Paper Group NANR 172
Coverage Path Planning using Path Primitive Sampling and Primitive Coverage Graph for Visual Inspection. Learning Representations from Healthcare Time Series Data for Unsupervised Anomaly Detection. Daniel@FinTOC-2019 Shared Task : TOC Extraction and Title Detection. Pseudonymisation of Swedish Electronic Patient Records Using a Rule-Based Approach …
Coverage Path Planning using Path Primitive Sampling and Primitive Coverage Graph for Visual Inspection
| Title | Coverage Path Planning using Path Primitive Sampling and Primitive Coverage Graph for Visual Inspection |
| Authors | Wei Jing, Di Deng2, Zhe Xiao3, Yong Liu1， Kenji Shimada2 |
| Abstract | Abstract— Planning the path to gather the surface information of the target objects is crucial to improve the efficiency of and reduce the overall cost, for visual inspection applications with Unmanned Aerial Vehicles (UAVs). Coverage Path Planning (CPP) problem is often formulated for these inspection applications because of the coverage requirement. Traditionally, researchers usually plan and optimize the viewpoints to capture the surface information first, and then optimize the path to visit the selected viewpoints. In this paper, we propose a novel planning method to directly sample and plan the inspection path for a camera-equipped UAV to acquire visual and geometric information of the target structures as a video stream setting in complex 3D environment. The proposed planning method first generates via-points and path primitives around the target object by using sampling methods based on voxel dilation and subtraction. A novel Primitive Coverage Graph (PCG) is then proposed to encode the topological information, flying distances, and visibility information, with the sampled via-points and path primitives. Finally graph search is performed to find the resultant path in the PCG to complete the inspection task with the coverage requirements. The effectiveness of the proposed method is demonstrated through simulation and field tests in this paper. |
| Tasks | |
| Published | 2019-08-08 |
| URL | https://arxiv.org/abs/1908.02901 |
| https://arxiv.org/pdf/1908.02901.pdf | |
| PWC | https://paperswithcode.com/paper/coverage-path-planning-using-path-primitive |
| Repo | |
| Framework | |
Learning Representations from Healthcare Time Series Data for Unsupervised Anomaly Detection
| Title | Learning Representations from Healthcare Time Series Data for Unsupervised Anomaly Detection |
| Authors | João Pereira, Margarida Silveira |
| Abstract | The amount of time series data generated in Healthcare is growing very fast and so is the need for methods that can analyse these data, detect anomalies and provide meaningful insights. However, most of the data available is unlabelled and, therefore, anomaly detection in this scenario has been a great challenge for researchers and practitioners. Recently, unsupervised representation learning with deep generative models has been applied to find representations of data, without the need for big labelled datasets. Motivated by their success, we propose an unsupervised framework for anomaly detection in time series data. In our method, both representation learning and anomaly detection are fully unsupervised. In addition, the training data may contain anomalous data. We first learn representations of time series using a Variational Recurrent Autoencoder. Afterwards, based on those representations, we detect anomalous time series using Clustering and the Wasserstein distance. Our results on the publicly available ECG5000 electrocardiogram dataset show the ability of the proposed approach to detect anomalous heartbeats in a fully unsupervised fashion, while providing structured and expressive data representations. Furthermore, our approach outperforms previous supervised and unsupervised methods on this dataset. |
| Tasks | Anomaly Detection, Outlier Detection, Representation Learning, Time Series, Unsupervised Anomaly Detection, Unsupervised Representation Learning |
| Published | 2019-04-04 |
| URL | https://doi.org/10.1109/BIGCOMP.2019.8679157 |
| http://www.joao-pereira.pt/docs/accepted_version_BigComp19.pdf | |
| PWC | https://paperswithcode.com/paper/learning-representations-from-healthcare-time |
| Repo | |
| Framework | |
Daniel@FinTOC-2019 Shared Task : TOC Extraction and Title Detection
| Title | Daniel@FinTOC-2019 Shared Task : TOC Extraction and Title Detection |
| Authors | Emmanuel Giguet, Ga{"e}l Lejeune |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6409/ |
| https://www.aclweb.org/anthology/W19-6409 | |
| PWC | https://paperswithcode.com/paper/danielfintoc-2019-shared-task-toc-extraction |
| Repo | |
| Framework | |
Pseudonymisation of Swedish Electronic Patient Records Using a Rule-Based Approach
| Title | Pseudonymisation of Swedish Electronic Patient Records Using a Rule-Based Approach |
| Authors | Hercules Dalianis |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6503/ |
| https://www.aclweb.org/anthology/W19-6503 | |
| PWC | https://paperswithcode.com/paper/pseudonymisation-of-swedish-electronic |
| Repo | |
| Framework | |
Task Agnostic Meta-Learning for Few-Shot Learning
| Title | Task Agnostic Meta-Learning for Few-Shot Learning |
| Authors | Muhammad Abdullah Jamal, Guo-Jun Qi |
| Abstract | Meta-learning approaches have been proposed to tackle the few-shot learning problem. Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a meta-learner could be fragile when it is over-trained on existing tasks during meta-training phase. In other words, the initial model of a meta-learner could be too biased towards existing tasks to adapt to new tasks, especially when only very few examples are available to update the model. To avoid a biased meta-learner and improve its generalizability, we propose a novel paradigm of Task-Agnostic Meta-Learning (TAML) algorithms. Specifically, we present an entropy-based approach that meta-learns an unbiased initial model with the largest uncertainty over the output labels by preventing it from over-performing in classification tasks. Alternatively, a more general inequality-minimization TAML is presented for more ubiquitous scenarios by directly minimizing the inequality of initial losses beyond the classification tasks wherever a suitable loss can be defined. Experiments on benchmarked datasets demonstrate that the proposed approaches outperform compared meta-learning algorithms in both few-shot classification and reinforcement learning tasks. |
| Tasks | Few-Shot Learning, Meta-Learning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Jamal_Task_Agnostic_Meta-Learning_for_Few-Shot_Learning_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Jamal_Task_Agnostic_Meta-Learning_for_Few-Shot_Learning_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/task-agnostic-meta-learning-for-few-shot-1 |
| Repo | |
| Framework | |
DFKI-NMT Submission to the WMT19 News Translation Task
| Title | DFKI-NMT Submission to the WMT19 News Translation Task |
| Authors | Jingyi Zhang, Josef van Genabith |
| Abstract | This paper describes the DFKI-NMT submission to the WMT19 News translation task. We participated in both English-to-German and German-to-English directions. We trained Transformer models and adopted various techniques for effectively training our models, including data selection, back-translation and in-domain fine-tuning. We give a detailed analysis of the performance of our system. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5350/ |
| https://www.aclweb.org/anthology/W19-5350 | |
| PWC | https://paperswithcode.com/paper/dfki-nmt-submission-to-the-wmt19-news |
| Repo | |
| Framework | |
Text Emotion Distribution Learning from Small Sample: A Meta-Learning Approach
| Title | Text Emotion Distribution Learning from Small Sample: A Meta-Learning Approach |
| Authors | Zhenjie Zhao, Xiaojuan Ma |
| Abstract | Text emotion distribution learning (EDL) aims to develop models that can predict the intensity values of a sentence across a set of emotion categories. Existing methods based on supervised learning require a large amount of well-labelled training data, which is difficult to obtain due to inconsistent perception of fine-grained emotion intensity. In this paper, we propose a meta-learning approach to learn text emotion distributions from a small sample. Specifically, we propose to learn low-rank sentence embeddings by tensor decomposition to capture their contextual semantic similarity, and use K-nearest neighbors (KNNs) of each sentence in the embedding space to generate sample clusters. We then train a meta-learner that can adapt to new data with only a few training samples on the clusters, and further fit the meta-learner on KNNs of a testing sample for EDL. In this way, we effectively augment the learning ability of a model on the small sample. To demonstrate the performance, we compare the proposed approach with state-of-the-art EDL methods on a widely used EDL dataset: SemEval 2007 Task 14 (Strapparava and Mihalcea, 2007). Results show the superiority of our method on small-sample emotion distribution learning. |
| Tasks | Meta-Learning, Semantic Similarity, Semantic Textual Similarity, Sentence Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1408/ |
| https://www.aclweb.org/anthology/D19-1408 | |
| PWC | https://paperswithcode.com/paper/text-emotion-distribution-learning-from-small |
| Repo | |
| Framework | |
Graph Enhanced Cross-Domain Text-to-SQL Generation
| Title | Graph Enhanced Cross-Domain Text-to-SQL Generation |
| Authors | Siyu Huo, Tengfei Ma, Jie Chen, Maria Chang, Lingfei Wu, Michael Witbrock |
| Abstract | Semantic parsing is a fundamental problem in natural language understanding, as it involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations. Existing deep learning approaches for semantic parsing have shown promise on a variety of benchmark data sets, particularly on text-to-SQL parsing. However, most text-to-SQL parsers do not generalize to unseen data sets in different domains. In this paper, we propose a new cross-domain learning scheme to perform text-to-SQL translation and demonstrate its use on Spider, a large-scale cross-domain text-to-SQL data set. We improve upon a state-of-the-art Spider model, SyntaxSQLNet, by constructing a graph of column names for all databases and using graph neural networks to compute their embeddings. The resulting embeddings offer better cross-domain representations and SQL queries, as evidenced by substantial improvement on the Spider data set compared to SyntaxSQLNet. |
| Tasks | Semantic Parsing, Text-To-Sql |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5319/ |
| https://www.aclweb.org/anthology/D19-5319 | |
| PWC | https://paperswithcode.com/paper/graph-enhanced-cross-domain-text-to-sql |
| Repo | |
| Framework | |
Brain-inspired Robust Vision using Convolutional Neural Networks with Feedback
| Title | Brain-inspired Robust Vision using Convolutional Neural Networks with Feedback |
| Authors | Yujia Huang, Sihui Dai, Tan Nguyen, Pinglei Bao, Doris Y. Tsao, Richard G. Baraniuk, Anima Anandkumar |
| Abstract | Primates have a remarkable ability to correctly classify images even in the presence of significant noise and degradation. In contrast, even the state-of-art CNNs are extremely vulnerable to imperceptible level of noise. Many neuroscience studies have suggested that robustness in human vision arises from the interaction between the feedforward signals from bottom-up pathways of the visual cortex and the feedback signals from the top-down pathways. Motivated by this, we propose a new neuro-inspired model, namely Convolutional Neural Networks with Feedback (CNN-F). CNN-F augments CNN with a feedback generative network that shares the same set of weights along with an additional set of latent variables. CNN-F combines bottom-up and top-down inference through approximate loopy belief propagation to obtain the MAP-estimates of the latent variables. We show that CNN-F’s iterative inference allows for disentanglement of latent variables across layers. We validate the advantages of CNN-F over the baseline CNN in multiple ways. Our experimental results suggest that the CNN-F is more robust to image degradation such as pixel noise, occlusion, and blur than the corresponding CNN. Furthermore, we show that the CNN-F is capable of restoring original images from the degraded ones with high reconstruction accuracy while introducing negligible artifacts. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://openreview.net/forum?id=rylU4mtUIS |
| https://pdfs.semanticscholar.org/d44a/122e36024c062d19842aab61f9cd8f8c2fed.pdf?_ga=2.134582392.841563911.1579190460-8434615.1579190460 | |
| PWC | https://paperswithcode.com/paper/brain-inspired-robust-vision-using |
| Repo | |
| Framework | |
AMPERSAND: Argument Mining for PERSuAsive oNline Discussions
| Title | AMPERSAND: Argument Mining for PERSuAsive oNline Discussions |
| Authors | Tuhin Chakrabarty, Christopher Hidey, Smar Muresan, a, Kathy McKeown, Alyssa Hwang |
| Abstract | Argumentation is a type of discourse where speakers try to persuade their audience about the reasonableness of a claim by presenting supportive arguments. Most work in argument mining has focused on modeling arguments in monologues. We propose a computational model for argument mining in online persuasive discussion forums that brings together the micro-level (argument as product) and macro-level (argument as process) models of argumentation. Fundamentally, this approach relies on identifying relations between components of arguments in a discussion thread. Our approach for relation prediction uses contextual information in terms of fine-tuning a pre-trained language model and leveraging discourse relations based on Rhetorical Structure Theory. We additionally propose a candidate selection method to automatically predict what parts of one{'}s argument will be targeted by other participants in the discussion. Our models obtain significant improvements compared to recent state-of-the-art approaches using pointer networks and a pre-trained language model. |
| Tasks | Argument Mining, Language Modelling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1291/ |
| https://www.aclweb.org/anthology/D19-1291 | |
| PWC | https://paperswithcode.com/paper/ampersand-argument-mining-for-persuasive |
| Repo | |
| Framework | |
A Cascade Model for Proposition Extraction in Argumentation
| Title | A Cascade Model for Proposition Extraction in Argumentation |
| Authors | Yohan Jo, Jacky Visser, Chris Reed, Eduard Hovy |
| Abstract | We present a model to tackle a fundamental but understudied problem in computational argumentation: proposition extraction. Propositions are the basic units of an argument and the primary building blocks of most argument mining systems. However, they are usually substituted by argumentative discourse units obtained via surface-level text segmentation, which may yield text segments that lack semantic information necessary for subsequent argument mining processes. In contrast, our cascade model aims to extract complete propositions by handling anaphora resolution, text segmentation, reported speech, questions, imperatives, missing subjects, and revision. We formulate each task as a computational problem and test various models using a corpus of the 2016 U.S. presidential debates. We show promising performance for some tasks and discuss main challenges in proposition extraction. |
| Tasks | Argument Mining |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4502/ |
| https://www.aclweb.org/anthology/W19-4502 | |
| PWC | https://paperswithcode.com/paper/a-cascade-model-for-proposition-extraction-in |
| Repo | |
| Framework | |
Inforex — a Collaborative Systemfor Text Corpora Annotation and Analysis Goes Open
| Title | Inforex — a Collaborative Systemfor Text Corpora Annotation and Analysis Goes Open |
| Authors | Micha{\l} Marci{'n}czuk, Marcin Oleksy |
| Abstract | In the paper we present the latest changes introduce to Inforex {—} a web-based system for qualitative and collaborative text corpora annotation and analysis. One of the most important news is the release of source codes. Now the system is available on the GitHub repository (https://github.com/CLARIN-PL/Inforex) as an open source project. The system can be easily setup and run in a Docker container what simplifies the installation process. The major improvements include: semi-automatic text annotation, multilingual text preprocessing using CLARIN-PL web services, morphological tagging of XML documents, improved editor for annotation attribute, batch annotation attribute editor, morphological disambiguation, extended word sense annotation. This paper contains a brief description of the mentioned improvements. We also present two use cases in which various Inforex features were used and tested in real-life projects. |
| Tasks | Morphological Tagging |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1083/ |
| https://www.aclweb.org/anthology/R19-1083 | |
| PWC | https://paperswithcode.com/paper/inforex-a-collaborative-systemfor-text |
| Repo | |
| Framework | |
Transferring Knowledge from Discourse to Arguments: A Case Study with Scientific Abstracts
| Title | Transferring Knowledge from Discourse to Arguments: A Case Study with Scientific Abstracts |
| Authors | Pablo Accuosto, Horacio Saggion |
| Abstract | In this work we propose to leverage resources available with discourse-level annotations to facilitate the identification of argumentative components and relations in scientific texts, which has been recognized as a particularly challenging task. In particular, we implement and evaluate a transfer learning approach in which contextualized representations learned from discourse parsing tasks are used as input of argument mining models. As a pilot application, we explore the feasibility of using automatically identified argumentative components and relations to predict the acceptance of papers in computer science venues. In order to conduct our experiments, we propose an annotation scheme for argumentative units and relations and use it to enrich an existing corpus with an argumentation layer. |
| Tasks | Argument Mining, Transfer Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4505/ |
| https://www.aclweb.org/anthology/W19-4505 | |
| PWC | https://paperswithcode.com/paper/transferring-knowledge-from-discourse-to |
| Repo | |
| Framework | |
Data-Anonymous Encoding for Text-to-SQL Generation
| Title | Data-Anonymous Encoding for Text-to-SQL Generation |
| Authors | Zhen Dong, Shizhao Sun, Hongzhi Liu, Jian-Guang Lou, Dongmei Zhang |
| Abstract | On text-to-SQL generation, the input utterance usually contains lots of tokens that are related to column names or cells in the table, called \textit{table-related tokens}. These table-related tokens are troublesome for the downstream neural semantic parser because it brings complex semantics and hinders the sharing across the training examples. However, existing approaches either ignore handling these tokens before the semantic parser or simply use deterministic approaches based on string-match or word embedding similarity. In this work, we propose a more efficient approach to handle table-related tokens before the semantic parser. First, we formulate it as a sequential tagging problem and propose a two-stage anonymization model to learn the semantic relationship between tables and input utterances. Then, we leverage the implicit supervision from SQL queries by policy gradient to guide the training. Experiments demonstrate that our approach consistently improves performances of different neural semantic parsers and significantly outperforms deterministic approaches. |
| Tasks | Text-To-Sql |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1543/ |
| https://www.aclweb.org/anthology/D19-1543 | |
| PWC | https://paperswithcode.com/paper/data-anonymous-encoding-for-text-to-sql |
| Repo | |
| Framework | |
Spatio-Temporal Prediction of Dialectal Variant Usage
| Title | Spatio-Temporal Prediction of Dialectal Variant Usage |
| Authors | P{'e}ter Jeszenszky, Panote Siriaraya, Philipp Stoeckle, Adam Jatowt |
| Abstract | The distribution of most dialectal variants have not only spatial but also temporal patterns. Based on the {}apparent time hypothesis{'}, much of dialect change is happening through younger speakers accepting innovations. Thus, synchronic diversity can be interpreted diachronically. With the assumption of the {}contact effect{'}, i.e. contact possibility (contact and isolation) between speaker communities being responsible for language change, and the apparent time hypothesis, we aim to predict the usage of dialectal variants. In this paper we model the contact possibility based on two of the most important factors in sociolinguistics to be affecting language change: age and distance. The first steps of the approach involve modeling contact possibility using a logistic predictor, taking the age of respondents into account. We test the \textit{global}, and the \textit{local} role of age for variation where the local level means spatial subsets around each survey site, chosen based on \textit{k} nearest neighbors. The prediction approach is tested on Swiss German syntactic survey data, featuring multiple respondents from different age cohorts at survey sites. The results show the relative success of the logistic prediction approach and the limitations of the method, therefore further proposals are made to develop the methodology. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4723/ |
| https://www.aclweb.org/anthology/W19-4723 | |
| PWC | https://paperswithcode.com/paper/spatio-temporal-prediction-of-dialectal |
| Repo | |
| Framework | |
