Paper Group NANR 189
Neural Feature Extraction for Contextual Emotion Detection. Set to Ordered Text: Generating Discharge Instructions from Medical Billing Codes. Identifying Patients with Pain in Emergency Departments using Conventional Machine Learning and Deep Learning. Deep Denoising: Rate-Optimal Recovery of Structured Signals with a Deep Prior. Proceedings of th …
Neural Feature Extraction for Contextual Emotion Detection
| Title | Neural Feature Extraction for Contextual Emotion Detection |
| Authors | Elham Mohammadi, Hessam Amini, Leila Kosseim |
| Abstract | This paper describes a new approach for the task of contextual emotion detection. The approach is based on a neural feature extractor, composed of a recurrent neural network with an attention mechanism, followed by a classifier, that can be neural or SVM-based. We evaluated the model with the dataset of the task 3 of SemEval 2019 (EmoContext), which includes short 3-turn conversations, tagged with 4 emotion classes. The best performing setup was achieved using ELMo word embeddings and POS tags as input, bidirectional GRU as hidden units, and an SVM as the final classifier. This configuration reached 69.93{%} in terms of micro-average F1 score on the main 3 emotion classes, a score that outperformed the baseline system by 11.25{%}. |
| Tasks | Word Embeddings |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1091/ |
| https://www.aclweb.org/anthology/R19-1091 | |
| PWC | https://paperswithcode.com/paper/neural-feature-extraction-for-contextual |
| Repo | |
| Framework | |
Set to Ordered Text: Generating Discharge Instructions from Medical Billing Codes
| Title | Set to Ordered Text: Generating Discharge Instructions from Medical Billing Codes |
| Authors | Litton J Kurisinkel, Nancy Chen |
| Abstract | We present set to ordered text, a natural language generation task applied to automatically generating discharge instructions from admission ICD (International Classification of Diseases) codes. This task differs from other natural language generation tasks in the following ways: (1) The input is a set of identifiable entities (ICD codes) where the relations between individual entity are not explicitly specified. (2) The output text is not a narrative description (e.g. news articles) composed from the input. Rather, inferences are made from the input (symptoms specified in ICD codes) to generate the output (instructions). (3) There is an optimal order in which each sentence (instruction) should appear in the output. Unlike most other tasks, neither the input (ICD codes) nor their corresponding symptoms appear in the output, so the ordering of the output instructions needs to be learned in an unsupervised fashion. Based on clinical intuition, we hypothesize that each instruction in the output is mapped to a subset of ICD codes specified in the input. We propose a neural architecture that jointly models (a) subset selection: choosing relevant subsets from a set of input entities; (b) content ordering: learning the order of instructions; and (c) text generation: representing the instructions corresponding to the selected subsets in natural language. In addition, we penalize redundancy during beam search to improve tractability for long text generation. Our model outperforms baseline models in BLEU scores and human evaluation. We plan to extend this work to other tasks such as recipe generation from ingredients. |
| Tasks | Recipe Generation, Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1638/ |
| https://www.aclweb.org/anthology/D19-1638 | |
| PWC | https://paperswithcode.com/paper/set-to-ordered-text-generating-discharge |
| Repo | |
| Framework | |
Identifying Patients with Pain in Emergency Departments using Conventional Machine Learning and Deep Learning
| Title | Identifying Patients with Pain in Emergency Departments using Conventional Machine Learning and Deep Learning |
| Authors | Thanh Vu, Anthony Nguyen, Nathan Brown, James Hughes |
| Abstract | Pain is the main symptom that patients present with to the emergency department (ED). Pain management, however, is often poorly done aspect of emergency care and patients with painful conditions can endure long waits before their pain is assessed or treated. To improve pain management quality, identifying whether or not an ED patient presents with pain is an important task and allows for further investigation of the quality of care provided. In this paper, machine learning was utilised to handle the task of automatically detecting patients who present at EDs with pain from retrospective data. Experimental results on a manually annotated dataset show that our proposed machine learning models achieve high performances, in which the highest accuracy and macro-averaged F1 are 91.00{%} and 90.96{%}, respectively. |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1015/ |
| https://www.aclweb.org/anthology/U19-1015 | |
| PWC | https://paperswithcode.com/paper/identifying-patients-with-pain-in-emergency |
| Repo | |
| Framework | |
Deep Denoising: Rate-Optimal Recovery of Structured Signals with a Deep Prior
| Title | Deep Denoising: Rate-Optimal Recovery of Structured Signals with a Deep Prior |
| Authors | Reinhard Heckel, Wen Huang, Paul Hand, Vladislav Voroninski |
| Abstract | Deep neural networks provide state-of-the-art performance for image denoising, where the goal is to recover a near noise-free image from a noisy image. The underlying principle is that neural networks trained on large datasets have empirically been shown to be able to generate natural images well from a low-dimensional latent representation of the image. Given such a generator network, or prior, a noisy image can be denoised by finding the closest image in the range of the prior. However, there is little theory to justify this success, let alone to predict the denoising performance as a function of the networks parameters. In this paper we consider the problem of denoising an image from additive Gaussian noise, assuming the image is well described by a deep neural network with ReLu activations functions, mapping a k-dimensional latent space to an n-dimensional image. We state and analyze a simple gradient-descent-like iterative algorithm that minimizes a non-convex loss function, and provably removes a fraction of (1 - O(k/n)) of the noise energy. We also demonstrate in numerical experiments that this denoising performance is, indeed, achieved by generative priors learned from data. |
| Tasks | Denoising, Image Denoising |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SklcFsAcKX |
| https://openreview.net/pdf?id=SklcFsAcKX | |
| PWC | https://paperswithcode.com/paper/deep-denoising-rate-optimal-recovery-of-1 |
| Repo | |
| Framework | |
Proceedings of the 13th International Workshop on Semantic Evaluation
| Title | Proceedings of the 13th International Workshop on Semantic Evaluation |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2000/ |
| https://www.aclweb.org/anthology/S19-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-13th-international-3 |
| Repo | |
| Framework | |
Fast Sparse Group Lasso
| Title | Fast Sparse Group Lasso |
| Authors | Yasutoshi Ida, Yasuhiro Fujiwara, Hisashi Kashima |
| Abstract | Sparse Group Lasso is a method of linear regression analysis that finds sparse parameters in terms of both feature groups and individual features. Block Coordinate Descent is a standard approach to obtain the parameters of Sparse Group Lasso, and iteratively updates the parameters for each parameter group. However, as an update of only one parameter group depends on all the parameter groups or data points, the computation cost is high when the number of the parameters or data points is large. This paper proposes a fast Block Coordinate Descent for Sparse Group Lasso. It efficiently skips the updates of the groups whose parameters must be zeros by using the parameters in one group. In addition, it preferentially updates parameters in a candidate group set, which contains groups whose parameters must not be zeros. Theoretically, our approach guarantees the same results as the original Block Coordinate Descent. Experiments show that our algorithm enhances the efficiency of the original algorithm without any loss of accuracy. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8447-fast-sparse-group-lasso |
| http://papers.nips.cc/paper/8447-fast-sparse-group-lasso.pdf | |
| PWC | https://paperswithcode.com/paper/fast-sparse-group-lasso |
| Repo | |
| Framework | |
Unsupervised classification into unknown number of classes
| Title | Unsupervised classification into unknown number of classes |
| Authors | Sungyeob Han, Daeyoung Kim, Jungwoo Lee |
| Abstract | We propose a novel unsupervised classification method based on graph Laplacian. Unlike the widely used classification method, this architecture does not require the labels of data and the number of classes. Our key idea is to introduce a approximate linear map and a spectral clustering theory on the dimension reduced spaces into generative adversarial networks. Inspired by the human visual recognition system, the proposed framework can classify and also generate images as the human brains do. We build an approximate linear connector network $C$ analogous to the cerebral cortex, between the discriminator $D$ and the generator $G$. The connector network allows us to estimate the unknown number of classes. Estimating the number of classes is one of the challenging researches in the unsupervised learning, especially in spectral clustering. The proposed method can also classify the images by using the estimated number of classes. Therefore, we define our method as an unsupervised classification method. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=S1gUVjCqKm |
| https://openreview.net/pdf?id=S1gUVjCqKm | |
| PWC | https://paperswithcode.com/paper/unsupervised-classification-into-unknown |
| Repo | |
| Framework | |
Co-Occurrence Neural Network
| Title | Co-Occurrence Neural Network |
| Authors | Irina Shevlev, Shai Avidan |
| Abstract | Convolutional Neural Networks (CNNs) became a very popular tool for image analysis. Convolutions are fast to compute and easy to store, but they also have some limitations. First, they are shift-invariant and, as a result, they do not adapt to different regions of the image. Second, they have a fixed spatial layout, so small geometric deformations in the layout of a patch will completely change the filter response. For these reasons, we need multiple filters to handle the different parts and variations in the input. We augment the standard convolutional tools used in CNNs with a new filter that addresses both issues raised above. Our filter combines two terms, a spatial filter and a term that is based on the co-occurrence statistics of input values in the neighborhood. The proposed filter is differentiable and can therefore be packaged as a layer in CNN and trained using back-propagation. We show how to train the filter as part of the network and report results on several data sets. In particular, we replace a convolutional layer with hundreds of thousands of parameters with a Co-occurrence Layer consisting of only a few hundred parameters with minimal impact on accuracy. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Shevlev_Co-Occurrence_Neural_Network_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Shevlev_Co-Occurrence_Neural_Network_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/co-occurrence-neural-network |
| Repo | |
| Framework | |
Dataset Creation for Ranking Constructive News Comments
| Title | Dataset Creation for Ranking Constructive News Comments |
| Authors | Soichiro Fujita, Hayato Kobayashi, Manabu Okumura |
| Abstract | Ranking comments on an online news service is a practically important task for the service provider, and thus there have been many studies on this task. However, most of them considered users{'} positive feedback, such as {}Like{''}-button clicks, as a quality measure. In this paper, we address directly evaluating the quality of comments on the basis of {}constructiveness,{''} separately from user feedback. To this end, we create a new dataset including 100K+ Japanese comments with constructiveness scores (C-scores). Our experiments clarify that C-scores are not always related to users{'} positive feedback, and the performance of pairwise ranking models tends to be enhanced by the variation of comments rather than articles. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1250/ |
| https://www.aclweb.org/anthology/P19-1250 | |
| PWC | https://paperswithcode.com/paper/dataset-creation-for-ranking-constructive |
| Repo | |
| Framework | |
Robust Principal Component Analysis with Adaptive Neighbors
| Title | Robust Principal Component Analysis with Adaptive Neighbors |
| Authors | Rui Zhang, Hanghang Tong |
| Abstract | Suppose certain data points are overly contaminated, then the existing principal component analysis (PCA) methods are frequently incapable of filtering out and eliminating the excessively polluted ones, which potentially lead to the functional degeneration of the corresponding models. To tackle the issue, we propose a general framework namely robust weight learning with adaptive neighbors (RWL-AN), via which adaptive weight vector is automatically obtained with both robustness and sparse neighbors. More significantly, the degree of the sparsity is steerable such that only exact k well-fitting samples with least reconstruction errors are activated during the optimization, while the residual samples, i.e., the extreme noised ones are eliminated for the global robustness. Additionally, the framework is further applied to PCA problem to demonstrate the superiority and effectiveness of the proposed RWL-AN model. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8919-robust-principal-component-analysis-with-adaptive-neighbors |
| http://papers.nips.cc/paper/8919-robust-principal-component-analysis-with-adaptive-neighbors.pdf | |
| PWC | https://paperswithcode.com/paper/robust-principal-component-analysis-with |
| Repo | |
| Framework | |
Finding Generalizable Evidence by Learning to Convince Q&A Models
| Title | Finding Generalizable Evidence by Learning to Convince Q&A Models |
| Authors | Ethan Perez, Siddharth Karamcheti, Rob Fergus, Jason Weston, Douwe Kiela, Kyunghyun Cho |
| Abstract | We propose a system that finds the strongest supporting evidence for a given answer to a question, using passage-based question-answering (QA) as a testbed. We train evidence agents to select the passage sentences that most convince a pretrained QA model of a given answer, if the QA model received those sentences instead of the full passage. Rather than finding evidence that convinces one model alone, we find that agents select evidence that generalizes; agent-chosen evidence increases the plausibility of the supported answer, as judged by other QA models and humans. Given its general nature, this approach improves QA in a robust manner: using agent-selected evidence (i) humans can correctly answer questions with only {\textasciitilde}20{%} of the full passage and (ii) QA models can generalize to longer passages and harder questions. |
| Tasks | Question Answering |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1244/ |
| https://www.aclweb.org/anthology/D19-1244 | |
| PWC | https://paperswithcode.com/paper/finding-generalizable-evidence-by-learning-to-1 |
| Repo | |
| Framework | |
Narrative Generation in the Wild: Methods from NaNoGenMo
| Title | Narrative Generation in the Wild: Methods from NaNoGenMo |
| Authors | Judith van Stegeren, Mari{"e}t Theune |
| Abstract | In text generation, generating long stories is still a challenge. Coherence tends to decrease rapidly as the output length increases. Especially for generated stories, coherence of the narrative is an important quality aspect of the output text. In this paper we examine how narrative coherence is attained in the submissions of NaNoGenMo 2018, an online text generation event where participants are challenged to generate a 50,000 word novel. We list the main approaches that were used to generate coherent narratives and link them to scientific literature. Finally, we give recommendations on when to use which approach. |
| Tasks | Text Generation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3407/ |
| https://www.aclweb.org/anthology/W19-3407 | |
| PWC | https://paperswithcode.com/paper/narrative-generation-in-the-wild-methods-from |
| Repo | |
| Framework | |
Exploring Sequence-to-Sequence Learning in Aspect Term Extraction
| Title | Exploring Sequence-to-Sequence Learning in Aspect Term Extraction |
| Authors | Dehong Ma, Sujian Li, Fangzhao Wu, Xing Xie, Houfeng Wang |
| Abstract | Aspect term extraction (ATE) aims at identifying all aspect terms in a sentence and is usually modeled as a sequence labeling problem. However, sequence labeling based methods cannot make full use of the overall meaning of the whole sentence and have the limitation in processing dependencies between labels. To tackle these problems, we first explore to formalize ATE as a sequence-to-sequence (Seq2Seq) learning task where the source sequence and target sequence are composed of words and labels respectively. At the same time, to make Seq2Seq learning suit to ATE where labels correspond to words one by one, we design the gated unit networks to incorporate corresponding word representation into the decoder, and position-aware attention to pay more attention to the adjacent words of a target word. The experimental results on two datasets show that Seq2Seq learning is effective in ATE accompanied with our proposed gated unit networks and position-aware attention mechanism. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1344/ |
| https://www.aclweb.org/anthology/P19-1344 | |
| PWC | https://paperswithcode.com/paper/exploring-sequence-to-sequence-learning-in |
| Repo | |
| Framework | |
Learning Localized Generative Models for 3D Point Clouds via Graph Convolution
| Title | Learning Localized Generative Models for 3D Point Clouds via Graph Convolution |
| Authors | Diego Valsesia, Giulia Fracastoro, Enrico Magli |
| Abstract | Point clouds are an important type of geometric data and have widespread use in computer graphics and vision. However, learning representations for point clouds is particularly challenging due to their nature as being an unordered collection of points irregularly distributed in 3D space. Graph convolution, a generalization of the convolution operation for data defined over graphs, has been recently shown to be very successful at extracting localized features from point clouds in supervised or semi-supervised tasks such as classification or segmentation. This paper studies the unsupervised problem of a generative model exploiting graph convolution. We focus on the generator of a GAN and define methods for graph convolution when the graph is not known in advance as it is the very output of the generator. The proposed architecture learns to generate localized features that approximate graph embeddings of the output geometry. We also study the problem of defining an upsampling layer in the graph-convolutional generator, such that it learns to exploit a self-similarity prior on the data distribution to sample more effectively. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJeXSo09FQ |
| https://openreview.net/pdf?id=SJeXSo09FQ | |
| PWC | https://paperswithcode.com/paper/learning-localized-generative-models-for-3d |
| Repo | |
| Framework | |
Does Learning Specific Features for Related Parts Help Human Pose Estimation?
| Title | Does Learning Specific Features for Related Parts Help Human Pose Estimation? |
| Authors | Wei Tang, Ying Wu |
| Abstract | Human pose estimation (HPE) is inherently a homogeneous multi-task learning problem, with the localization of each body part as a different task. Recent HPE approaches universally learn a shared representation for all parts, from which their locations are linearly regressed. However, our statistical analysis indicates not all parts are related to each other. As a result, such a sharing mechanism can lead to negative transfer and deteriorate the performance. This potential issue drives us to raise an interesting question. Can we identify related parts and learn specific features for them to improve pose estimation? Since unrelated tasks no longer share a high-level representation, we expect to avoid the adverse effect of negative transfer. In addition, more explicit structural knowledge, e.g., ankles and knees are highly related, is incorporated into the model, which helps resolve ambiguities in HPE. To answer this question, we first propose a data-driven approach to group related parts based on how much information they share. Then a part-based branching network (PBN) is introduced to learn representations specific to each part group. We further present a multi-stage version of this network to repeatedly refine intermediate features and pose estimates. Ablation experiments indicate learning specific features significantly improves the localization of occluded parts and thus benefits HPE. Our approach also outperforms all state-of-the-art methods on two benchmark datasets, with an outstanding advantage when occlusion occurs. |
| Tasks | Multi-Task Learning, Pose Estimation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Tang_Does_Learning_Specific_Features_for_Related_Parts_Help_Human_Pose_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Tang_Does_Learning_Specific_Features_for_Related_Parts_Help_Human_Pose_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/does-learning-specific-features-for-related |
| Repo | |
| Framework | |
