin Li, Xiaobing Zhou |
Abstract | Machine Comprehension of text is a typical Natural Language Processing task which remains an elusive challenge. This paper is to solve the task 11 of SemEval-2018, Machine Comprehension using Commonsense Knowledge task. We use deep learning model to solve the problem. We build distributed word embedding of text, question and answering respectively instead of manually extracting features by linguistic tools. Meanwhile, we use a series of frameworks such as CNN model, LSTM model, LSTM with attention model and biLSTM with attention model for processing word vector. Experiments demonstrate the superior performance of biLSTM with attention framework compared to other models. We also delete high frequency words and combine word vector and data augmentation methods, achieved a certain effect. The approach we proposed rank 6th in official results, with accuracy rate of 0.7437 in test dataset. |
Tasks | Data Augmentation, Reading Comprehension |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1180/ |
https://www.aclweb.org/anthology/S18-1180 | |
PWC | https://paperswithcode.com/paper/lyb3b-at-semeval-2018-task-11-machine |
Repo | |
Framework | |
Compound Memory Networks for Few-shot Video Classification
Title | Compound Memory Networks for Few-shot Video Classification |
Authors | Linchao Zhu, Yi Yang |
Abstract | In this paper, we propose a new memory network structure for few-shot video classification by making the following contributions. First, we propose a compound memory network (CMN) structure under the key-value memory network paradigm, in which each key memory involves multiple constituent keys. These constituent keys work collaboratively for training, which enables the CMN to obtain an optimal video representation in a larger space. Second, we introduce a multi-saliency embedding algorithm which encodes a variable-length video sequence into a fixed-size matrix representation by discovering multiple saliencies of interest. For example, given a video of car auction, some people are interested in the car, while others are interested in the auction activities. Third, we design an abstract memory on top of the constituent keys. The abstract memory and constituent keys form a layered structure, which makes the CMN more efficient and capable of being scaled, while also retaining the representation capability of the multiple keys. We compare CMN with several state-of-the-art baselines on a new few-shot video classification dataset and show the effectiveness of our approach. |
Tasks | Video Classification |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Linchao_Zhu_Compound_Memory_Networks_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Linchao_Zhu_Compound_Memory_Networks_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/compound-memory-networks-for-few-shot-video |
Repo | |
Framework | |
Scale-Transferrable Object Detection
Title | Scale-Transferrable Object Detection |
Authors | Peng Zhou, Bingbing Ni, Cong Geng, Jianguo Hu, Yi Xu |
Abstract | Scale problem lies in the heart of object detection. In this work, we develop a novel Scale-Transferrable Detection Network (STDN) for detecting multi-scale objects in images. In contrast to previous methods that simply combine object predictions from multiple feature maps from different network depths, the proposed network is equipped with embedded super-resolution layers (named as scale-transfer layer/module in this work) to explicitly explore the inter-scale consistency nature across multiple detection scales. Scale-transfer module naturally fits the base network with little computational cost. This module is further integrated with a dense convolutional network (DenseNet) to yield a one-stage object detector. We evaluate our proposed architecture on PASCAL VOC 2007 and MS COCO benchmark tasks and STDN obtains significant improvements over the comparable state-of-the-art detection models. |
Tasks | Object Detection, Super-Resolution |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_Scale-Transferrable_Object_Detection_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Scale-Transferrable_Object_Detection_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/scale-transferrable-object-detection |
Repo | |
Framework | |
The Sockeye Neural Machine Translation Toolkit at AMTA 2018
Title | The Sockeye Neural Machine Translation Toolkit at AMTA 2018 |
Authors | Felix Hieber, Tobias Domhan, Michael Denkowski, David Vilar, Artem Sokolov, Ann Clifton, Matt Post |
Abstract | |
Tasks | Machine Translation |
Published | 2018-03-01 |
URL | https://www.aclweb.org/anthology/W18-1820/ |
https://www.aclweb.org/anthology/W18-1820 | |
PWC | https://paperswithcode.com/paper/the-sockeye-neural-machine-translation |
Repo | |
Framework | |
Towards Automated Extraction of Business Constraints from Unstructured Regulatory Text
Title | Towards Automated Extraction of Business Constraints from Unstructured Regulatory Text |
Authors | Rahul Nair, Killian Levacher, Martin Stephenson |
Abstract | Large organizations spend considerable resources in reviewing regulations and ensuring that their business processes are compliant with the law. To make compliance workflows more efficient and responsive, we present a system for machine-driven annotations of legal documents. A set of natural language processing pipelines are designed and aimed at addressing some key questions in this domain: (a) is this (new) regulation relevant for me? (b) what set of requirements does this law impose?, and (c) what is the regulatory intent of a law? The system is currently undergoing user trials within our organization. |
Tasks | Entity Extraction, Question Answering |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-2034/ |
https://www.aclweb.org/anthology/C18-2034 | |
PWC | https://paperswithcode.com/paper/towards-automated-extraction-of-business |
Repo | |
Framework | |
Mixture Matrix Completion
Title | Mixture Matrix Completion |
Authors | Daniel Pimentel-Alarcon |
Abstract | Completing a data matrix X has become an ubiquitous problem in modern data science, with motivations in recommender systems, computer vision, and networks inference, to name a few. One typical assumption is that X is low-rank. A more general model assumes that each column of X corresponds to one of several low-rank matrices. This paper generalizes these models to what we call mixture matrix completion (MMC): the case where each entry of X corresponds to one of several low-rank matrices. MMC is a more accurate model for recommender systems, and brings more flexibility to other completion and clustering problems. We make four fundamental contributions about this new model. First, we show that MMC is theoretically possible (well-posed). Second, we give its precise information-theoretic identifiability conditions. Third, we derive the sample complexity of MMC. Finally, we give a practical algorithm for MMC with performance comparable to the state-of-the-art for simpler related problems, both on synthetic and real data. |
Tasks | Matrix Completion, Recommendation Systems |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7488-mixture-matrix-completion |
http://papers.nips.cc/paper/7488-mixture-matrix-completion.pdf | |
PWC | https://paperswithcode.com/paper/mixture-matrix-completion-1 |
Repo | |
Framework | |
Fixed Similes: Measuring aspects of the relation between MWE idiomatic semantics and syntactic flexibility
Title | Fixed Similes: Measuring aspects of the relation between MWE idiomatic semantics and syntactic flexibility |
Authors | Stella Markantonatou, Panagiotis Kouris, Yanis Maistros |
Abstract | We shed light on aspects of the relation between the semantics and the syntactic flexibility of multiword expressions by investigating fixed adjective similes (FS), a predicative multiword expression class not studied in this respect before. We find that only a subset of the syntactic structures observed in the data are related with idiomaticity. We identify and measure two aspects of idiomaticity, one of which seems to allow for predictions about FS syntactic flexibility. Our research draws on a resource developed with the semantic and detailed syntactic annotation of web-retrieved Modern Greek material, indicating frequency of use of the individual similes. |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4908/ |
https://www.aclweb.org/anthology/W18-4908 | |
PWC | https://paperswithcode.com/paper/fixed-similes-measuring-aspects-of-the |
Repo | |
Framework | |
Real-Time Hair Rendering using Sequential Adversarial Networks
Title | Real-Time Hair Rendering using Sequential Adversarial Networks |
Authors | Lingyu Wei, Liwen Hu, Vladimir Kim, Ersin Yumer, Hao Li |
Abstract | We present an adversarial network for rendering photorealistic hair as an alternative to conventional computer graphics pipelines. Our deep learning approach does not require low-level parameter tuning nor ad-hoc asset design. Our method simply takes a strand-based 3D hair model as input and provides intuitive user-control for color and lighting through reference images. To handle the diversity of hairstyles and its appearance complexity, we disentangle hair structure, color, and illumination properties using a sequential GAN architecture and a semi-supervised training approach. We also introduce an intermediate edge activation map to orientation field conversion step to ensure a successful CG-to-photoreal transition, while preserving the hair structures of the original input data. As we only require a feed-forward pass through the network, our rendering performs in real-time. We demonstrate the synthesis of photorealistic hair images on a wide range of intricate hairstyles and compare our technique with state-of-the-art hair rendering methods. |
Tasks | |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Lingyu_Wei_Real-Time_Hair_Rendering_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Lingyu_Wei_Real-Time_Hair_Rendering_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/real-time-hair-rendering-using-sequential |
Repo | |
Framework | |
Enriching Word Embeddings with Domain Knowledge for Readability Assessment
Title | Enriching Word Embeddings with Domain Knowledge for Readability Assessment |
Authors | Zhiwei Jiang, Qing Gu, Yafeng Yin, Daoxu Chen |
Abstract | In this paper, we present a method which learns the word embedding for readability assessment. For the existing word embedding models, they typically focus on the syntactic or semantic relations of words, while ignoring the reading difficulty, thus they may not be suitable for readability assessment. Hence, we provide the knowledge-enriched word embedding (KEWE), which encodes the knowledge on reading difficulty into the representation of words. Specifically, we extract the knowledge on word-level difficulty from three perspectives to construct a knowledge graph, and develop two word embedding models to incorporate the difficulty context derived from the knowledge graph to define the loss functions. Experiments are designed to apply KEWE for readability assessment on both English and Chinese datasets, and the results demonstrate both effectiveness and potential of KEWE. |
Tasks | Word Embeddings |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1031/ |
https://www.aclweb.org/anthology/C18-1031 | |
PWC | https://paperswithcode.com/paper/enriching-word-embeddings-with-domain |
Repo | |
Framework | |
Faster Discovery of Neural Architectures by Searching for Paths in a Large Model
Title | Faster Discovery of Neural Architectures by Searching for Paths in a Large Model |
Authors | Hieu Pham, Melody Y. Guan, Barret Zoph, Quoc V. Le, Jeff Dean |
Abstract | We propose Efficient Neural Architecture Search (ENAS), a faster and less expensive approach to automated model design than previous methods. In ENAS, a controller learns to discover neural network architectures by searching for an optimal path within a larger model. The controller is trained with policy gradient to select a path that maximizes the expected reward on the validation set. Meanwhile the model corresponding to the selected path is trained to minimize the cross entropy loss. On the Penn Treebank dataset, ENAS can discover a novel architecture thats achieves a test perplexity of 57.8, which is state-of-the-art among automatic model design methods on Penn Treebank. On the CIFAR-10 dataset, ENAS can design novel architectures that achieve a test error of 2.89%, close to the 2.65% achieved by standard NAS (Zoph et al., 2017). Most importantly, our experiments show that ENAS is more than 10x faster and 100x less resource-demanding than NAS. |
Tasks | Neural Architecture Search |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=ByQZjx-0- |
https://openreview.net/pdf?id=ByQZjx-0- | |
PWC | https://paperswithcode.com/paper/faster-discovery-of-neural-architectures-by |
Repo | |
Framework | |
Exactly two things to learn from modeling scope ambiguity resolution: Developmental continuity and numeral semantics
Title | Exactly two things to learn from modeling scope ambiguity resolution: Developmental continuity and numeral semantics |
Authors | K.J. Savinelli, Greg Scontras, Lisa Pearl |
Abstract | |
Tasks | Language Acquisition |
Published | 2018-01-01 |
URL | https://www.aclweb.org/anthology/W18-0108/ |
https://www.aclweb.org/anthology/W18-0108 | |
PWC | https://paperswithcode.com/paper/exactly-two-things-to-learn-from-modeling |
Repo | |
Framework | |