Paper Group NANR 136
Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing. The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval. Feature-guided Neural Model Training for Supervised Document Representation Learning. Collocation Classification with Unsupervised Relation Vectors. Learning to Generate Word- and Ph …
Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing
| Title | Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing |
| Authors | Jiaxin Chen, Jie Qin, Li Liu, Fan Zhu, Fumin Shen, Jin Xie, Ling Shao |
| Abstract | Sketch-based 3D shape retrieval has been extensively studied in recent works, most of which focus on improving the retrieval accuracy, whilst neglecting the efficiency. In this paper, we propose a novel framework for efficient sketch-based 3D shape retrieval, i.e., Deep Sketch-Shape Hashing (DSSH), which tackles the challenging problem from two perspectives. Firstly, we propose an intuitive 3D shape representation method to deal with unaligned shapes with arbitrary poses. Specifically, the proposed Segmented Stochastic-viewing Shape Network models discriminative 3D representations by a set of 2D images rendered from multiple views, which are stochastically selected from non-overlapping spatial segments of a 3D sphere. Secondly, Batch-Hard Binary Coding (BHBC) is developed to learn semantics-preserving compact binary codes by mining the hardest samples. The overall framework is jointly learned by developing an alternating iteration algorithm. Extensive experimental results on three benchmarks show that DSSH improves both the retrieval efficiency and accuracy remarkably, compared to the state-of-the-art methods. |
| Tasks | 3D Shape Representation, 3D Shape Retrieval |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_Deep_Sketch-Shape_Hashing_With_Segmented_3D_Stochastic_Viewing_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Chen_Deep_Sketch-Shape_Hashing_With_Segmented_3D_Stochastic_Viewing_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-sketch-shape-hashing-with-segmented-3d |
| Repo | |
| Framework | |
The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval
| Title | The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval |
| Authors | Constantine Lignos, Daniel Cohen, Yen-Chieh Lien, Pratik Mehta, W. Bruce Croft, Scott Miller |
| Abstract | When performing cross-language information retrieval (CLIR) for lower-resourced languages, a common approach is to retrieve over the output of machine translation (MT). However, there is no established guidance on how to optimize the resulting MT-IR system. In this paper, we examine the relationship between the performance of MT systems and both neural and term frequency-based IR models to identify how CLIR performance can be best predicted from MT quality. We explore performance at varying amounts of MT training data, byte pair encoding (BPE) merge operations, and across two IR collections and retrieval models. We find that the choice of IR collection can substantially affect the predictive power of MT tuning decisions and evaluation, potentially introducing dissociations between MT-only and overall CLIR performance. |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1353/ |
| https://www.aclweb.org/anthology/D19-1353 | |
| PWC | https://paperswithcode.com/paper/the-challenges-of-optimizing-machine |
| Repo | |
| Framework | |
Feature-guided Neural Model Training for Supervised Document Representation Learning
| Title | Feature-guided Neural Model Training for Supervised Document Representation Learning |
| Authors | Aili Shen, Bahar Salehi, Jianzhong Qi, Timothy Baldwin |
| Abstract | |
| Tasks | Representation Learning |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1007/ |
| https://www.aclweb.org/anthology/U19-1007 | |
| PWC | https://paperswithcode.com/paper/feature-guided-neural-model-training-for |
| Repo | |
| Framework | |
Collocation Classification with Unsupervised Relation Vectors
| Title | Collocation Classification with Unsupervised Relation Vectors |
| Authors | Luis Espinosa Anke, Steven Schockaert, Leo Wanner |
| Abstract | Lexical relation classification is the task of predicting whether a certain relation holds between a given pair of words. In this paper, we explore to which extent the current distributional landscape based on word embeddings provides a suitable basis for classification of collocations, i.e., pairs of words between which idiosyncratic lexical relations hold. First, we introduce a novel dataset with collocations categorized according to lexical functions. Second, we conduct experiments on a subset of this benchmark, comparing it in particular to the well known DiffVec dataset. In these experiments, in addition to simple word vector arithmetic operations, we also investigate the role of unsupervised relation vectors as a complementary input. While these relation vectors indeed help, we also show that lexical function classification poses a greater challenge than the syntactic and semantic relations that are typically used for benchmarks in the literature. |
| Tasks | Relation Classification, Word Embeddings |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1576/ |
| https://www.aclweb.org/anthology/P19-1576 | |
| PWC | https://paperswithcode.com/paper/collocation-classification-with-unsupervised |
| Repo | |
| Framework | |
Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation
| Title | Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation |
| Authors | Chan Young Park, Yulia Tsvetkov |
| Abstract | Neural machine translation (NMT) often fails in one-to-many translation, e.g., in the translation of multi-word expressions, compounds, and collocations. To improve the translation of phrases, phrase-based NMT systems have been proposed; these typically combine word-based NMT with external phrase dictionaries or with phrase tables from phrase-based statistical MT systems. These solutions introduce a significant overhead of additional resources and computational costs. In this paper, we introduce a phrase-based NMT model built upon continuous-output NMT, in which the decoder generates embeddings of words or phrases. The model uses a fertility module, which guides the decoder to generate embeddings of sequences of varying lengths. We show that our model learns to translate phrases better, performing on par with state of the art phrase-based NMT. Since our model does not resort to softmax computation over a huge vocabulary of phrases, its training time is about 112x faster than the baseline. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5626/ |
| https://www.aclweb.org/anthology/D19-5626 | |
| PWC | https://paperswithcode.com/paper/learning-to-generate-word-and-phrase |
| Repo | |
| Framework | |
Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision
| Title | Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision |
| Authors | Abiola Obamuyide, Andreas Vlachos |
| Abstract | In this paper we frame the task of supervised relation classification as an instance of meta-learning. We propose a model-agnostic meta-learning protocol for training relation classifiers to achieve enhanced predictive performance in limited supervision settings. During training, we aim to not only learn good parameters for classifying relations with sufficient supervision, but also learn model parameters that can be fine-tuned to enhance predictive performance for relations with limited supervision. In experiments conducted on two relation classification datasets, we demonstrate that the proposed meta-learning approach improves the predictive performance of two state-of-the-art supervised relation classification models. |
| Tasks | Meta-Learning, Relation Classification |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1589/ |
| https://www.aclweb.org/anthology/P19-1589 | |
| PWC | https://paperswithcode.com/paper/model-agnostic-meta-learning-for-relation |
| Repo | |
| Framework | |
Improved Road Connectivity by Joint Learning of Orientation and Segmentation
| Title | Improved Road Connectivity by Joint Learning of Orientation and Segmentation |
| Authors | Anil Batra, Suriya Singh, Guan Pang, Saikat Basu, C.V. Jawahar, Manohar Paluri |
| Abstract | Road network extraction from satellite images often produce fragmented road segments leading to road maps unfit for real applications. Pixel-wise classification fails to predict topologically correct and connected road masks due to the absence of connectivity supervision and difficulty in enforcing topological constraints. In this paper, we propose a connectivity task called Orientation Learning, motivated by the human behavior of annotating roads by tracing it at a specific orientation. We also develop a stacked multi-branch convolutional module to effectively utilize the mutual information between orientation learning and segmentation tasks. These contributions ensure that the model predicts topologically correct and connected road masks. We also propose Connectivity Refinement approach to further enhance the estimated road networks. The refinement model is pre-trained to connect and refine the corrupted ground-truth masks and later fine-tuned to enhance the predicted road masks. We demonstrate the advantages of our approach on two diverse road extraction datasets SpaceNet and DeepGlobe. Our approach improves over the state-of-the-art techniques by 9% and 7.5% in road topology metric on SpaceNet and DeepGlobe, respectively. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Batra_Improved_Road_Connectivity_by_Joint_Learning_of_Orientation_and_Segmentation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Batra_Improved_Road_Connectivity_by_Joint_Learning_of_Orientation_and_Segmentation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/improved-road-connectivity-by-joint-learning |
| Repo | |
| Framework | |
Semantic Language Model for Tunisian Dialect
| Title | Semantic Language Model for Tunisian Dialect |
| Authors | Abir MASMOUDI, Rim Laatar, Mariem ellouze, lamia hadrich belguith |
| Abstract | In this paper, we describe the process of creating a statistical Language Model (LM) for the Tunisian Dialect. Indeed, this work is part of the realization of Automatic Speech Recognition (ASR) system for the Tunisian Railway Transport Network. Since our eld of work has been limited, there are several words with similar behaviors (semantic for example) but they do not have the same appearance probability; their class groupings will therefore be possible. For these reasons, we propose to build an n-class LM that is based mainly on the integration of purely semantic data. Indeed, each class represents an abstraction of similar labels. In order to improve the sequence labeling task, we proposed to use a discriminative algorithm based on the Conditional Random Field (CRF) model. To better judge our choice of creating an n-class word model, we compared the created model with the 3-gram type model on the same test corpus of evaluation. Additionally, to assess the impact of using the CRF model to perform the semantic labelling task in order to construct semantic classes, we compared the n-class created model with using the CRF in the semantic labelling task and the n- class model without using the CRF in the semantic labelling task. The drawn comparison of the predictive power of the n-class model obtained by applying the CRF model in the semantic labelling is that it is better than the other two models presenting the highest value of its perplexity. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1084/ |
| https://www.aclweb.org/anthology/R19-1084 | |
| PWC | https://paperswithcode.com/paper/semantic-language-model-for-tunisian-dialect |
| Repo | |
| Framework | |
Artwork painting identification method for panorama based on adaptive rectilinear projection and optimized ASIFT
| Title | Artwork painting identification method for panorama based on adaptive rectilinear projection and optimized ASIFT |
| Authors | Dayou, Jiang; Jongweon, Kim |
| Abstract | In the paper, the authors present an artwork painting identification method for panorama based on adaptive rectilinear projection and optimized ASIFT (Affine Scale-Invariant Feature Transform). Firstly, the authors use the panorama dataset to train the artwork painting detection network to obtain the location information of artwork paintings. Secondly, the authors use the adaptive rectilinear projection to map the artwork painting into a square image with a fixed size. Then the authors use the image enhancement method to improve the image quality. Finally, the authors use the optimized ASIFT for features extraction and image matching. Several contrast experiments were conducted on the artwork paintings panorama dataset for artwork paintings identification. The results show that the proposed method can achieve 96% identification accuracy on average for the whole test artwork paintings panorama dataset. The proposed adaptive rectilinear based-method can improve at least 20% of the recognition accuracy. The proposed optimized ASIFT can improve at least 30% of the identification accuracy than SIFT. The authors also study other factors such as the size of the original artwork image, the image matching threshold, whether using image enhancement or not. The results show the size of the original artwork has little influence on the artwork identification in the panorama. The image matching threshold with 2.0 is better than 3.0. Furthermore, using the image enhancement method can improve about 2% of the identification accuracy. |
| Tasks | Image Enhancement |
| Published | 2019-07-28 |
| URL | https://www.mendeley.com/catalogue/artwork-painting-identification-method-panorama-based-adaptive-rectilinear-projection-optimized-asif/ |
| https://sci-hub.tw/10.1007/s11042-019-07985-4 | |
| PWC | https://paperswithcode.com/paper/artwork-painting-identification-method-for |
| Repo | |
| Framework | |
Relation Classification Using Segment-Level Attention-based CNN and Dependency-based RNN
| Title | Relation Classification Using Segment-Level Attention-based CNN and Dependency-based RNN |
| Authors | Van-Hien Tran, Van-Thuy Phi, Hiroyuki Shindo, Yuji Matsumoto |
| Abstract | Recently, relation classification has gained much success by exploiting deep neural networks. In this paper, we propose a new model effectively combining Segment-level Attention-based Convolutional Neural Networks (SACNNs) and Dependency-based Recurrent Neural Networks (DepRNNs). While SACNNs allow the model to selectively focus on the important information segment from the raw sequence, DepRNNs help to handle the long-distance relations from the shortest dependency path of relation entities. Experiments on the SemEval-2010 Task 8 dataset show that our model is comparable to the state-of-the-art without using any external lexical features. |
| Tasks | Relation Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1286/ |
| https://www.aclweb.org/anthology/N19-1286 | |
| PWC | https://paperswithcode.com/paper/relation-classification-using-segment-level |
| Repo | |
| Framework | |
Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings
| Title | Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings |
| Authors | Linh The Nguyen, Linh Van Ngo, Khoat Than, Thien Huu Nguyen |
| Abstract | It has been shown that implicit connectives can be exploited to improve the performance of the models for implicit discourse relation recognition (IDRR). An important property of the implicit connectives is that they can be accurately mapped into the discourse relations conveying their functions. In this work, we explore this property in a multi-task learning framework for IDRR in which the relations and the connectives are simultaneously predicted, and the mapping is leveraged to transfer knowledge between the two prediction tasks via the embeddings of relations and connectives. We propose several techniques to enable such knowledge transfer that yield the state-of-the-art performance for IDRR on several settings of the benchmark dataset (i.e., the Penn Discourse Treebank dataset). |
| Tasks | Multi-Task Learning, Transfer Learning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1411/ |
| https://www.aclweb.org/anthology/P19-1411 | |
| PWC | https://paperswithcode.com/paper/employing-the-correspondence-of-relations-and |
| Repo | |
| Framework | |
Dependency Tree Annotation with Mechanical Turk
| Title | Dependency Tree Annotation with Mechanical Turk |
| Authors | Stephen Tratz |
| Abstract | Crowdsourcing is frequently employed to quickly and inexpensively obtain valuable linguistic annotations but is rarely used for parsing, likely due to the perceived difficulty of the task and the limited training of the available workers. This paper presents what is, to the best of our knowledge, the first published use of Mechanical Turk (or similar platform) to crowdsource parse trees. We pay Turkers to construct unlabeled dependency trees for 500 English sentences using an interactive graphical dependency tree editor, collecting 10 annotations per sentence. Despite not requiring any training, several of the more prolific workers meet or exceed 90{%} attachment agreement with the Penn Treebank (PTB) portion of our data, and, furthermore, for 72{%} of these PTB sentences, at least one Turker produces a perfect parse. Thus, we find that, supported with a simple graphical interface, people with presumably no prior experience can achieve surprisingly high degrees of accuracy on this task. To facilitate research into aggregation techniques for complex crowdsourced annotations, we publicly release our annotated corpus. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5901/ |
| https://www.aclweb.org/anthology/D19-5901 | |
| PWC | https://paperswithcode.com/paper/dependency-tree-annotation-with-mechanical |
| Repo | |
| Framework | |
Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification
| Title | Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification |
| Authors | Si Wu, Guangchang Deng, Jichang Li, Rui Li, Zhiwen Yu, Hau-San Wong |
| Abstract | Learning class-conditional data distributions is crucial for Generative Adversarial Networks (GAN) in semi-supervised learning. To improve both instance synthesis and classification in this setting, we propose an enhanced TripleGAN (EnhancedTGAN) model in this work. We follow the adversarial training scheme of the original TripleGAN, but completely re-design the training targets of the generator and classifier. Specifically, we adopt feature-semantics matching to enhance the generator in learning class-conditional distributions from both the aspects of statistics in the latent space and semantics consistency with respect to the generator and classifier. Since a limited amount of labeled data is not sufficient to determine satisfactory decision boundaries, we include two classifiers, and incorporate collaborative learning into our model to provide better guidance for generator training. The synthesized high-fidelity data can in turn be used for improving classifier training. In the experiments, the superior performance of our approach on multiple benchmark datasets demonstrates the effectiveness of the mutual reinforcement between the generator and classifiers in facilitating semi-supervised instance synthesis and classification. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wu_Enhancing_TripleGAN_for_Semi-Supervised_Conditional_Instance_Synthesis_and_Classification_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wu_Enhancing_TripleGAN_for_Semi-Supervised_Conditional_Instance_Synthesis_and_Classification_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/enhancing-triplegan-for-semi-supervised |
| Repo | |
| Framework | |
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)
| Title | Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-4000/ |
| https://www.aclweb.org/anthology/N19-4000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2019-conference-of-the-3 |
| Repo | |
| Framework | |
Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks
| Title | Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks |
| Authors | Gabriele Farina, Chun Kai Ling, Fei Fang, Tuomas Sandholm |
| Abstract | While Nash equilibrium in extensive-form games is well understood, very little is known about the properties of extensive-form correlated equilibrium (EFCE), both from a behavioral and from a computational point of view. In this setting, the strategic behavior of players is complemented by an external device that privately recommends moves to agents as the game progresses; players are free to deviate at any time, but will then not receive future recommendations. Our contributions are threefold. First, we show that an EFCE can be formulated as the solution to a bilinear saddle-point problem. To showcase how this novel formulation can inspire new algorithms to compute EFCEs, we propose a simple subgradient descent method which exploits this formulation and structural properties of EFCEs. Our method has better scalability than the prior approach based on linear programming. Second, we propose two benchmark games, which we hope will serve as the basis for future evaluation of EFCE solvers. These games were chosen so as to cover two natural application domains for EFCE: conflict resolution via a mediator, and bargaining and negotiation. Third, we document the qualitative behavior of EFCE in our proposed games. We show that the social-welfare-maximizing equilibria in these games are highly nontrivial and exhibit surprisingly subtle sequential behavior that so far has not received attention in the literature. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9122-correlation-in-extensive-form-games-saddle-point-formulation-and-benchmarks |
| http://papers.nips.cc/paper/9122-correlation-in-extensive-form-games-saddle-point-formulation-and-benchmarks.pdf | |
| PWC | https://paperswithcode.com/paper/correlation-in-extensive-form-games-saddle |
| Repo | |
| Framework | |
