Paper Group NANR 46
Sentiment Analysis: It’s Complicated!. Statistical shape analysis of simplified neuronal trees. Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning Based Registration. Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences. Convex Elicitation of Continuous Properties. Distributed Learni …
Sentiment Analysis: It’s Complicated!
| Title | Sentiment Analysis: It’s Complicated! |
| Authors | Kian Kenyon-Dean, Eisha Ahmed, Scott Fujimoto, Jeremy Georges-Filteau, Christopher Glasz, Barleen Kaur, Lal, Auguste e, Bh, Shruti eri, Robert Belfer, Nirmal Kanagasabai, Roman Sarrazingendron, Rohit Verma, Derek Ruths |
| Abstract | Sentiment analysis is used as a proxy to measure human emotion, where the objective is to categorize text according to some predefined notion of sentiment. Sentiment analysis datasets are typically constructed with gold-standard sentiment labels, assigned based on the results of manual annotations. When working with such annotations, it is common for dataset constructors to discard {}noisy{''} or {}controversial{''} data where there is significant disagreement on the proper label. In datasets constructed for the purpose of Twitter sentiment analysis (TSA), these controversial examples can compose over 30{%} of the originally annotated data. We argue that the removal of such data is a problematic trend because, when performing real-time sentiment classification of short-text, an automated system cannot know a priori which samples would fall into this category of disputed sentiment. We therefore propose the notion of a {``}complicated{''} class of sentiment to categorize such text, and argue that its inclusion in the short-text sentiment analysis framework will improve the quality of automated sentiment analysis systems as they are implemented in real-world settings. We motivate this argument by building and analyzing a new publicly available TSA dataset of over 7,000 tweets annotated with 5x coverage, named MTSA. Our analysis of classifier performance over our dataset offers insights into sentiment analysis dataset and model design, how current techniques would perform in the real world, and how researchers should handle difficult data. | |
| Tasks | Sentiment Analysis, Twitter Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1171/ |
| https://www.aclweb.org/anthology/N18-1171 | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-itas-complicated |
| Repo | |
| Framework | |
Statistical shape analysis of simplified neuronal trees
| Title | Statistical shape analysis of simplified neuronal trees |
| Authors | Adam Duncan, Eric Klassen, and Anuj Srivastava |
| Abstract | Neuron morphology plays a central role in characterizing cognitive health and functionality of brain structures. The problem of quantifying neuron shapes and capturing statistical variability of shapes is difficult because neurons differ both in geometry and in topology. This paper develops a mathematical representation of neuronal trees, restricting to the trees that consist of: (1) a main branch viewed as a parameterized curve in R 3 R3 , and (2) some number of secondary branches—also parameterized curves in R 3 R3 —which emanate from the main branch at arbitrary points. It imposes a metric on the representation space, in order to compare neuronal shapes, and to obtain optimal deformations (geodesics) across arbitrary trees. The key idea is to impose certain equivalence relations that allow trees with different geometries and topologies to be compared efficiently. The combinatorial problem of matching side branches across trees is reduced to a linear assignment with well-known efficient solutions. This framework is then applied to comparing, clustering, and classifying neurons using fully automated algorithms. The framework is illustrated on three datasets of neuron reconstructions, specifically showing geodesics paths and cross-validated classification between experimental groups. |
| Tasks | |
| Published | 2018-11-03 |
| URL | https://projecteuclid.org/euclid.aoas/1536652959 |
| https://projecteuclid.org/download/pdfview_1/euclid.aoas/1536652959 | |
| PWC | https://paperswithcode.com/paper/statistical-shape-analysis-of-simplified |
| Repo | |
| Framework | |
Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning Based Registration
| Title | Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning Based Registration |
| Authors | Jingfan Fan，Xiaohuan Cao， Zhong Xue, Pew-Thian Yap, and Dinggang Shen |
| Abstract | This paper introduces an unsupervised adversarial similarity network for image registration. Unlike existing deep learning registration frameworks,our approach does not require ground-truth deformations and specific similarity metrics. We connect a registration network and a discrimination network with adeformable transformation layer. The registration network is trained with feedback from the discrimination network, which is designed to judge whether a pair of registered images are sufficiently similar. Using adversarial training, the registration network is trained to predict deformations that are accurate enough to fool the discrimination network. Experiments on four brain MRI datasets indicate that our method yields registration performance that is promising in both accuracy and efficiency compared with state-of-the-art registration methods, including those based on deep learning. |
| Tasks | Image Registration |
| Published | 2018-09-10 |
| URL | https://www.researchgate.net/publication/327628479_Adversarial_Similarity_Network_for_Evaluating_Image_Alignment_in_Deep_Learning_Based_Registration |
| https://www.researchgate.net/publication/327628479_Adversarial_Similarity_Network_for_Evaluating_Image_Alignment_in_Deep_Learning_Based_Registration | |
| PWC | https://paperswithcode.com/paper/adversarial-similarity-network-for-evaluating |
| Repo | |
| Framework | |
Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences
| Title | Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences |
| Authors | Athul Paul Jacob, Zhouhan Lin, Aless Sordoni, ro, Yoshua Bengio |
| Abstract | We propose a hierarchical model for sequential data that learns a tree on-the-fly, i.e. while reading the sequence. In the model, a recurrent network adapts its structure and reuses recurrent weights in a recursive manner. This creates adaptive skip-connections that ease the learning of long-term dependencies. The tree structure can either be inferred without supervision through reinforcement learning, or learned in a supervised manner. We provide preliminary experiments in a novel Math Expression Evaluation (MEE) task, which is created to have a hierarchical tree structure that can be used to study the effectiveness of our model. Additionally, we test our model in a well-known propositional logic and language modelling tasks. Experimental results have shown the potential of our approach. |
| Tasks | Language Modelling, Representation Learning |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3020/ |
| https://www.aclweb.org/anthology/W18-3020 | |
| PWC | https://paperswithcode.com/paper/learning-hierarchical-structures-on-the-fly |
| Repo | |
| Framework | |
Convex Elicitation of Continuous Properties
| Title | Convex Elicitation of Continuous Properties |
| Authors | Jessica Finocchiaro, Rafael Frongillo |
| Abstract | A property or statistic of a distribution is said to be elicitable if it can be expressed as the minimizer of some loss function in expectation. Recent work shows that continuous real-valued properties are elicitable if and only if they are identifiable, meaning the set of distributions with the same property value can be described by linear constraints. From a practical standpoint, one may ask for which such properties do there exist convex loss functions. In this paper, in a finite-outcome setting, we show that in fact every elicitable real-valued property can be elicited by a convex loss function. Our proof is constructive, and leads to convex loss functions for new properties. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8241-convex-elicitation-of-continuous-properties |
| http://papers.nips.cc/paper/8241-convex-elicitation-of-continuous-properties.pdf | |
| PWC | https://paperswithcode.com/paper/convex-elicitation-of-continuous-properties |
| Repo | |
| Framework | |
Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization
| Title | Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization |
| Authors | Bargav Jayaraman, Lingxiao Wang, David Evans, Quanquan Gu |
| Abstract | Distributed learning allows a group of independent data owners to collaboratively learn a model over their data sets without exposing their private data. We present a distributed learning approach that combines differential privacy with secure multi-party computation. We explore two popular methods of differential privacy, output perturbation and gradient perturbation, and advance the state-of-the-art for both methods in the distributed learning setting. In our output perturbation method, the parties combine local models within a secure computation and then add the required differential privacy noise before revealing the model. In our gradient perturbation method, the data owners collaboratively train a global model via an iterative learning algorithm. At each iteration, the parties aggregate their local gradients within a secure computation, adding sufficient noise to ensure privacy before the gradient updates are revealed. For both methods, we show that the noise can be reduced in the multi-party setting by adding the noise inside the secure computation after aggregation, asymptotically improving upon the best previous results. Experiments on real world data sets demonstrate that our methods provide substantial utility gains for typical privacy requirements. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7871-distributed-learning-without-distress-privacy-preserving-empirical-risk-minimization |
| http://papers.nips.cc/paper/7871-distributed-learning-without-distress-privacy-preserving-empirical-risk-minimization.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-learning-without-distress-privacy |
| Repo | |
| Framework | |
Summarizing First-Person Videos from Third Persons’ Points of View
| Title | Summarizing First-Person Videos from Third Persons’ Points of View |
| Authors | HSUAN-I HO, Wei-Chen Chiu, Yu-Chiang Frank Wang |
| Abstract | Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage. However, most existing studies rely on training data of third-person videos, which cannot easily generalize to highlight the first-person ones. With the goal of deriving an effective model to summarize first-person videos, we propose a novel deep neural network architecture for describing and discriminating vital spatiotemporal information across videos with different points of view. Our proposed model is realized in a semi-supervised setting, in which fully annotated third-person videos, unlabeled first-person videos, and a small amount of annotated first-person ones are presented during training. In our experiments, qualitative and quantitative evaluations on both benchmarks and our collected first-person video datasets are presented. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/HSUAN-I_HO_Summarizing_First-Person_Videos_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/HSUAN-I_HO_Summarizing_First-Person_Videos_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/summarizing-first-person-videos-from-third-1 |
| Repo | |
| Framework | |
Proceedings of the 27th International Conference on Computational Linguistics
| Title | Proceedings of the 27th International Conference on Computational Linguistics |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1000/ |
| https://www.aclweb.org/anthology/C18-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-27th-international-1 |
| Repo | |
| Framework | |
Global Convergence of Policy Gradient Methods for Linearized Control Problems
| Title | Global Convergence of Policy Gradient Methods for Linearized Control Problems |
| Authors | Maryam Fazel, Rong Ge, Sham M. Kakade, Mehran Mesbahi |
| Abstract | Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model; 2) they are an “end-to-end” approach, directly optimizing the performance metric of interest; 3) they inherently allow for richly parameterized policies. A notable drawback is that even in the most basic continuous control problem (that of linear quadratic regulators), these methods must solve a non-convex optimization problem, where little is understood about their efficiency from both computational and statistical perspectives. In contrast, system identification and model based planning in optimal control theory have a much more solid theoretical footing, where much is known with regards to their computational and statistical properties. This work bridges this gap showing that (model free) policy gradient methods globally converge to the optimal solution and are efficient (polynomially so in relevant problem dependent quantities) with regards to their sample and computational complexities. |
| Tasks | Continuous Control, Policy Gradient Methods |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BJDEbngCZ |
| https://openreview.net/pdf?id=BJDEbngCZ | |
| PWC | https://paperswithcode.com/paper/global-convergence-of-policy-gradient-methods-1 |
| Repo | |
| Framework | |
Generalization of Learning using Reservoir Computing
| Title | Generalization of Learning using Reservoir Computing |
| Authors | Sanjukta Krishnagopal, Yiannis Aloimonos, Michelle Girvan |
| Abstract | We investigate the methods by which a Reservoir Computing Network (RCN) learns concepts such as ‘similar’ and ‘different’ between pairs of images using a small training dataset and generalizes these concepts to previously unseen types of data. Specifically, we show that an RCN trained to identify relationships between image-pairs drawn from a subset of digits from the MNIST database or the depth maps of subset of visual scenes from a moving camera generalizes the learned transformations to images of digits unseen during training or depth maps of different visual scenes. We infer, using Principal Component Analysis, that the high dimensional reservoir states generated from an input image pair with a specific transformation converge over time to a unique relationship. Thus, as opposed to training the entire high dimensional reservoir state, the reservoir only needs to train on these unique relationships, allowing the reservoir to perform well with very few training examples. Thus, generalization of learning to unseen images is interpretable in terms of clustering of the reservoir state onto the attractor corresponding to the transformation in reservoir space. We find that RCNs can identify and generalize linear and non-linear transformations, and combinations of transformations, naturally and be a robust and effective image classifier. Additionally, RCNs perform significantly better than state of the art neural network classification techniques such as deep Siamese Neural Networks (SNNs) in generalization tasks both on the MNIST dataset and more complex depth maps of visual scenes from a moving camera. This work helps bridge the gap between explainable machine learning and biological learning through analogies using small datasets, and points to new directions in the investigation of learning processes. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HyFaiGbCW |
| https://openreview.net/pdf?id=HyFaiGbCW | |
| PWC | https://paperswithcode.com/paper/generalization-of-learning-using-reservoir |
| Repo | |
| Framework | |
EmoIntens Tracker at SemEval-2018 Task 1: Emotional Intensity Levels in #Tweets
| Title | EmoIntens Tracker at SemEval-2018 Task 1: Emotional Intensity Levels in #Tweets |
| Authors | Ramona-Andreea Turcu, Amar, S ei, ra Maria, Iuliana-Alex Flescan-Lovin-Arseni, ra, Daniela Gifu, Tr, Diana abat |
| Abstract | The „Affect in Tweets{''} task is centered on emotions categorization and evaluation matrix using multi-language tweets (English and Spanish). In this research, SemEval Affect dataset was preprocessed, categorized, and evaluated accordingly (precision, recall, and accuracy). The system described in this paper is based on the implementation of supervised machine learning (Naive Bayes, KNN and SVM), deep learning (NN Tensor Flow model), and decision trees algorithms. |
| Tasks | Emotion Recognition, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1026/ |
| https://www.aclweb.org/anthology/S18-1026 | |
| PWC | https://paperswithcode.com/paper/emointens-tracker-at-semeval-2018-task-1 |
| Repo | |
| Framework | |
A Sequence Learning Method for Domain-Specific Entity Linking
| Title | A Sequence Learning Method for Domain-Specific Entity Linking |
| Authors | Emrah Inan, Oguz Dikenelli |
| Abstract | Recent collective Entity Linking studies usually promote global coherence of all the mapped entities in the same document by using semantic embeddings and graph-based approaches. Although graph-based approaches are shown to achieve remarkable results, they are computationally expensive for general datasets. Also, semantic embeddings only indicate relatedness between entity pairs without considering sequences. In this paper, we address these problems by introducing a two-fold neural model. First, we match easy mention-entity pairs and using the domain information of this pair to filter candidate entities of closer mentions. Second, we resolve more ambiguous pairs using bidirectional Long Short-Term Memory and CRF models for the entity disambiguation. Our proposed system outperforms state-of-the-art systems on the generated domain-specific evaluation dataset. |
| Tasks | Entity Disambiguation, Entity Linking, Knowledge Graph Completion, Link Prediction, Relation Extraction, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2403/ |
| https://www.aclweb.org/anthology/W18-2403 | |
| PWC | https://paperswithcode.com/paper/a-sequence-learning-method-for-domain |
| Repo | |
| Framework | |
Benchmarks and models for entity-oriented polarity detection
| Title | Benchmarks and models for entity-oriented polarity detection |
| Authors | Lidia Pivovarova, Arto Klami, Roman Yangarber |
| Abstract | We address the problem of determining entity-oriented polarity in business news. This can be viewed as classifying the polarity of the sentiment expressed toward a given mention of a company in a news article. We present a complete, end-to-end approach to the problem. We introduce a new dataset of over 17,000 manually labeled documents, which is substantially larger than any currently available resources. We propose a benchmark solution based on convolutional neural networks for classifying entity-oriented polarity. Although our dataset is much larger than those currently available, it is small on the scale of datasets commonly used for training robust neural network models. To compensate for this, we use transfer learning{—}pre-train the model on a much larger dataset, annotated for a related but different classification task, in order to learn a good representation for business text, and then fine-tune it on the smaller polarity dataset. |
| Tasks | Sentiment Analysis, Transfer Learning |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-3016/ |
| https://www.aclweb.org/anthology/N18-3016 | |
| PWC | https://paperswithcode.com/paper/benchmarks-and-models-for-entity-oriented |
| Repo | |
| Framework | |
Yuan at SemEval-2018 Task 1: Tweets Emotion Intensity Prediction using Ensemble Recurrent Neural Network
| Title | Yuan at SemEval-2018 Task 1: Tweets Emotion Intensity Prediction using Ensemble Recurrent Neural Network |
| Authors | Min Wang, Xiaobing Zhou |
| Abstract | We perform the LSTM and BiLSTM model for the emotion intensity prediction. We only join the third subtask in Task 1:Affect in Tweets. Our system rank 6th among all the teams. |
| Tasks | Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1031/ |
| https://www.aclweb.org/anthology/S18-1031 | |
| PWC | https://paperswithcode.com/paper/yuan-at-semeval-2018-task-1-tweets-emotion |
| Repo | |
| Framework | |
Large Batch Training of Convolutional Networks with Layer-wise Adaptive Rate Scaling
| Title | Large Batch Training of Convolutional Networks with Layer-wise Adaptive Rate Scaling |
| Authors | Boris Ginsburg, Igor Gitman, Yang You |
| Abstract | A common way to speed up training of large convolutional networks is to add computational units. Training is then performed using data-parallel synchronous Stochastic Gradient Descent (SGD) with a mini-batch divided between computational units. With an increase in the number of nodes, the batch size grows. However, training with a large batch often results in lower model accuracy. We argue that the current recipe for large batch training (linear learning rate scaling with warm-up) is not general enough and training may diverge. To overcome these optimization difficulties, we propose a new training algorithm based on Layer-wise Adaptive Rate Scaling (LARS). Using LARS, we scaled AlexNet and ResNet-50 to a batch size of 16K. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rJ4uaX2aW |
| https://openreview.net/pdf?id=rJ4uaX2aW | |
| PWC | https://paperswithcode.com/paper/large-batch-training-of-convolutional-1 |
| Repo | |
| Framework | |
