Paper Group ANR 1020
Inferring Which Medical Treatments Work from Reports of Clinical Trials. Using AI/ML to gain situational understanding from passive networkobservations. Deep Learning based Precoding for the MIMO Gaussian Wiretap Channel. iSarcasm: A Dataset of Intended Sarcasm. Deep Bidirectional Transformers for Relation Extraction without Supervision. Detection …
Inferring Which Medical Treatments Work from Reports of Clinical Trials
| Title | Inferring Which Medical Treatments Work from Reports of Clinical Trials |
| Authors | Eric Lehman, Jay DeYoung, Regina Barzilay, Byron C. Wallace |
| Abstract | How do we know if a particular medical treatment actually works? Ideally one would consult all available evidence from relevant clinical trials. Unfortunately, such results are primarily disseminated in natural language scientific articles, imposing substantial burden on those trying to make sense of them. In this paper, we present a new task and corpus for making this unstructured evidence actionable. The task entails inferring reported findings from a full-text article describing a randomized controlled trial (RCT) with respect to a given intervention, comparator, and outcome of interest, e.g., inferring if an article provides evidence supporting the use of aspirin to reduce risk of stroke, as compared to placebo. We present a new corpus for this task comprising 10,000+ prompts coupled with full-text articles describing RCTs. Results using a suite of models — ranging from heuristic (rule-based) approaches to attentive neural architectures — demonstrate the difficulty of the task, which we believe largely owes to the lengthy, technical input texts. To facilitate further work on this important, challenging problem we make the corpus, documentation, a website and leaderboard, and code for baselines and evaluation available at http://evidence-inference.ebm-nlp.com/. |
| Tasks | |
| Published | 2019-04-02 |
| URL | http://arxiv.org/abs/1904.01606v2 |
| http://arxiv.org/pdf/1904.01606v2.pdf | |
| PWC | https://paperswithcode.com/paper/inferring-which-medical-treatments-work-from |
| Repo | |
| Framework | |
Using AI/ML to gain situational understanding from passive networkobservations
| Title | Using AI/ML to gain situational understanding from passive networkobservations |
| Authors | D. Verma, S. Calo |
| Abstract | The data available in the network traffic fromany Government building contains a significant amount ofinformation. An analysis of the traffic can yield insightsand situational understanding about what is happening inthe building. However, the use of traditional network packet inspection, either deep or shallow, is useful for only a limited understanding of the environment, with applicability limited to some aspects of network and security management. If weuse AI/ML based techniques to understand the network traffic, we can gain significant insights which increase our situational awareness of what is happening in the environment.At IBM, we have created a system which uses a combination of network domain knowledge and machine learning techniques to convert network traffic into actionable insights about the on premise environment. These insights include characterization of the communicating devices, discovering unauthorized devices that may violate policy requirements, identifying hidden components and vulnerability points, detecting leakage of sensitive information, and identifying the presence of people and devices.In this paper, we will describe the overall design of this system, the major use-cases that have been identified for it, and the lessons learnt when deploying this system for some of those use-cases |
| Tasks | |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06266v1 |
| https://arxiv.org/pdf/1910.06266v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-aiml-to-gain-situational-understanding |
| Repo | |
| Framework | |
Deep Learning based Precoding for the MIMO Gaussian Wiretap Channel
| Title | Deep Learning based Precoding for the MIMO Gaussian Wiretap Channel |
| Authors | Xinliang Zhang, Mojtaba Vaezi |
| Abstract | A novel precoding method based on supervised deep neural networks is introduced for the multiple-input multiple-output Gaussian wiretap channel. The proposed deep learning (DL)-based precoding learns the input covariance matrix through offline training over a large set of input channels and their corresponding covariance matrices for efficient, reliable, and secure transmission of information. Furthermore, by spending time in offline training, this method remarkably reduces the computation complexity in real-time applications. Compared to traditional precoding methods, the proposed DL-based precoding is significantly faster and reaches near-capacity secrecy rates. DL-based precoding is also more robust than transitional precoding approaches to the number of antennas at the eavesdropper. This new approach to precoding is promising in applications in which delay and complexity are critical. |
| Tasks | |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07963v1 |
| https://arxiv.org/pdf/1909.07963v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-precoding-for-the-mimo |
| Repo | |
| Framework | |
iSarcasm: A Dataset of Intended Sarcasm
| Title | iSarcasm: A Dataset of Intended Sarcasm |
| Authors | Silviu Oprea, Walid Magdy |
| Abstract | This paper considers the distinction between intended and perceived sarcasm in the context of textual sarcasm detection. The former occurs when an utterance is sarcastic from the perspective of its author, while the latter occurs when the utterance is interpreted as sarcastic by the audience. We show the limitations of previous labelling methods in capturing intended sarcasm and introduce the iSarcasm dataset of tweets labeled for sarcasm directly by their authors. We experiment with sarcasm detection models on our dataset. The low performance indicates that sarcasm might be a phenomenon under-studied computationally thus far. |
| Tasks | Sarcasm Detection |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03123v1 |
| https://arxiv.org/pdf/1911.03123v1.pdf | |
| PWC | https://paperswithcode.com/paper/isarcasm-a-dataset-of-intended-sarcasm |
| Repo | |
| Framework | |
Deep Bidirectional Transformers for Relation Extraction without Supervision
| Title | Deep Bidirectional Transformers for Relation Extraction without Supervision |
| Authors | Yannis Papanikolaou, Ian Roberts, Andrea Pierleoni |
| Abstract | We present a novel framework to deal with relation extraction tasks in cases where there is complete lack of supervision, either in the form of gold annotations, or relations from a knowledge base. Our approach leverages syntactic parsing and pre-trained word embeddings to extract few but precise relations,which are then used to annotate a larger cor-pus, in a manner identical to distant supervision. The resulting data set is employed to fine tune a pre-trained BERT model in order to perform relation extraction. Empirical evaluation on four data sets from the biomedical domain shows that our method significantly outperforms two simple baselines for unsupervised relation extraction and, even if not using any supervision at all, achieves slightly worse results than the state-of-the-art in three out of four data sets. Importantly, we show that it is possible to successfully fine tune a large pre-trained language model with noisy data, as op-posed to previous works that rely on gold data for fine tuning. |
| Tasks | Language Modelling, Relation Extraction, Word Embeddings |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00313v1 |
| https://arxiv.org/pdf/1911.00313v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-bidirectional-transformers-for-relation-1 |
| Repo | |
| Framework | |
Detection of Single Grapevine Berries in Images Using Fully Convolutional Neural Networks
| Title | Detection of Single Grapevine Berries in Images Using Fully Convolutional Neural Networks |
| Authors | Laura Zabawa, Anna Kicherer, Lasse Klingbeil, Andres Milioto, Reinhard Töpfer, Heiner Kuhlmann, Ribana Roscher |
| Abstract | Yield estimation and forecasting are of special interest in the field of grapevine breeding and viticulture. The number of harvested berries per plant is strongly correlated with the resulting quality. Therefore, early yield forecasting can enable a focused thinning of berries to ensure a high quality end product. Traditionally yield estimation is done by extrapolating from a small sample size and by utilizing historic data. Moreover, it needs to be carried out by skilled experts with much experience in this field. Berry detection in images offers a cheap, fast and non-invasive alternative to the otherwise time-consuming and subjective on-site analysis by experts. We apply fully convolutional neural networks on images acquired with the Phenoliner, a field phenotyping platform. We count single berries in images to avoid the error-prone detection of grapevine clusters. Clusters are often overlapping and can vary a lot in the size which makes the reliable detection of them difficult. We address especially the detection of white grapes directly in the vineyard. The detection of single berries is formulated as a classification task with three classes, namely ‘berry’, ‘edge’ and ‘background’. A connected component algorithm is applied to determine the number of berries in one image. We compare the automatically counted number of berries with the manually detected berries in 60 images showing Riesling plants in vertical shoot positioned trellis (VSP) and semi minimal pruned hedges (SMPH). We are able to detect berries correctly within the VSP system with an accuracy of 94.0 % and for the SMPH system with 85.6 %. |
| Tasks | |
| Published | 2019-05-01 |
| URL | http://arxiv.org/abs/1905.00458v1 |
| http://arxiv.org/pdf/1905.00458v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-of-single-grapevine-berries-in |
| Repo | |
| Framework | |
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection
| Title | ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection |
| Authors | Zhuo Chen, Jiyuan Zhang, Ruizhou Ding, Diana Marculescu |
| Abstract | In recent years, Convolutional Neural Networks (CNNs) have shown superior capability in visual learning tasks. While accuracy-wise CNNs provide unprecedented performance, they are also known to be computationally intensive and energy demanding for modern computer systems. In this paper, we propose Virtual Pooling (ViP), a model-level approach to improve speed and energy consumption of CNN-based image classification and object detection tasks, with a provable error bound. We show the efficacy of ViP through experiments on four CNN models, three representative datasets, both desktop and mobile platforms, and two visual learning tasks, i.e., image classification and object detection. For example, ViP delivers 2.1x speedup with less than 1.5% accuracy degradation in ImageNet classification on VGG-16, and 1.8x speedup with 0.025 mAP degradation in PASCAL VOC object detection with Faster-RCNN. ViP also reduces mobile GPU and CPU energy consumption by up to 55% and 70%, respectively. As a complementary method to existing acceleration approaches, ViP achieves 1.9x speedup on ThiNet leading to a combined speedup of 5.23x on VGG-16. Furthermore, ViP provides a knob for machine learning practitioners to generate a set of CNN models with varying trade-offs between system speed/energy consumption and accuracy to better accommodate the requirements of their tasks. Code is available at https://github.com/cmu-enyac/VirtualPooling. |
| Tasks | Image Classification, Object Detection |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.07912v2 |
| https://arxiv.org/pdf/1906.07912v2.pdf | |
| PWC | https://paperswithcode.com/paper/vip-virtual-pooling-for-accelerating-cnn |
| Repo | |
| Framework | |
Multi-task Learning for Chinese Word Usage Errors Detection
| Title | Multi-task Learning for Chinese Word Usage Errors Detection |
| Authors | Jinbin Zhang, Heng Wang |
| Abstract | Chinese word usage errors often occur in non-native Chinese learners’ writing. It is very helpful for non-native Chinese learners to detect them automatically when learning writing. In this paper, we propose a novel approach, which takes advantages of different auxiliary tasks, such as POS-tagging prediction and word log frequency prediction, to help the task of Chinese word usage error detection. With the help of these auxiliary tasks, we achieve the state-of-the-art results on the performances on the HSK corpus data, without any other extra data. |
| Tasks | Multi-Task Learning |
| Published | 2019-04-03 |
| URL | http://arxiv.org/abs/1904.01783v1 |
| http://arxiv.org/pdf/1904.01783v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-for-chinese-word-usage |
| Repo | |
| Framework | |
On the Calibration of Multiclass Classification with Rejection
| Title | On the Calibration of Multiclass Classification with Rejection |
| Authors | Chenri Ni, Nontawat Charoenphakdee, Junya Honda, Masashi Sugiyama |
| Abstract | We investigate the problem of multiclass classification with rejection, where a classifier can choose not to make a prediction to avoid critical misclassification. First, we consider an approach based on simultaneous training of a classifier and a rejector, which achieves the state-of-the-art performance in the binary case. We analyze this approach for the multiclass case and derive a general condition for calibration to the Bayes-optimal solution, which suggests that calibration is hard to achieve by general loss functions unlike the binary case. Next, we consider another traditional approach based on confidence scores, in which the existing work focuses on a specific class of losses. We propose rejection criteria for more general losses for this approach and guarantee calibration to the Bayes-optimal solution. Finally, we conduct experiments to validate the relevance of our theoretical findings. |
| Tasks | Calibration |
| Published | 2019-01-30 |
| URL | https://arxiv.org/abs/1901.10655v2 |
| https://arxiv.org/pdf/1901.10655v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-possibility-and-impossibility-of |
| Repo | |
| Framework | |
Emotional Voice Conversion using Multitask Learning with Text-to-speech
| Title | Emotional Voice Conversion using Multitask Learning with Text-to-speech |
| Authors | Tae-Ho Kim, Sungjae Cho, Shinkook Choi, Sejik Park, Soo-Young Lee |
| Abstract | Voice conversion (VC) is a task to transform a person’s voice to different style while conserving linguistic contents. Previous state-of-the-art on VC is based on sequence-to-sequence (seq2seq) model, which could mislead linguistic information. There was an attempt to overcome it by using textual supervision, it requires explicit alignment which loses the benefit of using seq2seq model. In this paper, a voice converter using multitask learning with text-to-speech (TTS) is presented. The embedding space of seq2seq-based TTS has abundant information on the text. The role of the decoder of TTS is to convert embedding space to speech, which is same to VC. In the proposed model, the whole network is trained to minimize loss of VC and TTS. VC is expected to capture more linguistic information and to preserve training stability by multitask learning. Experiments of VC were performed on a male Korean emotional text-speech dataset, and it is shown that multitask learning is helpful to keep linguistic contents in VC. |
| Tasks | Voice Conversion |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.06149v2 |
| https://arxiv.org/pdf/1911.06149v2.pdf | |
| PWC | https://paperswithcode.com/paper/emotional-voice-conversion-using-multitask |
| Repo | |
| Framework | |
Reinforcement Learning: a Comparison of UCB Versus Alternative Adaptive Policies
| Title | Reinforcement Learning: a Comparison of UCB Versus Alternative Adaptive Policies |
| Authors | Wesley Cowan, Michael N. Katehakis, Daniel Pirutinsky |
| Abstract | In this paper we consider the basic version of Reinforcement Learning (RL) that involves computing optimal data driven (adaptive) policies for Markovian decision process with unknown transition probabilities. We provide a brief survey of the state of the art of the area and we compare the performance of the classic UCB policy of \cc{bkmdp97} with a new policy developed herein which we call MDP-Deterministic Minimum Empirical Divergence (MDP-DMED), and a method based on Posterior sampling (MDP-PS). |
| Tasks | |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06019v1 |
| https://arxiv.org/pdf/1909.06019v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-a-comparison-of-ucb |
| Repo | |
| Framework | |
PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation
| Title | PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation |
| Authors | Haojie Liu, Kang Liao, Chunyu Lin, Yao Zhao, Yulan Guo |
| Abstract | LiDAR sensors can provide dependable 3D spatial information at a low frequency (around 10Hz) and have been widely applied in the field of autonomous driving and UAV. However, the camera with a higher frequency (around 20Hz) has to be decreased so as to match with LiDAR in a multi-sensor system. In this paper, we propose a novel Pseudo-LiDAR interpolation network (PLIN) to increase the frequency of LiDAR sensors. PLIN can generate temporally and spatially high-quality point cloud sequences to match the high frequency of cameras. To achieve this goal, we design a coarse interpolation stage guided by consecutive sparse depth maps and motion relationship. We also propose a refined interpolation stage guided by the realistic scene. Using this coarse-to-fine cascade structure, our method can progressively perceive multi-modal information and generate accurate intermediate point clouds. To the best of our knowledge, this is the first deep framework for Pseudo-LiDAR point cloud interpolation, which shows appealing applications in navigation systems equipped with LiDAR and cameras. Experimental results demonstrate that PLIN achieves promising performance on the KITTI dataset, significantly outperforming the traditional interpolation method and the state-of-the-art video interpolation technique. |
| Tasks | Autonomous Driving |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07137v1 |
| https://arxiv.org/pdf/1909.07137v1.pdf | |
| PWC | https://paperswithcode.com/paper/plin-a-network-for-pseudo-lidar-point-cloud |
| Repo | |
| Framework | |
Transductive Auxiliary Task Self-Training for Neural Multi-Task Models
| Title | Transductive Auxiliary Task Self-Training for Neural Multi-Task Models |
| Authors | Johannes Bjerva, Katharina Kann, Isabelle Augenstein |
| Abstract | Multi-task learning and self-training are two common ways to improve a machine learning model’s performance in settings with limited training data. Drawing heavily on ideas from those two approaches, we suggest transductive auxiliary task self-training: training a multi-task model on (i) a combination of main and auxiliary task training data, and (ii) test instances with auxiliary task labels which a single-task version of the model has previously generated. We perform extensive experiments on 86 combinations of languages and tasks. Our results are that, on average, transductive auxiliary task self-training improves absolute accuracy by up to 9.56% over the pure multi-task model for dependency relation tagging and by up to 13.03% for semantic tagging. |
| Tasks | Multi-Task Learning |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06136v2 |
| https://arxiv.org/pdf/1908.06136v2.pdf | |
| PWC | https://paperswithcode.com/paper/transductive-auxiliary-task-self-training-for |
| Repo | |
| Framework | |
Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS
| Title | Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS |
| Authors | Petro Liashchynskyi, Pavlo Liashchynskyi |
| Abstract | In this paper, we compare the three most popular algorithms for hyperparameter optimization (Grid Search, Random Search, and Genetic Algorithm) and attempt to use them for neural architecture search (NAS). We use these algorithms for building a convolutional neural network (search architecture). Experimental results on CIFAR-10 dataset further demonstrate the performance difference between compared algorithms. The comparison results are based on the execution time of the above algorithms and accuracy of the proposed models. |
| Tasks | Hyperparameter Optimization, Neural Architecture Search |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06059v1 |
| https://arxiv.org/pdf/1912.06059v1.pdf | |
| PWC | https://paperswithcode.com/paper/grid-search-random-search-genetic-algorithm-a |
| Repo | |
| Framework | |
Recognition of Ischaemia and Infection in Diabetic Foot Ulcers: Dataset and Techniques
| Title | Recognition of Ischaemia and Infection in Diabetic Foot Ulcers: Dataset and Techniques |
| Authors | Manu Goyal, Neil Reeves, Satyan Rajbhandari, Naseer Ahmad, Chuan Wang, Moi Hoon Yap |
| Abstract | Recognition and analysis of Diabetic Foot Ulcers (DFU) using computerized methods is an emerging research area with the evolution of image-based machine learning algorithms. Existing research using visual computerized methods mainly focuses on recognition, detection, and segmentation of the visual appearance of the DFU as well as tissue classification. According to DFU medical classification systems, the presence of infection (bacteria in the wound) and ischaemia (inadequate blood supply) has important clinical implications for DFU assessment, which are used to predict the risk of amputation. In this work, we propose a new dataset and computer vision techniques to identify the presence of infection and ischaemia in DFU. This is the first time a DFU dataset with ground truth labels of ischaemia and infection cases is introduced for research purposes. For the handcrafted machine learning approach, we propose a new feature descriptor, namely the Superpixel Color Descriptor. Then we use the Ensemble Convolutional Neural Network (CNN) model for more effective recognition of ischaemia and infection. We propose to use a natural data-augmentation method, which identifies the region of interest on foot images and focuses on finding the salient features existing in this area. Finally, we evaluate the performance of our proposed techniques on binary classification, i.e. ischaemia versus non-ischaemia and infection versus non-infection. Overall, our method performed better in the classification of ischaemia than infection. We found that our proposed Ensemble CNN deep learning algorithms performed better for both classification tasks as compared to handcrafted machine learning algorithms, with 90% accuracy in ischaemia classification and 73% in infection classification. |
| Tasks | Data Augmentation |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05317v4 |
| https://arxiv.org/pdf/1908.05317v4.pdf | |
| PWC | https://paperswithcode.com/paper/recognition-of-ischaemia-and-infection-in |
| Repo | |
| Framework | |
