Paper Group NAWR 11
RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-imbalanced Labels for Network Embedding. Neural Activation Semantic Models: Computational lexical semantic models of localized neural activations. Reproducing and Regularizing the SCRN Model. Crowd Counting With Deep Negative Correlation Learning. The Influence of Context on Sent …
RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-imbalanced Labels for Network Embedding
Title | RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-imbalanced Labels for Network Embedding |
Authors | ZhengWang, Xiaojun Ye, Chaokun Wang, YuexinWu, ChangpingWang, Kaiwen Liang |
Abstract | Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promising performance. However, existing semi-supervised methods would get unappealing results in the completely-imbalanced label setting where some classes have no labeled nodes at all. To alleviate this, we propose a novel semi-supervised network embedding method, termed Relaxed Similarity and Dissimilarity Network Embedding (RSDNE). Specifically, to benefit from the completely-imbalanced labels, RSDNE guarantees both intra-class similarity and inter-class dissimilarity in an approximate way. Experimental results on several real-world datasets demonstrate the superiority of the proposed method. |
Tasks | Network Embedding |
Published | 2018-04-25 |
URL | https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16062 |
https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16062/15722 | |
PWC | https://paperswithcode.com/paper/rsdne-exploring-relaxed-similarity-and |
Repo | https://github.com/zhengwang100/RSDNE-python |
Framework | none |
Neural Activation Semantic Models: Computational lexical semantic models of localized neural activations
Title | Neural Activation Semantic Models: Computational lexical semantic models of localized neural activations |
Authors | Nikos Athanasiou, Elias Iosif, Alex Potamianos, ros |
Abstract | Neural activation models have been proposed in the literature that use a set of example words for which fMRI measurements are available in order to find a mapping between word semantics and localized neural activations. Successful mappings let us expand to the full lexicon of concrete nouns using the assumption that similarity of meaning implies similar neural activation patterns. In this paper, we propose a computational model that estimates semantic similarity in the neural activation space and investigates the relative performance of this model for various natural language processing tasks. Despite the simplicity of the proposed model and the very small number of example words used to bootstrap it, the neural activation semantic model performs surprisingly well compared to state-of-the-art word embeddings. Specifically, the neural activation semantic model performs better than the state-of-the-art for the task of semantic similarity estimation between very similar or very dissimilar words, while performing well on other tasks such as entailment and word categorization. These are strong indications that neural activation semantic models can not only shed some light into human cognition but also contribute to computation models for certain tasks. |
Tasks | Dimensionality Reduction, Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1243/ |
https://www.aclweb.org/anthology/C18-1243 | |
PWC | https://paperswithcode.com/paper/neural-activation-semantic-models |
Repo | https://github.com/athn-nik/neural_asm |
Framework | none |
Reproducing and Regularizing the SCRN Model
Title | Reproducing and Regularizing the SCRN Model |
Authors | Olzhas Kabdolov, Zhenisbek Assylbekov, Rustem Takhanov |
Abstract | We reproduce the Structurally Constrained Recurrent Network (SCRN) model, and then regularize it using the existing widespread techniques, such as naive dropout, variational dropout, and weight tying. We show that when regularized and optimized appropriately the SCRN model can achieve performance comparable with the ubiquitous LSTM model in language modeling task on English data, while outperforming it on non-English data. |
Tasks | Language Modelling |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1145/ |
https://www.aclweb.org/anthology/C18-1145 | |
PWC | https://paperswithcode.com/paper/reproducing-and-regularizing-the-scrn-model |
Repo | https://github.com/zh3nis/scrn |
Framework | tf |
Crowd Counting With Deep Negative Correlation Learning
Title | Crowd Counting With Deep Negative Correlation Learning |
Authors | Zenglin Shi, Le Zhang, Yun Liu, Xiaofeng Cao, Yangdong Ye, Ming-Ming Cheng, Guoyan Zheng |
Abstract | Deep convolutional networks (ConvNets) have achieved unprecedented performances on many computer vision tasks. However, their adaptations to crowd counting on single images are still in their infancy and suffer from severe over-fitting. Here we propose a new learning strategy to produce generalizable features by way of deep negative correlation learning (NCL). More specifically, we deeply learn a pool of decorrelated regressors with sound generalization capabilities through managing their intrinsic diversities. Our proposed method, named decorrelated ConvNet (D-ConvNet), is end-to-end-trainable and independent of the backbone fully-convolutional network architectures. Extensive experiments on very deep VGGNet as well as our customized network structure indicate the superiority of D-ConvNet when compared with several state-of-the-art methods. Our implementation will be released at https://github.com/shizenglin/Deep-NCL |
Tasks | Crowd Counting |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Shi_Crowd_Counting_With_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Shi_Crowd_Counting_With_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/crowd-counting-with-deep-negative-correlation |
Repo | https://github.com/shizenglin/Deep-NCL |
Framework | none |
The Influence of Context on Sentence Acceptability Judgements
Title | The Influence of Context on Sentence Acceptability Judgements |
Authors | Jean-Philippe Bernardy, Shalom Lappin, Jey Han Lau |
Abstract | We investigate the influence that document context exerts on human acceptability judgements for English sentences, via two sets of experiments. The first compares ratings for sentences presented on their own with ratings for the same set of sentences given in their document contexts. The second assesses the accuracy with which two types of neural models {—} one that incorporates context during training and one that does not {—} predict these judgements. Our results indicate that: (1) context improves acceptability ratings for ill-formed sentences, but also reduces them for well-formed sentences; and (2) context helps unsupervised systems to model acceptability. |
Tasks | Language Modelling, Machine Translation, Text Generation |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-2073/ |
https://www.aclweb.org/anthology/P18-2073 | |
PWC | https://paperswithcode.com/paper/the-influence-of-context-on-sentence |
Repo | https://github.com/GU-CLASP/BLL2018 |
Framework | none |
Sharing Copies of Synthetic Clinical Corpora without Physical Distribution — A Case Study to Get Around IPRs and Privacy Constraints Featuring the German JSYNCC Corpus
Title | Sharing Copies of Synthetic Clinical Corpora without Physical Distribution — A Case Study to Get Around IPRs and Privacy Constraints Featuring the German JSYNCC Corpus |
Authors | Christina Lohr, Sven Buechel, Udo Hahn |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1201/ |
https://www.aclweb.org/anthology/L18-1201 | |
PWC | https://paperswithcode.com/paper/sharing-copies-of-synthetic-clinical-corpora |
Repo | https://github.com/JULIELab/jsyncc |
Framework | none |
deepQuest: A Framework for Neural-based Quality Estimation
Title | deepQuest: A Framework for Neural-based Quality Estimation |
Authors | Julia Ive, Fr{'e}d{'e}ric Blain, Lucia Specia |
Abstract | Predicting Machine Translation (MT) quality can help in many practical tasks such as MT post-editing. The performance of Quality Estimation (QE) methods has drastically improved recently with the introduction of neural approaches to the problem. However, thus far neural approaches have only been designed for word and sentence-level prediction. We present a neural framework that is able to accommodate neural QE approaches at these fine-grained levels and generalize them to the level of documents. We test the framework with two sentence-level neural QE approaches: a state of the art approach that requires extensive pre-training, and a new light-weight approach that we propose, which employs basic encoders. Our approach is significantly faster and yields performance improvements for a range of document-level quality estimation tasks. To our knowledge, this is the first neural architecture for document-level QE. In addition, for the first time we apply QE models to the output of both statistical and neural MT systems for a series of European languages and highlight the new challenges resulting from the use of neural MT. |
Tasks | Feature Engineering, Machine Translation |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1266/ |
https://www.aclweb.org/anthology/C18-1266 | |
PWC | https://paperswithcode.com/paper/deepquest-a-framework-for-neural-based |
Repo | https://github.com/fredblain/docQE |
Framework | none |
SwapNet: Garment Transfer in Single View Images
Title | SwapNet: Garment Transfer in Single View Images |
Authors | Amit Raj, Patsorn Sangkloy, Huiwen Chang, Jingwan Lu, Duygu Ceylan, James Hays |
Abstract | We present SwapNet, a framework to transfer garments across images of people with arbitrary body pose, shape, and clothing. Garment transfer is a challenging task that requires (i) disentangling the features of the clothing from the body pose and shape and (ii) realistic synthesis of the garment texture on the new body. We present a neural network architecture that tackles these sub-problems with two task-specific sub-networks. Since acquiring pairs of images showing the same clothing on different bodies is difficult, we propose a novel weakly-supervised approach that generates training pairs from a single image via data augmentation. We present the first fully automatic method for garment transfer in unconstrained images without solving the difficult 3D reconstruction problem. We demonstrate a variety of transfer results and highlight our advantages over traditional image-to-image and analogy pipelines. |
Tasks | 3D Reconstruction, Data Augmentation |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Amit_Raj_SwapNet_Garment_Transfer_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Amit_Raj_SwapNet_Garment_Transfer_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/swapnet-garment-transfer-in-single-view |
Repo | https://github.com/andrewjong/SwapNet |
Framework | pytorch |
Gourmet Photography Dataset for Aesthetic Assessment of Food Images
Title | Gourmet Photography Dataset for Aesthetic Assessment of Food Images |
Authors | Kekai Sheng, Weiming Dong, Haibin Huang, Chongyang Ma, Bao-Gang Hu |
Abstract | In this study, we present the Gourmet Photography Dataset (GPD), which is the first large-scale dataset for aesthetic assessment of food photographs. We collect 12,000 food images together with human-annotated labels (i.e., aesthetically positive or negative) to build this dataset. We evaluate the performance of several popular machine learning algorithms for aesthetic assessment of food images to verify the effectiveness and importance of our GPD dataset. Experimental results show that deep convolutional neural networks trained on GPD can achieve comparable performance with human experts in this task, even on unseen food photographs. Our experiments also provide insights to support further study and applications related to visual analysis of food images. |
Tasks | |
Published | 2018-12-04 |
URL | https://www.researchgate.net/publication/329329757_Gourmet_photography_dataset_for_aesthetic_assessment_of_food_images |
https://www.researchgate.net/publication/329329757_Gourmet_photography_dataset_for_aesthetic_assessment_of_food_images | |
PWC | https://paperswithcode.com/paper/gourmet-photography-dataset-for-aesthetic |
Repo | https://github.com/Openning07/GPA |
Framework | none |
Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing
Title | Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing |
Authors | Zilong Huang, Xinggang Wang, Jiasi Wang, Wenyu Liu, Jingdong Wang |
Abstract | This paper studies the problem of learning image semantic segmentation networks only using image-level labels as supervision, which is important since it can significantly reduce human annotation efforts. Recent state-of-the-art methods on this problem first infer the sparse and discriminative regions for each object class using a deep classification network, then train semantic a segmentation network using the discriminative regions as supervision. Inspired by the traditional image segmentation methods of seeded region growing, we propose to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing. The seeded region growing module is integrated in a deep segmentation network and can benefit from deep features. Different from conventional deep networks which have fixed/static labels, the proposed weakly-supervised network generates new labels using the contextual information within an image. The proposed method significantly outperforms the weakly-supervised semantic segmentation methods using static labels, and obtains the state-of-the-art performance, which are 63.2% mIoU score on the PASCAL VOC 2012 test set and 26.0% mIoU score on the COCO dataset. |
Tasks | Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Huang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/weakly-supervised-semantic-segmentation |
Repo | https://github.com/speedinghzl/DSRG |
Framework | caffe2 |
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)
Title | Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) |
Authors | Nicoletta Calzolari, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Koiti Hasida, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, H{'e}l{`e}ne Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis, Takenobu Tokunaga |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1000/ |
https://www.aclweb.org/anthology/L18-1.pdf | |
PWC | https://paperswithcode.com/paper/proceedings-of-the-eleventh-international-1 |
Repo | https://github.com/commul/fromthepage |
Framework | none |
Projecting Embeddings for Domain Adaption: Joint Modeling of Sentiment Analysis in Diverse Domains
Title | Projecting Embeddings for Domain Adaption: Joint Modeling of Sentiment Analysis in Diverse Domains |
Authors | Jeremy Barnes, Roman Klinger, Sabine Schulte im Walde |
Abstract | Domain adaptation for sentiment analysis is challenging due to the fact that supervised classifiers are very sensitive to changes in domain. The two most prominent approaches to this problem are structural correspondence learning and autoencoders. However, they either require long training times or suffer greatly on highly divergent domains. Inspired by recent advances in cross-lingual sentiment analysis, we provide a novel perspective and cast the domain adaptation problem as an embedding projection task. Our model takes as input two mono-domain embedding spaces and learns to project them to a bi-domain space, which is jointly optimized to (1) project across domains and to (2) predict sentiment. We perform domain adaptation experiments on 20 source-target domain pairs for sentiment classification and report novel state-of-the-art results on 11 domain pairs, including the Amazon domain adaptation datasets and SemEval 2013 and 2016 datasets. Our analysis shows that our model performs comparably to state-of-the-art approaches on domains that are similar, while performing significantly better on highly divergent domains. Our code is available at https://github.com/jbarnesspain/domain{_}blse |
Tasks | Domain Adaptation, Sentiment Analysis |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1070/ |
https://www.aclweb.org/anthology/C18-1070 | |
PWC | https://paperswithcode.com/paper/projecting-embeddings-for-domain-adaption |
Repo | https://github.com/jbarnesspain/domain_blse |
Framework | pytorch |
Named Entity Recognition for Hindi-English Code-Mixed Social Media Text
Title | Named Entity Recognition for Hindi-English Code-Mixed Social Media Text |
Authors | Vinay Singh, Deepanshu Vijay, Syed Sarfaraz Akhtar, Manish Shrivastava |
Abstract | Named Entity Recognition (NER) is a major task in the field of Natural Language Processing (NLP), and also is a sub-task of Information Extraction. The challenge of NER for tweets lie in the insufficient information available in a tweet. There has been a significant amount of work done related to entity extraction, but only for resource rich languages and domains such as newswire. Entity extraction is, in general, a challenging task for such an informal text, and code-mixed text further complicates the process with it{'}s unstructured and incomplete information. We propose experiments with different machine learning classification algorithms with word, character and lexical features. The algorithms we experimented with are Decision tree, Long Short-Term Memory (LSTM), and Conditional Random Field (CRF). In this paper, we present a corpus for NER in Hindi-English Code-Mixed along with extensive experiments on our machine learning models which achieved the best f1-score of 0.95 with both CRF and LSTM. |
Tasks | Entity Extraction, Named Entity Recognition |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-2405/ |
https://www.aclweb.org/anthology/W18-2405 | |
PWC | https://paperswithcode.com/paper/named-entity-recognition-for-hindi-english |
Repo | https://github.com/SilentFlame/Named-Entity-Recognition |
Framework | none |
Deep Density Destructors
Title | Deep Density Destructors |
Authors | David Inouye, Pradeep Ravikumar |
Abstract | We propose a unified framework for deep density models by formally defining density destructors. A density destructor is an invertible function that transforms a given density to the uniform density—essentially destroying any structure in the original density. This destructive transformation generalizes Gaussianization via ICA and more recent autoregressive models such as MAF and Real NVP. Informally, this transformation can be seen as a generalized whitening procedure or a multivariate generalization of the univariate CDF function. Unlike Gaussianization, our destructive transformation has the elegant property that the density function is equal to the absolute value of the Jacobian determinant. Thus, each layer of a deep density can be seen as a shallow density—uncovering a fundamental connection between shallow and deep densities. In addition, our framework provides a common interface for all previous methods enabling them to be systematically combined, evaluated and improved. Leveraging the connection to shallow densities, we also propose a novel tree destructor based on tree densities and an image-specific destructor based on pixel locality. We illustrate our framework on a 2D dataset, MNIST, and CIFAR-10. Code is available on first author’s website. |
Tasks | Density Estimation |
Published | 2018-07-01 |
URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2437 |
http://proceedings.mlr.press/v80/inouye18a/inouye18a.pdf | |
PWC | https://paperswithcode.com/paper/deep-density-destructors |
Repo | https://github.com/davidinouye/destructive-deep-learning |
Framework | none |
Predicting Concreteness and Imageability of Words Within and Across Languages via Word Embeddings
Title | Predicting Concreteness and Imageability of Words Within and Across Languages via Word Embeddings |
Authors | Nikola Ljube{\v{s}}i{'c}, Darja Fi{\v{s}}er, Anita Peti-Stanti{'c} |
Abstract | The notions of concreteness and imageability, traditionally important in psycholinguistics, are gaining significance in semantic-oriented natural language processing tasks. In this paper we investigate the predictability of these two concepts via supervised learning, using word embeddings as explanatory variables. We perform predictions both within and across languages by exploiting collections of cross-lingual embeddings aligned to a single vector space. We show that the notions of concreteness and imageability are highly predictable both within and across languages, with a moderate loss of up to 20{%} in correlation when predicting across languages. We further show that the cross-lingual transfer via word embeddings is more efficient than the simple transfer via bilingual dictionaries. |
Tasks | Cross-Lingual Transfer, Representation Learning, Word Embeddings |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-3028/ |
https://www.aclweb.org/anthology/W18-3028 | |
PWC | https://paperswithcode.com/paper/predicting-concreteness-and-imageability-of-1 |
Repo | https://github.com/clarinsi/megahr-crossling |
Framework | none |