Paper Group NANR 110
CUHK at MRP 2019: Transition-Based Parser with Cross-Framework Variable-Arity Resolve Action. The many dimensions of algorithmic fairness in educational applications. Grammaticalization in Derivational Morphology: Verification of the Process by Innovative Derivatives. Domain Adaptation for Low-Resource Neural Semantic Parsing. Skin-Based Identifica …
CUHK at MRP 2019: Transition-Based Parser with Cross-Framework Variable-Arity Resolve Action
| Title | CUHK at MRP 2019: Transition-Based Parser with Cross-Framework Variable-Arity Resolve Action |
| Authors | Sunny Lai, Chun Hei Lo, Kwong Sak Leung, Yee Leung |
| Abstract | This paper describes our system (RESOLVER) submitted to the CoNLL 2019 shared task on Cross-Framework Meaning Representation Parsing (MRP). Our system implements a transition-based parser with a directed acyclic graph (DAG) to tree preprocessor and a novel cross-framework variable-arity resolve action that generalizes over five different representations. Although we ranked low in the competition, we have shown the current limitations and potentials of including variable-arity action in MRP and concluded with directions for improvements in the future. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2010/ |
| https://www.aclweb.org/anthology/K19-2010 | |
| PWC | https://paperswithcode.com/paper/cuhk-at-mrp-2019-transition-based-parser-with |
| Repo | |
| Framework | |
The many dimensions of algorithmic fairness in educational applications
| Title | The many dimensions of algorithmic fairness in educational applications |
| Authors | Anastassia Loukina, Nitin Madnani, Klaus Zechner |
| Abstract | The issues of algorithmic fairness and bias have recently featured prominently in many publications highlighting the fact that training the algorithms for maximum performance may often result in predictions that are biased against various groups. Educational applications based on NLP and speech processing technologies often combine multiple complex machine learning algorithms and are thus vulnerable to the same sources of bias as other machine learning systems. Yet such systems can have high impact on people{'}s lives especially when deployed as part of high-stakes tests. In this paper we discuss different definitions of fairness and possible ways to apply them to educational applications. We then use simulated and real data to consider how test-takers{'} native language backgrounds can affect their automated scores on an English language proficiency assessment. We illustrate that total fairness may not be achievable and that different definitions of fairness may require different solutions. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4401/ |
| https://www.aclweb.org/anthology/W19-4401 | |
| PWC | https://paperswithcode.com/paper/the-many-dimensions-of-algorithmic-fairness |
| Repo | |
| Framework | |
Grammaticalization in Derivational Morphology: Verification of the Process by Innovative Derivatives
| Title | Grammaticalization in Derivational Morphology: Verification of the Process by Innovative Derivatives |
| Authors | Junya Morita |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8514/ |
| https://www.aclweb.org/anthology/W19-8514 | |
| PWC | https://paperswithcode.com/paper/grammaticalization-in-derivational-morphology |
| Repo | |
| Framework | |
Domain Adaptation for Low-Resource Neural Semantic Parsing
| Title | Domain Adaptation for Low-Resource Neural Semantic Parsing |
| Authors | Alvin Kennardi, Gabriela Ferraro, Qing Wang |
| Abstract | |
| Tasks | Domain Adaptation, Semantic Parsing |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1012/ |
| https://www.aclweb.org/anthology/U19-1012 | |
| PWC | https://paperswithcode.com/paper/domain-adaptation-for-low-resource-neural |
| Repo | |
| Framework | |
Skin-Based Identification From Multispectral Image Data Using CNNs
| Title | Skin-Based Identification From Multispectral Image Data Using CNNs |
| Authors | Takeshi Uemori, Atsushi Ito, Yusuke Moriuchi, Alexander Gatto, Jun Murayama |
| Abstract | User identification from hand images only is still a challenging task. In this paper, we propose a new biometric identification system based solely on a skin patch from a multispectral image. The system is utilizing a novel modified 3D CNN architecture which is taking advantage of multispectral data. We demonstrate the application of our system for the example of human identification from multispectral images of hands. To the best of our knowledge, this paper is the first to describe a pose-invariant and robust to overlapping real-time human identification system using hands. Additionally, we provide a framework to optimize the required spectral bands for the given spatial resolution limitations. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Uemori_Skin-Based_Identification_From_Multispectral_Image_Data_Using_CNNs_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Uemori_Skin-Based_Identification_From_Multispectral_Image_Data_Using_CNNs_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/skin-based-identification-from-multispectral |
| Repo | |
| Framework | |
Approximation capability of neural networks on sets of probability measures and tree-structured data
| Title | Approximation capability of neural networks on sets of probability measures and tree-structured data |
| Authors | Tomáš Pevný, Vojtěch Kovařík |
| Abstract | This paper extends the proof of density of neural networks in the space of continuous (or even measurable) functions on Euclidean spaces to functions on compact sets of probability measures. By doing so the work parallels a more then a decade old results on mean-map embedding of probability measures in reproducing kernel Hilbert spaces. The work has wide practical consequences for multi-instance learning, where it theoretically justifies some recently proposed constructions. The result is then extended to Cartesian products, yielding universal approximation theorem for tree-structured domains, which naturally occur in data-exchange formats like JSON, XML, YAML, AVRO, and ProtoBuffer. This has important practical implications, as it enables to automatically create an architecture of neural networks for processing structured data (AutoML paradigms), as demonstrated by an accompanied library for JSON format. |
| Tasks | AutoML |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HklJV3A9Ym |
| https://openreview.net/pdf?id=HklJV3A9Ym | |
| PWC | https://paperswithcode.com/paper/approximation-capability-of-neural-networks |
| Repo | |
| Framework | |
Pixel Redrawn For A Robust Adversarial Defense
| Title | Pixel Redrawn For A Robust Adversarial Defense |
| Authors | Jiacang Ho, Dae-Ki Kang |
| Abstract | Recently, an adversarial example becomes a serious problem to be aware of because it can fool trained neural networks easily. To prevent the issue, many researchers have proposed several defense techniques such as adversarial training, input transformation, stochastic activation pruning, etc. In this paper, we propose a novel defense technique, Pixel Redrawn (PR) method, which redraws every pixel of training images to convert them into distorted images. The motivation for our PR method is from the observation that the adversarial attacks have redrawn some pixels of the original image with the known parameters of the trained neural network. Mimicking these attacks, our PR method redraws the image without any knowledge of the trained neural network. This method can be similar to the adversarial training method but our PR method can be used to prevent future attacks. Experimental results on several benchmark datasets indicate our PR method not only relieves the over-fitting issue when we train neural networks with a large number of epochs, but it also boosts the robustness of the neural network. |
| Tasks | Adversarial Defense |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1ez_sRcFQ |
| https://openreview.net/pdf?id=r1ez_sRcFQ | |
| PWC | https://paperswithcode.com/paper/pixel-redrawn-for-a-robust-adversarial |
| Repo | |
| Framework | |
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
| Title | Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1000/ |
| https://www.aclweb.org/anthology/K19-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-23rd-conference-on |
| Repo | |
| Framework | |
A Lexicon-Based Graph Neural Network for Chinese NER
| Title | A Lexicon-Based Graph Neural Network for Chinese NER |
| Authors | Tao Gui, Yicheng Zou, Qi Zhang, Minlong Peng, Jinlan Fu, Zhongyu Wei, Xuanjing Huang |
| Abstract | Recurrent neural networks (RNN) used for Chinese named entity recognition (NER) that sequentially track character and word information have achieved great success. However, the characteristic of chain structure and the lack of global semantics determine that RNN-based models are vulnerable to word ambiguities. In this work, we try to alleviate this problem by introducing a lexicon-based graph neural network with global semantics, in which lexicon knowledge is used to connect characters to capture the local composition, while a global relay node can capture global sentence semantics and long-range dependency. Based on the multiple graph-based interactions among characters, potential words, and the whole-sentence semantics, word ambiguities can be effectively tackled. Experiments on four NER datasets show that the proposed model achieves significant improvements against other baseline models. |
| Tasks | Chinese Named Entity Recognition, Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1096/ |
| https://www.aclweb.org/anthology/D19-1096 | |
| PWC | https://paperswithcode.com/paper/a-lexicon-based-graph-neural-network-for |
| Repo | |
| Framework | |
Sampling Wisely: Deep Image Embedding by Top-K Precision Optimization
| Title | Sampling Wisely: Deep Image Embedding by Top-K Precision Optimization |
| Authors | Jing Lu, Chaofan Xu, Wei Zhang, Ling-Yu Duan, Tao Mei |
| Abstract | Deep image embedding aims at learning a convolutional neural network (CNN) based mapping function that maps an image to a feature vector. The embedding quality is usually evaluated by the performance in image search tasks. Since very few users bother to open the second page search results, top-k precision mostly dominates the user experience and thus is one of the crucial evaluation metrics for the embedding quality. Despite being extensively studied, existing algorithms are usually based on heuristic observation without theoretical guarantee. Consequently, gradient descent direction on the training loss is mostly inconsistent with the direction of optimizing the concerned evaluation metric. This inconsistency certainly misleads the training direction and degrades the performance. In contrast to existing works, in this paper, we propose a novel deep image embedding algorithm with end-to-end optimization to top-k precision, the evaluation metric that is closely related to user experience. Specially, our loss function is constructed with wisely selected “misplaced” images along the top k nearest neighbor decision boundary, so that the gradient descent update directly promotes the concerned metric, top-k precision. Further more, our theoretical analysis on the upper bounding and consistency properties of the proposed loss supports that minimizing our proposed loss is equivalent to maximizing top-k precision. Experiments show that our proposed algorithm outperforms all compared state-of-the-art deep image embedding algorithms on three benchmark datasets. |
| Tasks | Image Retrieval |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Lu_Sampling_Wisely_Deep_Image_Embedding_by_Top-K_Precision_Optimization_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Lu_Sampling_Wisely_Deep_Image_Embedding_by_Top-K_Precision_Optimization_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sampling-wisely-deep-image-embedding-by-top-k |
| Repo | |
| Framework | |
Deep Natural Language Understanding of News Text
| Title | Deep Natural Language Understanding of News Text |
| Authors | Jaya Shree, Emily Liu, Andrew Gordon, Jerry Hobbs |
| Abstract | Early proposals for the deep understanding of natural language text advocated an approach of {``}interpretation as abduction,{''} where the meaning of a text was derived as an explanation that logically entailed the input words, given a knowledge base of lexical and commonsense axioms. While most subsequent NLP research has instead pursued statistical and data-driven methods, the approach of interpretation as abduction has seen steady advancements in both theory and software implementations. In this paper, we summarize advances in deriving the logical form of the text, encoding commonsense knowledge, and technologies for scalable abductive reasoning. We then explore the application of these advancements to the deep understanding of a paragraph of news text, where the subtle meaning of words and phrases are resolved by backward chaining on a knowledge base of 80 hand-authored axioms. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2403/ |
| https://www.aclweb.org/anthology/W19-2403 | |
| PWC | https://paperswithcode.com/paper/deep-natural-language-understanding-of-news |
| Repo | |
| Framework | |
Maximum-Margin Hamming Hashing
| Title | Maximum-Margin Hamming Hashing |
| Authors | Rong Kang, Yue Cao, Mingsheng Long, Jianmin Wang, Philip S. Yu |
| Abstract | Deep hashing enables computation and memory efficient image search through end-to-end learning of feature representations and binary codes. While linear scan over binary hash codes is more efficient than over the high-dimensional representations, its linear-time complexity is still unacceptable for very large databases. Hamming space retrieval enables constant-time search through hash lookups, where for each query, there is a Hamming ball centered at the query and the data points within the ball are returned as relevant. Since inside the Hamming ball implies retrievable while outside irretrievable, it is crucial to explicitly characterize the Hamming ball. The main idea of this work is to directly embody the Hamming radius into the loss functions, leading to Maximum-Margin Hamming Hashing (MMHH), a new model specifically optimized for Hamming space retrieval. We introduce a max-margin t-distribution loss, where the t-distribution concentrates more similar data points to be within the Hamming ball, and the margin characterizes the Hamming radius such that less penalization is applied to similar data points within the Hamming ball. The loss function also introduces robustness to data noise, where the similarity supervision may be inaccurate in practical problems. The model is trained end-to-end using a new semi-batch optimization algorithm tailored to extremely imbalanced data. Our method yields state-of-the-art results on four datasets and shows superior performance on noisy data. |
| Tasks | Image Retrieval |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Kang_Maximum-Margin_Hamming_Hashing_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Kang_Maximum-Margin_Hamming_Hashing_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/maximum-margin-hamming-hashing |
| Repo | |
| Framework | |
Weird Inflects but OK: Making Sense of Morphological Generation Errors
| Title | Weird Inflects but OK: Making Sense of Morphological Generation Errors |
| Authors | Kyle Gorman, Arya D. McCarthy, Ryan Cotterell, Ekaterina Vylomova, Miikka Silfverberg, Magdalena Markowska |
| Abstract | We conduct a manual error analysis of the CoNLL-SIGMORPHON Shared Task on Morphological Reinflection. This task involves natural language generation: systems are given a word in citation form (e.g., hug) and asked to produce the corresponding inflected form (e.g., the simple past hugged). We propose an error taxonomy and use it to annotate errors made by the top two systems across twelve languages. Many of the observed errors are related to inflectional patterns sensitive to inherent linguistic properties such as animacy or affect; many others are failures to predict truly unpredictable inflectional behaviors. We also find nearly one quarter of the residual {``}errors{''} reflect errors in the gold data. | |
| Tasks | Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1014/ |
| https://www.aclweb.org/anthology/K19-1014 | |
| PWC | https://paperswithcode.com/paper/weird-inflects-but-ok-making-sense-of |
| Repo | |
| Framework | |
Deep Learning Framework for Steel Surface Defects Classification
| Title | Deep Learning Framework for Steel Surface Defects Classification |
| Authors | Karun Singla1, Gangesh Chawla2, Ranganath M. Singari3 |
| Abstract | Deep learning has offered new avenues in the field of industrial management. Traditional methods of quality inspection such as Acceptance Sampling relies on a probabilistic measure derived from inspecting a sample of finished products. Evaluating a fixed number of products to derive the quality level for the complete batch is not a robust approach. Visual inspection solutions based on deep learning can be employed in the large manufacturing units to improve the quality inspection units for steel surface defect detection. This leads to optimization of the human capital due to reduction in manual intervention and turnaround time in the overall supply chain of the industry. Consequently, the sample size in the Acceptance sampling can be increased with minimal effort vis-à-vis an increase in the overall accuracy of the inspection. The learning curve of this work is supported by Convolutional Neural Network which has been used to extract feature representations from grayscale images to classify the inputs into six types of surface defects. The neural network architecture is compiled in Keras framework using Tensor flow backend with state of the art Adam RMS Prop with Nesterov Momentum (NADAM) optimizer. The proposed classification algorithm holds the potential to identify the dominant flaws in the manufacturing system responsible for leaking costs. |
| Tasks | |
| Published | 2019-01-25 |
| URL | http://ijapie.org/Volume4_Issue1.html |
| http://ijapie.org/Volume4_Issue1.html | |
| PWC | https://paperswithcode.com/paper/deep-learning-framework-for-steel-surface |
| Repo | |
| Framework | |
Know Your Graph. State-of-the-Art Knowledge-Based WSD
| Title | Know Your Graph. State-of-the-Art Knowledge-Based WSD |
| Authors | Alex Popov, er, Kiril Simov, Petya Osenova |
| Abstract | This paper introduces several improvements over the current state of the art in knowledge-based word sense disambiguation. Those innovations are the result of modifying and enriching a knowledge base created originally on the basis of WordNet. They reflect several separate but connected strategies: manipulating the shape and the content of the knowledge base, assigning weights over the relations in the knowledge base, and the addition of new relations to it. The main contribution of the paper is to demonstrate that the previously proposed knowledge bases organize linguistic and world knowledge suboptimally for the task of word sense disambiguation. In doing so, the paper also establishes a new state of the art for knowledge-based approaches. Its best models are competitive in the broader context of supervised systems as well. |
| Tasks | Word Sense Disambiguation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1110/ |
| https://www.aclweb.org/anthology/R19-1110 | |
| PWC | https://paperswithcode.com/paper/know-your-graph-state-of-the-art-knowledge |
| Repo | |
| Framework | |
