Paper Group NANR 29
Can Character Embeddings Improve Cause-of-Death Classification for Verbal Autopsy Narratives?. Yimmon at SemEval-2019 Task 9: Suggestion Mining with Hybrid Augmented Approaches. Clinical Case Reports for NLP. Parsing Weighted Order-Preserving Hyperedge Replacement Grammars. Classifying Arabic dialect text in the Social Media Arabic Dialect Corpus ( …
Can Character Embeddings Improve Cause-of-Death Classification for Verbal Autopsy Narratives?
| Title | Can Character Embeddings Improve Cause-of-Death Classification for Verbal Autopsy Narratives? |
| Authors | Zhaodong Yan, Serena Jeblee, Graeme Hirst |
| Abstract | We present two models for combining word and character embeddings for cause-of-death classification of verbal autopsy reports using the text of the narratives. We find that for smaller datasets (500 to 1000 records), adding character information to the model improves classification, making character-based CNNs a promising method for automated verbal autopsy coding. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5025/ |
| https://www.aclweb.org/anthology/W19-5025 | |
| PWC | https://paperswithcode.com/paper/can-character-embeddings-improve-cause-of |
| Repo | |
| Framework | |
Yimmon at SemEval-2019 Task 9: Suggestion Mining with Hybrid Augmented Approaches
| Title | Yimmon at SemEval-2019 Task 9: Suggestion Mining with Hybrid Augmented Approaches |
| Authors | Yimeng Zhuang |
| Abstract | Suggestion mining task aims to extract tips, advice, and recommendations from unstructured text. The task includes many challenges, such as class imbalance, figurative expressions, context dependency, and long and complex sentences. This paper gives a detailed system description of our submission in SemEval 2019 Task 9 Subtask A. We transfer Self-Attention Network (SAN), a successful model in machine reading comprehension field, into this task. Our model concentrates on modeling long-term dependency which is indispensable to parse long and complex sentences. Besides, we also adopt techniques, such as contextualized embedding, back-translation, and auxiliary loss, to augment the system. Our model achieves a performance of F1=76.3, and rank 4th among 34 participating systems. Further ablation study shows that the techniques used in our system are beneficial to the performance. |
| Tasks | Machine Reading Comprehension, Reading Comprehension |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2222/ |
| https://www.aclweb.org/anthology/S19-2222 | |
| PWC | https://paperswithcode.com/paper/yimmon-at-semeval-2019-task-9-suggestion |
| Repo | |
| Framework | |
Clinical Case Reports for NLP
| Title | Clinical Case Reports for NLP |
| Authors | Cyril Grouin, Natalia Grabar, Vincent Claveau, Thierry Hamon |
| Abstract | Textual data are useful for accessing expert information. Yet, since the texts are representative of distinct language uses, it is necessary to build specific corpora in order to be able to design suitable NLP tools. In some domains, such as medical domain, it may be complicated to access the representative textual data and their semantic annotations, while there exists a real need for providing efficient tools and methods. Our paper presents a corpus of clinical cases written in French, and their semantic annotations. Thus, we manually annotated a set of 717 files into four general categories (age, gender, outcome, and origin) for a total number of 2,835 annotations. The values of age, gender, and outcome are normalized. A subset with 70 files has been additionally manually annotated into 27 categories for a total number of 5,198 annotations. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5029/ |
| https://www.aclweb.org/anthology/W19-5029 | |
| PWC | https://paperswithcode.com/paper/clinical-case-reports-for-nlp |
| Repo | |
| Framework | |
Parsing Weighted Order-Preserving Hyperedge Replacement Grammars
| Title | Parsing Weighted Order-Preserving Hyperedge Replacement Grammars |
| Authors | Henrik Bj{"o}rklund, Frank Drewes, Petter Ericson |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5701/ |
| https://www.aclweb.org/anthology/W19-5701 | |
| PWC | https://paperswithcode.com/paper/parsing-weighted-order-preserving-hyperedge |
| Repo | |
| Framework | |
Classifying Arabic dialect text in the Social Media Arabic Dialect Corpus (SMADC)
| Title | Classifying Arabic dialect text in the Social Media Arabic Dialect Corpus (SMADC) |
| Authors | Areej Alshutayri, Eric Atwell |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5607/ |
| https://www.aclweb.org/anthology/W19-5607 | |
| PWC | https://paperswithcode.com/paper/classifying-arabic-dialect-text-in-the-social |
| Repo | |
| Framework | |
Sensing Tree Automata as a Model of Syntactic Dependencies
| Title | Sensing Tree Automata as a Model of Syntactic Dependencies |
| Authors | Thomas Graf, Aniello De Santo |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5702/ |
| https://www.aclweb.org/anthology/W19-5702 | |
| PWC | https://paperswithcode.com/paper/sensing-tree-automata-as-a-model-of-syntactic |
| Repo | |
| Framework | |
Efficient Near-Optimal Testing of Community Changes in Balanced Stochastic Block Models
| Title | Efficient Near-Optimal Testing of Community Changes in Balanced Stochastic Block Models |
| Authors | Aditya Gangrade, Praveen Venkatesh, Bobak Nazer, Venkatesh Saligrama |
| Abstract | We propose and analyze the problems of \textit{community goodness-of-fit and two-sample testing} for stochastic block models (SBM), where changes arise due to modification in community memberships of nodes. Motivated by practical applications, we consider the challenging sparse regime, where expected node degrees are constant, and the inter-community mean degree ($b$) scales proportionally to intra-community mean degree ($a$). Prior work has sharply characterized partial or full community recovery in terms of a ``signal-to-noise ratio’’ ($\mathrm{SNR}$) based on $a$ and $b$. For both problems, we propose computationally-efficient tests that can succeed far beyond the regime where recovery of community membership is even possible. Overall, for large changes, $s \gg \sqrt{n}$, we need only $\mathrm{SNR}= O(1)$ whereas a na"ive test based on community recovery with $O(s)$ errors requires $\mathrm{SNR}= \Theta(\log n)$. Conversely, in the small change regime, $s \ll \sqrt{n}$, via an information theoretic lower bound, we show that, surprisingly, no algorithm can do better than the na"ive algorithm that first estimates the community up to $O(s)$ errors and then detects changes. We validate these phenomena numerically on SBMs and on real-world datasets as well as Markov Random Fields where we only observe node data rather than the existence of links. | |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9224-efficient-near-optimal-testing-of-community-changes-in-balanced-stochastic-block-models |
| http://papers.nips.cc/paper/9224-efficient-near-optimal-testing-of-community-changes-in-balanced-stochastic-block-models.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-near-optimal-testing-of-community |
| Repo | |
| Framework | |
The Scientization of Literary Study
| Title | The Scientization of Literary Study |
| Authors | Stefania Degaetano-Ortlieb, Andrew Piper |
| Abstract | Scholarly practices within the humanities have historically been perceived as distinct from the natural sciences. We look at literary studies, a discipline strongly anchored in the humanities, and hypothesize that over the past half-century literary studies has instead undergone a process of {}scientization{''}, adopting linguistic behavior similar to the sciences. We test this using methods based on information theory, comparing a corpus of literary studies articles (around 63,400) with a corpus of standard English and scientific English respectively. We show evidence for {}scientization{''} effects in literary studies, though at a more muted level than scientific English, suggesting that literary studies occupies a middle ground with respect to standard English in the larger space of academic disciplines. More generally, our methodology can be applied to investigate the social positioning and development of language use across different domains (e.g. scientific disciplines, language varieties, registers). |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2503/ |
| https://www.aclweb.org/anthology/W19-2503 | |
| PWC | https://paperswithcode.com/paper/the-scientization-of-literary-study |
| Repo | |
| Framework | |
Reciprocal Multi-Layer Subspace Learning for Multi-View Clustering
| Title | Reciprocal Multi-Layer Subspace Learning for Multi-View Clustering |
| Authors | Ruihuang Li, Changqing Zhang, Huazhu Fu, Xi Peng, Tianyi Zhou, Qinghua Hu |
| Abstract | Multi-view clustering is a long-standing important research topic, however, remains challenging when handling high-dimensional data and simultaneously exploring the consistency and complementarity of different views. In this work, we present a novel Reciprocal Multi-layer Subspace Learning (RMSL) algorithm for multi-view clustering, which is composed of two main components: Hierarchical Self-Representative Layers (HSRL), and Backward Encoding Networks (BEN). Specifically, HSRL constructs reciprocal multi-layer subspace representations linked with a latent representation to hierarchically recover the underlying low-dimensional subspaces in which the high-dimensional data lie; BEN explores complex relationships among different views and implicitly enforces the subspaces of all views to be consistent with each other and more separable. The latent representation flexibly encodes complementary information from multiple views and depicts data more comprehensively. Our model can be efficiently optimized by an alternating optimization scheme. Extensive experiments on benchmark datasets show the superiority of RMSL over other state-of-the-art clustering methods. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Li_Reciprocal_Multi-Layer_Subspace_Learning_for_Multi-View_Clustering_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_Reciprocal_Multi-Layer_Subspace_Learning_for_Multi-View_Clustering_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/reciprocal-multi-layer-subspace-learning-for |
| Repo | |
| Framework | |
Incorporating Graph Attention Mechanism into Knowledge Graph Reasoning Based on Deep Reinforcement Learning
| Title | Incorporating Graph Attention Mechanism into Knowledge Graph Reasoning Based on Deep Reinforcement Learning |
| Authors | Heng Wang, Shuangyin Li, Rong Pan, Mingzhi Mao |
| Abstract | Knowledge Graph (KG) reasoning aims at finding reasoning paths for relations, in order to solve the problem of incompleteness in KG. Many previous path-based methods like PRA and DeepPath suffer from lacking memory components, or stuck in training. Therefore, their performances always rely on well-pretraining. In this paper, we present a deep reinforcement learning based model named by AttnPath, which incorporates LSTM and Graph Attention Mechanism as the memory components. We define two metrics, Mean Selection Rate (MSR) and Mean Replacement Rate (MRR), to quantitatively measure how difficult it is to learn the query relations, and take advantages of them to fine-tune the model under the framework of reinforcement learning. Meanwhile, a novel mechanism of reinforcement learning is proposed by forcing an agent to walk forward every step to avoid the agent stalling at the same entity node constantly. Based on this operation, the proposed model not only can get rid of the pretraining process, but also achieves state-of-the-art performance comparing with the other models. We test our model on FB15K-237 and NELL-995 datasets with different tasks. Extensive experiments show that our model is effective and competitive with many current state-of-the-art methods, and also performs well in practice. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1264/ |
| https://www.aclweb.org/anthology/D19-1264 | |
| PWC | https://paperswithcode.com/paper/incorporating-graph-attention-mechanism-into |
| Repo | |
| Framework | |
Proceedings of the 8th Workshop on NLP for Computer Assisted Language Learning
| Title | Proceedings of the 8th Workshop on NLP for Computer Assisted Language Learning |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6300/ |
| https://www.aclweb.org/anthology/W19-6300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-8th-workshop-on-nlp-for |
| Repo | |
| Framework | |
EV-Gait: Event-Based Robust Gait Recognition Using Dynamic Vision Sensors
| Title | EV-Gait: Event-Based Robust Gait Recognition Using Dynamic Vision Sensors |
| Authors | Yanxiang Wang, Bowen Du, Yiran Shen, Kai Wu, Guangrong Zhao, Jianguo Sun, Hongkai Wen |
| Abstract | In this paper, we introduce a new type of sensing modality, the Dynamic Vision Sensors (Event Cameras), for the task of gait recognition. Compared with the traditional RGB sensors, the event cameras have many unique advantages such as ultra low resources consumption, high temporal resolution and much larger dynamic range. However, those cameras only produce noisy and asynchronous events of intensity changes rather than frames, where conventional vision-based gait recognition algorithms can’t be directly applied. To address this, we propose a new Event-based Gait Recognition (EV-Gait) approach, which exploits motion consistency to effectively remove noise, and uses a deep neural network to recognise gait from the event streams. To evaluate the performance of EV-Gait, we collect two event-based gait datasets, one from real-world experiments and the other by converting the publicly available RGB gait recognition benchmark CASIA-B. Extensive experiments show that EV-Gait can get nearly 96% recognition accuracy in the real-world settings, while on the CASIA-B benchmark it achieves comparable performance with state-of-the-art RGB-based gait recognition approaches. |
| Tasks | Gait Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_EV-Gait_Event-Based_Robust_Gait_Recognition_Using_Dynamic_Vision_Sensors_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_EV-Gait_Event-Based_Robust_Gait_Recognition_Using_Dynamic_Vision_Sensors_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/ev-gait-event-based-robust-gait-recognition |
| Repo | |
| Framework | |
A Parametric Approach to Implemented Analyses: Valence-changing Morphology in the LinGO Grammar Matrix
| Title | A Parametric Approach to Implemented Analyses: Valence-changing Morphology in the LinGO Grammar Matrix |
| Authors | Christian Curtis |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8513/ |
| https://www.aclweb.org/anthology/W19-8513 | |
| PWC | https://paperswithcode.com/paper/a-parametric-approach-to-implemented-analyses |
| Repo | |
| Framework | |
Gradual Argumentation Evaluation for Stance Aggregation in Automated Fake News Detection
| Title | Gradual Argumentation Evaluation for Stance Aggregation in Automated Fake News Detection |
| Authors | Neema Kotonya, Francesca Toni |
| Abstract | Stance detection plays a pivot role in fake news detection. The task involves determining the point of view or stance {–} for or against {–} a text takes towards a claim. One very important stage in employing stance detection for fake news detection is the aggregation of multiple stance labels from different text sources in order to compute a prediction for the veracity of a claim. Typically, aggregation is treated as a credibility-weighted average of stance predictions. In this work, we take the novel approach of applying, for aggregation, a gradual argumentation semantics to bipolar argumentation frameworks mined using stance detection. Our empirical evaluation shows that our method results in more accurate veracity predictions. |
| Tasks | Fake News Detection, Stance Detection |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4518/ |
| https://www.aclweb.org/anthology/W19-4518 | |
| PWC | https://paperswithcode.com/paper/gradual-argumentation-evaluation-for-stance |
| Repo | |
| Framework | |
Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations
| Title | Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations |
| Authors | Bushra Algotiml, AbdelRahim Elmadany, Walid Magdy |
| Abstract | Speech acts are the actions that a speaker intends when performing an utterance within conversations. In this paper, we proposed speech act classification for asynchronous conversations on Twitter using multiple machine learning methods including SVM and deep neural networks. We applied the proposed methods on the ArSAS tweets dataset. The obtained results show that superiority of deep learning methods compared to SVMs, where Bi-LSTM managed to achieve an accuracy of 87.5{%} and a macro-averaged F1 score 61.5{%}. We believe that our results are the first to be reported on the task of speech-act recognition for asynchronous conversations on Arabic Twitter. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4620/ |
| https://www.aclweb.org/anthology/W19-4620 | |
| PWC | https://paperswithcode.com/paper/arabic-tweet-act-speech-act-recognition-for |
| Repo | |
| Framework | |
