Paper Group NANR 123
Globally optimal score-based learning of directed acyclic graphs in high-dimensions. YNU-junyi in BioNLP-OST 2019: Using CNN-LSTM Model with Embeddings for SeeDev Binary Event Extraction. JCTDHS at SemEval-2019 Task 5: Detection of Hate Speech in Tweets using Deep Learning Methods, Character N-gram Features, and Preprocessing Methods. Modeling Clau …
Globally optimal score-based learning of directed acyclic graphs in high-dimensions
| Title | Globally optimal score-based learning of directed acyclic graphs in high-dimensions |
| Authors | Bryon Aragam, Arash Amini, Qing Zhou |
| Abstract | We prove that $\Omega(s\log p)$ samples suffice to learn a sparse Gaussian directed acyclic graph (DAG) from data, where $s$ is the maximum Markov blanket size. This improves upon recent results that require $\Omega(s^{4}\log p)$ samples in the equal variance case. To prove this, we analyze a popular score-based estimator that has been the subject of extensive empirical inquiry in recent years and is known to achieve state-of-the-art results. Furthermore, the approach we study does not require strong assumptions such as faithfulness that existing theory for score-based learning crucially relies on. The resulting estimator is based around a difficult nonconvex optimization problem, and its analysis may be of independent interest given recent interest in nonconvex optimization in machine learning. Our analysis overcomes the drawbacks of existing theoretical analyses, which either fail to guarantee structure consistency in high-dimensions (i.e. learning the correct graph with high probability), or rely on restrictive assumptions. In contrast, we give explicit finite-sample bounds that are valid in the important $p\gg n$ regime. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8695-globally-optimal-score-based-learning-of-directed-acyclic-graphs-in-high-dimensions |
| http://papers.nips.cc/paper/8695-globally-optimal-score-based-learning-of-directed-acyclic-graphs-in-high-dimensions.pdf | |
| PWC | https://paperswithcode.com/paper/globally-optimal-score-based-learning-of |
| Repo | |
| Framework | |
YNU-junyi in BioNLP-OST 2019: Using CNN-LSTM Model with Embeddings for SeeDev Binary Event Extraction
| Title | YNU-junyi in BioNLP-OST 2019: Using CNN-LSTM Model with Embeddings for SeeDev Binary Event Extraction |
| Authors | Junyi Li, Xiaobing Zhou, Yuhang Wu, Bin Wang |
| Abstract | We participated in the BioNLP 2019 Open Shared Tasks: binary relation extraction of SeeDev task. The model was constructed us- ing convolutional neural networks (CNN) and long short term memory networks (LSTM). The full text information and context information were collected using the advantages of CNN and LSTM. The model consisted of two main modules: distributed semantic representation construction, such as word embedding, distance embedding and entity type embed- ding; and CNN-LSTM model. The F1 value of our participated task on the test data set of all types was 0.342. We achieved the second highest in the task. The results showed that our proposed method performed effectively in the binary relation extraction. |
| Tasks | Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5717/ |
| https://www.aclweb.org/anthology/D19-5717 | |
| PWC | https://paperswithcode.com/paper/ynu-junyi-in-bionlp-ost-2019-using-cnn-lstm |
| Repo | |
| Framework | |
JCTDHS at SemEval-2019 Task 5: Detection of Hate Speech in Tweets using Deep Learning Methods, Character N-gram Features, and Preprocessing Methods
| Title | JCTDHS at SemEval-2019 Task 5: Detection of Hate Speech in Tweets using Deep Learning Methods, Character N-gram Features, and Preprocessing Methods |
| Authors | Yaakov HaCohen-Kerner, Elyashiv Shayovitz, Shalom Rochman, Eli Cahn, Gal Didi, Ziv Ben-David |
| Abstract | In this paper, we describe our submissions to SemEval-2019 contest. We tackled subtask A - {}a binary classification where systems have to predict whether a tweet with a given target (women or immigrants) is hateful or not hateful{''}, a part of task 5 {}Multilingual detection of hate speech against immigrants and women in Twitter (hatEval){''}. Our system JCTDHS (Jerusalem College of Technology Detects Hate Speech) was developed for tweets written in English. We applied various supervised ML methods, various combinations of n-gram features using the TF-IDF scheme and. In addition, we applied various combinations of eight basic preprocessing methods. Our best submission was a special bidirectional RNN, which was ranked at the 11th position out of 68 submissions. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2075/ |
| https://www.aclweb.org/anthology/S19-2075 | |
| PWC | https://paperswithcode.com/paper/jctdhs-at-semeval-2019-task-5-detection-of |
| Repo | |
| Framework | |
Modeling Clausal Complementation for a Grammar Engineering Resource
| Title | Modeling Clausal Complementation for a Grammar Engineering Resource |
| Authors | Olga Zamaraeva, Kristen Howell, Emily M. Bender |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0105/ |
| https://www.aclweb.org/anthology/W19-0105 | |
| PWC | https://paperswithcode.com/paper/modeling-clausal-complementation-for-a |
| Repo | |
| Framework | |
A Unified Multi-task Adversarial Learning Framework for Pharmacovigilance Mining
| Title | A Unified Multi-task Adversarial Learning Framework for Pharmacovigilance Mining |
| Authors | Shweta Yadav, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya |
| Abstract | The mining of adverse drug reaction (ADR) has a crucial role in the pharmacovigilance. The traditional ways of identifying ADR are reliable but time-consuming, non-scalable and offer a very limited amount of ADR relevant information. With the unprecedented growth of information sources in the forms of social media texts (Twitter, Blogs, Reviews etc.), biomedical literature, and Electronic Medical Records (EMR), it has become crucial to extract the most pertinent ADR related information from these free-form texts. In this paper, we propose a neural network inspired multi- task learning framework that can simultaneously extract ADRs from various sources. We adopt a novel adversarial learning-based approach to learn features across multiple ADR information sources. Unlike the other existing techniques, our approach is capable to extracting fine-grained information (such as {}Indications{'}, {}Symptoms{'}, {}Finding{'}, {}Disease{'}, {`}Drug{'}) which provide important cues in pharmacovigilance. We evaluate our proposed approach on three publicly available real- world benchmark pharmacovigilance datasets, a Twitter dataset from PSB 2016 Social Me- dia Shared Task, CADEC corpus and Medline ADR corpus. Experiments show that our unified framework achieves state-of-the-art performance on individual tasks associated with the different benchmark datasets. This establishes the fact that our proposed approach is generic, which enables it to achieve high performance on the diverse datasets. | |
| Tasks | Multi-Task Learning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1516/ |
| https://www.aclweb.org/anthology/P19-1516 | |
| PWC | https://paperswithcode.com/paper/a-unified-multi-task-adversarial-learning |
| Repo | |
| Framework | |
Learning complex inflectional paradigms through blended gradient inputs
| Title | Learning complex inflectional paradigms through blended gradient inputs |
| Authors | Eric R. Rosen |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0111/ |
| https://www.aclweb.org/anthology/W19-0111 | |
| PWC | https://paperswithcode.com/paper/learning-complex-inflectional-paradigms |
| Repo | |
| Framework | |
When a `sport’ is a person and other issues for NMT of novels
| Title | When a `sport’ is a person and other issues for NMT of novels | |
| Authors | Arda Tezcan, Joke Daems, Lieve Macken |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7306/ |
| https://www.aclweb.org/anthology/W19-7306 | |
| PWC | https://paperswithcode.com/paper/when-a-sport-is-a-person-and-other-issues-for |
| Repo | |
| Framework | |
On the Statistical and Information Theoretical Characteristics of DNN Representations
| Title | On the Statistical and Information Theoretical Characteristics of DNN Representations |
| Authors | Daeyoung Choi, Wonjong Rhee, Kyungeun Lee, Changho Shin |
| Abstract | It has been common to argue or imply that a regularizer can be used to alter a statistical property of a hidden layer’s representation and thus improve generalization or performance of deep networks. For instance, dropout has been known to improve performance by reducing co-adaptation, and representational sparsity has been argued as a good characteristic because many data-generation processes have only a small number of factors that are independent. In this work, we analytically and empirically investigate the popular characteristics of learned representations, including correlation, sparsity, dead unit, rank, and mutual information, and disprove many of the \textit{conventional wisdom}. We first show that infinitely many Identical Output Networks (IONs) can be constructed for any deep network with a linear layer, where any invertible affine transformation can be applied to alter the layer’s representation characteristics. The existence of ION proves that the correlation characteristics of representation can be either low or high for a well-performing network. Extensions to ReLU layers are provided, too. Then, we consider sparsity, dead unit, and rank to show that only loose relationships exist among the three characteristics. It is shown that a higher sparsity or additional dead units do not imply a better or worse performance when the rank of representation is fixed. We also develop a rank regularizer and show that neither representation sparsity nor lower rank is helpful for improving performance even when the data-generation process has only a small number of independent factors. Mutual information $I(\z_l;\x)$ and $I(\z_l;\y)$ are investigated as well, and we show that regularizers can affect $I(\z_l;\x)$ and thus indirectly influence the performance. Finally, we explain how a rich set of regularizers can be used as a powerful tool for performance tuning. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryeyti0qKX |
| https://openreview.net/pdf?id=ryeyti0qKX | |
| PWC | https://paperswithcode.com/paper/on-the-statistical-and-information |
| Repo | |
| Framework | |
RelWalk – A Latent Variable Model Approach to Knowledge Graph Embedding
| Title | RelWalk – A Latent Variable Model Approach to Knowledge Graph Embedding |
| Authors | Danushka Bollegala, Huda Hakami, Yuichi Yoshida, Ken-ichi Kawarabayashi |
| Abstract | Knowledge Graph Embedding (KGE) is the task of jointly learning entity and relation embeddings for a given knowledge graph. Existing methods for learning KGEs can be seen as a two-stage process where (a) entities and relations in the knowledge graph are represented using some linear algebraic structures (embeddings), and (b) a scoring function is defined that evaluates the strength of a relation that holds between two entities using the corresponding relation and entity embeddings. Unfortunately, prior proposals for the scoring functions in the first step have been heuristically motivated, and it is unclear as to how the scoring functions in KGEs relate to the generation process of the underlying knowledge graph. To address this issue, we propose a generative account of the KGE learning task. Specifically, given a knowledge graph represented by a set of relational triples (h, R, t), where the semantic relation R holds between the two entities h (head) and t (tail), we extend the random walk model (Arora et al., 2016a) of word embeddings to KGE. We derive a theoretical relationship between the joint probability p(h, R, t) and the embeddings of h, R and t. Moreover, we show that marginal loss minimisation, a popular objective used by much prior work in KGE, follows naturally from the log-likelihood ratio maximisation under the probabilities estimated from the KGEs according to our theoretical relationship. We propose a learning objective motivated by the theoretical analysis to learn KGEs from a given knowledge graph. The KGEs learnt by our proposed method obtain state-of-the-art performance on FB15K237 and WN18RR benchmark datasets, providing empirical evidence in support of the theory. |
| Tasks | Entity Embeddings, Graph Embedding, Knowledge Graph Embedding, Word Embeddings |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SkxbDsR9Ym |
| https://openreview.net/pdf?id=SkxbDsR9Ym | |
| PWC | https://paperswithcode.com/paper/relwalk-a-latent-variable-model-approach-to |
| Repo | |
| Framework | |
A Comparative Analysis of Unsupervised Language Adaptation Methods
| Title | A Comparative Analysis of Unsupervised Language Adaptation Methods |
| Authors | Gil Rocha, Henrique Lopes Cardoso |
| Abstract | To overcome the lack of annotated resources in less-resourced languages, recent approaches have been proposed to perform unsupervised language adaptation. In this paper, we explore three recent proposals: Adversarial Training, Sentence Encoder Alignment and Shared-Private Architecture. We highlight the differences of these approaches in terms of unlabeled data requirements and capability to overcome additional domain shift in the data. A comparative analysis in two different tasks is conducted, namely on Sentiment Classification and Natural Language Inference. We show that adversarial training methods are more suitable when the source and target language datasets contain other variations in content besides the language shift. Otherwise, sentence encoder alignment methods are very effective and can yield scores on the target language that are close to the source language scores. |
| Tasks | Natural Language Inference, Sentiment Analysis |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6102/ |
| https://www.aclweb.org/anthology/D19-6102 | |
| PWC | https://paperswithcode.com/paper/a-comparative-analysis-of-unsupervised |
| Repo | |
| Framework | |
Real Time 3D Indoor Human Image Capturing Based on FMCW Radar
| Title | Real Time 3D Indoor Human Image Capturing Based on FMCW Radar |
| Authors | Hangqing Guo, Nan Zhang, Wenjun Shi, Saeed ALI-AlQarni, Shaoen Wu, Honggang Wang |
| Abstract | Compared to traditional camera-based computer vision and imaging, radio imaging based on wireless sensing does not require lighting and is friendly to privacy. This work proposes a deep learning radio imaging solution to visualize real-time user indoor activities. The proposed solution uses a low-power, MIMO Frequency Modulated Continuous Wave (FMCW) radar array to capture the reflected signals from human objects, and then constructs 3D human visualization through a serials of data analytics including: 1) a data preprocessing mechanism to remove background static reflection, 2) a signal processing mechanism to transfer received complex radar signals to a matrix containing spatial information, and 3) a deep learning scheme to filter abnormal frames resulted from rough surface of human body. This solution has been extensively evaluated in an indoor research lab. The constructed real-time human images are compared to the camera images captured at the same time. The results show that the proposed radio imaging solution can result in significantly high accuracy. IEEE publication: “Real-Time Indoor 3D Human Imaging Based on MIMO Radar Sensing” https://doi.org/10.1109/ICME.2019.00244 |
| Tasks | RF-based Pose Estimation |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1812.07099 |
| https://arxiv.org/pdf/1812.07099.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-3d-indoor-human-image-capturing |
| Repo | |
| Framework | |
ARS_NITK at MEDIQA 2019:Analysing Various Methods for Natural Language Inference, Recognising Question Entailment and Medical Question Answering System
| Title | ARS_NITK at MEDIQA 2019:Analysing Various Methods for Natural Language Inference, Recognising Question Entailment and Medical Question Answering System |
| Authors | Anumeha Agrawal, Rosa Anil George, Selvan Suntiha Ravi, Sowmya Kamath S, An Kumar, |
| Abstract | In this paper, we present three approaches for Natural Language Inference, Question Entailment Recognition and Question-Answering to improve domain-specific Information Retrieval. For addressing the NLI task, the UMLS Metathesaurus was used to find the synonyms of medical terms in given sentences, on which the InferSent model was trained to predict if the given sentence is an entailment, contradictory or neutral. We also introduce a new Extreme gradient boosting model built on PubMed embeddings to perform RQE. Further, a closed-domain Question Answering technique that uses Bi-directional LSTMs trained on the SquAD dataset to determine relevant ranks of answers for a given question is also discussed. |
| Tasks | Information Retrieval, Natural Language Inference, Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5059/ |
| https://www.aclweb.org/anthology/W19-5059 | |
| PWC | https://paperswithcode.com/paper/ars_nitk-at-mediqa-2019analysing-various |
| Repo | |
| Framework | |
Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition
| Title | Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition |
| Authors | Jiayu Dong, Huicheng Zheng, Lina Lian |
| Abstract | Sparse representation based methods have successfully put forward a general framework for robust face recognition through linear reconstruction and sparsity constraints. However, residual modeling in existing works is not yet robust enough when dealing with dense noise. In this paper, we aim at recognizing identities from faces with varying levels of noises of various forms such as occlusion, pixel corruption, or disguise, and take improving the fitting ability of the error model as the key to addressing this problem. To fully capture the characteristics of different noises, we propose a mixed model combining robust sparsity constraint and low-rank constraint, which can deal with random errors and structured errors simultaneously. For random noises such as pixel corruption, we adopt a Laplacian-uniform mixed function for fitting the error distribution. For structured errors like continuous occlusion or disguise, we utilize robust nuclear norm to constrain the rank of the error matrix. An effective iterative reweighted algorithm is then developed to solve the proposed model. Comprehensive experiments were conducted on several benchmark databases for robust face recognition, and the overall results demonstrate that our model is most robust against various kinds of noises, when compared with state-of-the-art methods. |
| Tasks | Face Recognition, Robust Face Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Dong_Low-Rank_Laplacian-Uniform_Mixed_Model_for_Robust_Face_Recognition_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Dong_Low-Rank_Laplacian-Uniform_Mixed_Model_for_Robust_Face_Recognition_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/low-rank-laplacian-uniform-mixed-model-for |
| Repo | |
| Framework | |
Written on Leaves or in Stones?: Computational Evidence for the Era of Authorship of Old Thai Prose
| Title | Written on Leaves or in Stones?: Computational Evidence for the Era of Authorship of Old Thai Prose |
| Authors | Attapol Rutherford, Santhawat Thanyawong |
| Abstract | We aim to provide computational evidence for the era of authorship of two important old Thai texts: Traiphumikatha and Pumratchatham. The era of authorship of these two books is still an ongoing debate among Thai literature scholars. Analysis of old Thai texts present a challenge for standard natural language processing techniques, due to the lack of corpora necessary for building old Thai word and syllable segmentation. We propose an accurate and interpretable model to classify each segment as one of the three eras of authorship (Sukhothai, Ayuddhya, or Rattanakosin) without sophisticated linguistic preprocessing. Contrary to previous hypotheses, our model suggests that both books were written during the Sukhothai era. Moreover, the second half of the Pumratchtham is uncharacteristic of the Sukhothai era, which may have confounded literary scholars in the past. Further, our model reveals that the most indicative linguistic changes stem from unidirectional grammaticalized words and polyfunctional words, which show up as most dominant features in the model. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4710/ |
| https://www.aclweb.org/anthology/W19-4710 | |
| PWC | https://paperswithcode.com/paper/written-on-leaves-or-in-stones-computational |
| Repo | |
| Framework | |
Transductive Learning for Zero-Shot Object Detection
| Title | Transductive Learning for Zero-Shot Object Detection |
| Authors | Shafin Rahman, Salman Khan, Nick Barnes |
| Abstract | Zero-shot object detection (ZSD) is a relatively unexplored research problem as compared to the conventional zero-shot recognition task. ZSD aims to detect previously unseen objects during inference. Existing ZSD works suffer from two critical issues: (a) large domain-shift between the source (seen) and target (unseen) domains since the two distributions are highly mismatched. (b) the learned model is biased against unseen classes, therefore in generalized ZSD settings, where both seen and unseen objects co-occur during inference, the learned model tends to misclassify unseen to seen categories. This brings up an important question: How effectively can a transductive setting address the aforementioned problems? To the best of our knowledge, we are the first to propose a transductive zero-shot object detection approach that convincingly reduces the domain-shift and model-bias against unseen classes. Our approach is based on a self-learning mechanism that uses a novel hybrid pseudo-labeling technique. It progressively updates learned model parameters by associating unlabeled data samples to their corresponding classes. During this process, our technique makes sure that knowledge that was previously acquired on the source domain is not forgotten. We report significant ‘relative’ improvements of 34.9% and 77.1% in terms of mAP and recall rates over the previous best inductive models on MSCOCO dataset. |
| Tasks | Object Detection, Zero-Shot Learning, Zero-Shot Object Detection |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Rahman_Transductive_Learning_for_Zero-Shot_Object_Detection_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Rahman_Transductive_Learning_for_Zero-Shot_Object_Detection_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/transductive-learning-for-zero-shot-object |
| Repo | |
| Framework | |
