Paper Group NANR 44
A Deep Learning based Feature Selection Method with Multi Level Feature Identification and Extraction using Convolutional Neural Network. Classifying Lexical-semantic Relationships by Exploiting Sense/Concept Representations. The Benefit of Syntactic vs. Linear N-grams for Linguistic Description. Robust Guarantees of Stochastic Greedy Algorithms. I …
A Deep Learning based Feature Selection Method with Multi Level Feature Identification and Extraction using Convolutional Neural Network
| Title | A Deep Learning based Feature Selection Method with Multi Level Feature Identification and Extraction using Convolutional Neural Network |
| Authors | Anil K.R, Gladston Raj S |
| Abstract | : Increasing popularity of feature selection in bioinformatics has led to the development of novel algorithms using neural networks. The objectives of the adaptation of neural networks architectures are proposed on efficient and optimal model for feature classification and selection. A competitive end unique approach in feature selection is adopted here using a convolutional neural network (CNN). Deep learning approach on feature selection is the novel idea which can contribute to the evolvement of identification process, diagnostic methods etc. The experimental work has given good result of ranking the attributes by building a CNN model. The traditional concept of CNN for classification has transformed to a modern approach for feature selection. Handling millions of data with multiple class identities can only be classified with a multi layers network. The CNN models are trained in completely supervised way with a batch gradient back propagation. The parameters are tuned and optimized to get better build type. |
| Tasks | Feature Selection |
| Published | 2017-12-01 |
| URL | http://iaetsdjaras.org/gallery/31-jaras-354-december.pdf |
| http://iaetsdjaras.org/gallery/31-jaras-354-december.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-based-feature-selection |
| Repo | |
| Framework | |
Classifying Lexical-semantic Relationships by Exploiting Sense/Concept Representations
| Title | Classifying Lexical-semantic Relationships by Exploiting Sense/Concept Representations |
| Authors | Kentaro Kanada, Tetsunori Kobayashi, Yoshihiko Hayashi |
| Abstract | This paper proposes a method for classifying the type of lexical-semantic relation between a given pair of words. Given an inventory of target relationships, this task can be seen as a multi-class classification problem. We train a supervised classifier by assuming: (1) a specific type of lexical-semantic relation between a pair of words would be indicated by a carefully designed set of relation-specific similarities associated with the words; and (2) the similarities could be effectively computed by {``}sense representations{''} (sense/concept embeddings). The experimental results show that the proposed method clearly outperforms an existing state-of-the-art method that does not utilize sense/concept embeddings, thereby demonstrating the effectiveness of the sense representations. | |
| Tasks | Relation Classification |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1905/ |
| https://www.aclweb.org/anthology/W17-1905 | |
| PWC | https://paperswithcode.com/paper/classifying-lexical-semantic-relationships-by |
| Repo | |
| Framework | |
The Benefit of Syntactic vs. Linear N-grams for Linguistic Description
| Title | The Benefit of Syntactic vs. Linear N-grams for Linguistic Description |
| Authors | Melanie Andresen, Heike Zinsmeister |
| Abstract | |
| Tasks | Language Modelling |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6503/ |
| https://www.aclweb.org/anthology/W17-6503 | |
| PWC | https://paperswithcode.com/paper/the-benefit-of-syntactic-vs-linear-n-grams |
| Repo | |
| Framework | |
Robust Guarantees of Stochastic Greedy Algorithms
| Title | Robust Guarantees of Stochastic Greedy Algorithms |
| Authors | Avinatan Hassidim, Yaron Singer |
| Abstract | In this paper we analyze the robustness of stochastic variants of the greedy algorithm for submodular maximization. Our main result shows that for maximizing a monotone submodular function under a cardinality constraint, iteratively selecting an element whose marginal contribution is approximately maximal in expectation is a sufficient condition to obtain the optimal approximation guarantee with exponentially high probability, assuming the cardinality is sufficiently large. One consequence of our result is that the linear-time STOCHASTIC-GREEDY algorithm recently proposed in (Mirzasoleiman et al.,2015) achieves the optimal running time while maintaining an optimal approximation guarantee. We also show that high probability guarantees cannot be obtained for stochastic greedy algorithms under matroid constraints, and prove an approximation guarantee which holds in expectation. In contrast to the guarantees of the greedy algorithm, we show that the approximation ratio of stochastic local search is arbitrarily bad, with high probability, as well as in expectation. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=475 |
| http://proceedings.mlr.press/v70/hassidim17a/hassidim17a.pdf | |
| PWC | https://paperswithcode.com/paper/robust-guarantees-of-stochastic-greedy |
| Repo | |
| Framework | |
Incorporating Dialectal Variability for Socially Equitable Language Identification
| Title | Incorporating Dialectal Variability for Socially Equitable Language Identification |
| Authors | David Jurgens, Yulia Tsvetkov, Dan Jurafsky |
| Abstract | Language identification (LID) is a critical first step for processing multilingual text. Yet most LID systems are not designed to handle the linguistic diversity of global platforms like Twitter, where local dialects and rampant code-switching lead language classifiers to systematically miss minority dialect speakers and multilingual speakers. We propose a new dataset and a character-based sequence-to-sequence model for LID designed to support dialectal and multilingual language varieties. Our model achieves state-of-the-art performance on multiple LID benchmarks. Furthermore, in a case study using Twitter for health tracking, our method substantially increases the availability of texts written by underrepresented populations, enabling the development of {``}socially inclusive{''} NLP tools. | |
| Tasks | Language Identification |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2009/ |
| https://www.aclweb.org/anthology/P17-2009 | |
| PWC | https://paperswithcode.com/paper/incorporating-dialectal-variability-for |
| Repo | |
| Framework | |
Estimating Defocus Blur via Rank of Local Patches
| Title | Estimating Defocus Blur via Rank of Local Patches |
| Authors | Guodong Xu, Yuhui Quan, Hui Ji |
| Abstract | This paper addresses the problem of defocus map estimation from a single image. We present a fast yet effective approach to estimate the spatially varying amounts of defocus blur at edge locations, which is based on the maximum, ranks of the corresponding local patches with different orientations in gradient domain. Such an approach is motivated by the theoretical analysis which reveals the connection between the rank of a local patch blurred by a defocus blur kernel and the blur amount by the kernel. After the amounts of defocus blur at edge locations are obtained, a complete defocus map is generated by a standard propagation procedure. The proposed method is extensively evaluated on real image datasets, and the experimental results show its superior performance to existing approaches.proposed method is extensively evaluated on real data, and the experimental results show its superior performance to existing approaches. |
| Tasks | |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Xu_Estimating_Defocus_Blur_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Xu_Estimating_Defocus_Blur_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-defocus-blur-via-rank-of-local |
| Repo | |
| Framework | |
Proceedings of the Australasian Language Technology Association Workshop 2017
| Title | Proceedings of the Australasian Language Technology Association Workshop 2017 |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1000/ |
| https://www.aclweb.org/anthology/U17-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-australasian-language-3 |
| Repo | |
| Framework | |
Fine-Grained Image Classification via Combining Vision and Language
| Title | Fine-Grained Image Classification via Combining Vision and Language |
| Authors | Xiangteng He, Yuxin Peng |
| Abstract | Fine-grained image classification is a challenging task due to the large intra-class variance and small inter-class variance, aiming at recognizing hundreds of sub-categories belonging to the same basic-level category. Most existing fine-grained image classification methods generally learn part detection models to obtain the semantic parts for better classification accuracy. Despite achieving promising results, these methods mainly have two limitations: (1) not all the parts which obtained through the part detection models are beneficial and indispensable for classification, and (2) fine-grained image classification requires more detailed visual descriptions which could not be provided by the part locations or attribute annotations. For addressing the above two limitations, this paper proposes the two-stream model combing vision and language (CVL) for learning latent semantic representations. The vision stream learns deep representations from the original visual information via deep convolutional neural network. The language stream utilizes the natural language descriptions which could point out the discriminative parts or characteristics for each image, and provides a flexible and compact way of encoding the salient visual aspects for distinguishing sub-categories. Since the two streams are complementary, combing the two streams can further achieves better classification accuracy. Comparing with 12 state-of-the-art methods on the widely used CUB-200-2011 dataset for fine-grained image classification, the experimental results demonstrate our CVL approach achieves the best performance. |
| Tasks | Fine-Grained Image Classification, Image Classification |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/He_Fine-Grained_Image_Classification_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/He_Fine-Grained_Image_Classification_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-image-classification-via |
| Repo | |
| Framework | |
Endangered Data for Endangered Languages: Digitizing Print dictionaries
| Title | Endangered Data for Endangered Languages: Digitizing Print dictionaries |
| Authors | Michael Maxwell, Aric Bills |
| Abstract | |
| Tasks | Optical Character Recognition |
| Published | 2017-03-01 |
| URL | https://www.aclweb.org/anthology/W17-0112/ |
| https://www.aclweb.org/anthology/W17-0112 | |
| PWC | https://paperswithcode.com/paper/endangered-data-for-endangered-languages |
| Repo | |
| Framework | |
Memory Augmented Neural Networks for Natural Language Processing
| Title | Memory Augmented Neural Networks for Natural Language Processing |
| Authors | Caglar Gulcehre, Ch, Sarath ar |
| Abstract | Designing of general-purpose learning algorithms is a long-standing goal of artificial intelligence. A general purpose AI agent should be able to have a memory that it can store and retrieve information from. Despite the success of deep learning in particular with the introduction of LSTMs and GRUs to this area, there are still a set of complex tasks that can be challenging for conventional neural networks. Those tasks often require a neural network to be equipped with an explicit, external memory in which a larger, potentially unbounded, set of facts need to be stored. They include but are not limited to, reasoning, planning, episodic question-answering and learning compact algorithms. Recently two promising approaches based on neural networks to this type of tasks have been proposed: Memory Networks and Neural Turing Machines.In this tutorial, we will give an overview of this new paradigm of {``}neural networks with memory{''}. We will present a unified architecture for Memory Augmented Neural Networks (MANN) and discuss the ways in which one can address the external memory and hence read/write from it. Then we will introduce Neural Turing Machines and Memory Networks as specific instantiations of this general architecture. In the second half of the tutorial, we will focus on recent advances in MANN which focus on the following questions: How can we read/write from an extremely large memory in a scalable way? How can we design efficient non-linear addressing schemes? How can we do efficient reasoning using large scale memory and an episodic memory? The answer to any one of these questions introduces a variant of MANN. We will conclude the tutorial with several open challenges in MANN and its applications to NLP.We will introduce several applications of MANN in NLP throughout the tutorial. Few examples include language modeling, question answering, visual question answering, and dialogue systems.For updated information and material, please refer to our tutorial website: https://sites.google.com/view/mann-emnlp2017/. | |
| Tasks | Language Modelling, Question Answering, Visual Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-3005/ |
| https://www.aclweb.org/anthology/D17-3005 | |
| PWC | https://paperswithcode.com/paper/memory-augmented-neural-networks-for-natural |
| Repo | |
| Framework | |
Word Learning by Young Bilinguals: Understanding the Denotation and Connotation Differences of ``Cut’’ Verbs in English and Chinese
| Title | Word Learning by Young Bilinguals: Understanding the Denotation and Connotation Differences of ``Cut’’ Verbs in English and Chinese | |
| Authors | Keng Hwee Neo, Helena Gao |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1033/ |
| https://www.aclweb.org/anthology/Y17-1033 | |
| PWC | https://paperswithcode.com/paper/word-learning-by-young-bilinguals |
| Repo | |
| Framework | |
Investigating the Relationship between Literary Genres and Emotional Plot Development
| Title | Investigating the Relationship between Literary Genres and Emotional Plot Development |
| Authors | Evgeny Kim, Sebastian Pad{'o}, Roman Klinger |
| Abstract | Literary genres are commonly viewed as being defined in terms of content and stylistic features. In this paper, we focus on one particular class of lexical features, namely emotion information, and investigate the hypothesis that emotion-related information correlates with particular genres. Using genre classification as a testbed, we compare a model that computes lexicon-based emotion scores globally for complete stories with a model that tracks emotion arcs through stories on a subset of Project Gutenberg with five genres. Our main findings are: (a), the global emotion model is competitive with a large-vocabulary bag-of-words genre classifier (80{%}F1); (b), the emotion arc model shows a lower performance (59 {%} F1) but shows complementary behavior to the global model, as indicated by a very good performance of an oracle model (94 {%} F1) and an improved performance of an ensemble model (84 {%} F1); (c), genres differ in the extent to which stories follow the same emotional arcs, with particularly uniform behavior for anger (mystery) and fear (adventures, romance, humor, science fiction). |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2203/ |
| https://www.aclweb.org/anthology/W17-2203 | |
| PWC | https://paperswithcode.com/paper/investigating-the-relationship-between |
| Repo | |
| Framework | |
Stochastic and Adversarial Online Learning without Hyperparameters
| Title | Stochastic and Adversarial Online Learning without Hyperparameters |
| Authors | Ashok Cutkosky, Kwabena A. Boahen |
| Abstract | Most online optimization algorithms focus on one of two things: performing well in adversarial settings by adapting to unknown data parameters (such as Lipschitz constants), typically achieving $O(\sqrt{T})$ regret, or performing well in stochastic settings where they can leverage some structure in the losses (such as strong convexity), typically achieving $O(\log(T))$ regret. Algorithms that focus on the former problem hitherto achieved $O(\sqrt{T})$ in the stochastic setting rather than $O(\log(T))$. Here we introduce an online optimization algorithm that achieves $O(\log^4(T))$ regret in a wide class of stochastic settings while gracefully degrading to the optimal $O(\sqrt{T})$ regret in adversarial settings (up to logarithmic factors). Our algorithm does not require any prior knowledge about the data or tuning of parameters to achieve superior performance. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7091-stochastic-and-adversarial-online-learning-without-hyperparameters |
| http://papers.nips.cc/paper/7091-stochastic-and-adversarial-online-learning-without-hyperparameters.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-and-adversarial-online-learning |
| Repo | |
| Framework | |
Learning from Relatives: Unified Dialectal Arabic Segmentation
| Title | Learning from Relatives: Unified Dialectal Arabic Segmentation |
| Authors | Younes Samih, Mohamed Eldesouki, Mohammed Attia, Kareem Darwish, Ahmed Abdelali, Hamdy Mubarak, Laura Kallmeyer |
| Abstract | Arabic dialects do not just share a common koin{'e}, but there are shared pan-dialectal linguistic phenomena that allow computational models for dialects to learn from each other. In this paper we build a unified segmentation model where the training data for different dialects are combined and a single model is trained. The model yields higher accuracies than dialect-specific models, eliminating the need for dialect identification before segmentation. We also measure the degree of relatedness between four major Arabic dialects by testing how a segmentation model trained on one dialect performs on the other dialects. We found that linguistic relatedness is contingent with geographical proximity. In our experiments we use SVM-based ranking and bi-LSTM-CRF sequence labeling. |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1043/ |
| https://www.aclweb.org/anthology/K17-1043 | |
| PWC | https://paperswithcode.com/paper/learning-from-relatives-unified-dialectal |
| Repo | |
| Framework | |
Human Evaluation of Multi-modal Neural Machine Translation: A Case-Study on E-Commerce Listing Titles
| Title | Human Evaluation of Multi-modal Neural Machine Translation: A Case-Study on E-Commerce Listing Titles |
| Authors | Iacer Calixto, Daniel Stein, Evgeny Matusov, Sheila Castilho, Andy Way |
| Abstract | In this paper, we study how humans perceive the use of images as an additional knowledge source to machine-translate user-generated product listings in an e-commerce company. We conduct a human evaluation where we assess how a multi-modal neural machine translation (NMT) model compares to two text-only approaches: a conventional state-of-the-art attention-based NMT and a phrase-based statistical machine translation (PBSMT) model. We evaluate translations obtained with different systems and also discuss the data set of user-generated product listings, which in our case comprises both product listings and associated images. We found that humans preferred translations obtained with a PBSMT system to both text-only and multi-modal NMT over 56{%} of the time. Nonetheless, human evaluators ranked translations from a multi-modal NMT model as better than those of a text-only NMT over 88{%} of the time, which suggests that images do help NMT in this use-case. |
| Tasks | Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-2004/ |
| https://www.aclweb.org/anthology/W17-2004 | |
| PWC | https://paperswithcode.com/paper/human-evaluation-of-multi-modal-neural |
| Repo | |
| Framework | |
