Paper Group NANR 183
Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization. Passive Diagnosis Incorporating the PHQ-4 for Depression and Anxiety. Annotating Information Structure in Italian: Characteristics and Cross-Linguistic Applicability of a QUD-Based Approach. ParallelDots at SemEval-2019 Task 3: Domain Adaptation with feature embeddings …
Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization
| Title | Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization |
| Authors | Manling Li, Lingyu Zhang, Heng Ji, Richard J. Radke |
| Abstract | Transcripts of natural, multi-person meetings differ significantly from documents like news articles, which can make Natural Language Generation models for generating summaries unfocused. We develop an abstractive meeting summarizer from both videos and audios of meeting recordings. Specifically, we propose a multi-modal hierarchical attention across three levels: segment, utterance and word. To narrow down the focus into topically-relevant segments, we jointly model topic segmentation and summarization. In addition to traditional text features, we introduce new multi-modal features derived from visual focus of attention, based on the assumption that the utterance is more important if the speaker receives more attention. Experiments show that our model significantly outperforms the state-of-the-art with both BLEU and ROUGE measures. |
| Tasks | Meeting Summarization, Text Generation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1210/ |
| https://www.aclweb.org/anthology/P19-1210 | |
| PWC | https://paperswithcode.com/paper/keep-meeting-summaries-on-topic-abstractive |
| Repo | |
| Framework | |
Passive Diagnosis Incorporating the PHQ-4 for Depression and Anxiety
| Title | Passive Diagnosis Incorporating the PHQ-4 for Depression and Anxiety |
| Authors | Fionn Delahunty, Robert Johansson, Mihael Arcan |
| Abstract | Depression and anxiety are the two most prevalent mental health disorders worldwide, impacting the lives of millions of people each year. In this work, we develop and evaluate a multilabel, multidimensional deep neural network designed to predict PHQ-4 scores based on individuals written text. Our system outperforms random baseline metrics and provides a novel approach to how we can predict psychometric scores from written text. Additionally, we explore how this architecture can be applied to analyse social media data. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3205/ |
| https://www.aclweb.org/anthology/W19-3205 | |
| PWC | https://paperswithcode.com/paper/passive-diagnosis-incorporating-the-phq-4-for |
| Repo | |
| Framework | |
Annotating Information Structure in Italian: Characteristics and Cross-Linguistic Applicability of a QUD-Based Approach
| Title | Annotating Information Structure in Italian: Characteristics and Cross-Linguistic Applicability of a QUD-Based Approach |
| Authors | Kordula De Kuthy, Lisa Brunetti, Marta Berardi |
| Abstract | We present a discourse annotation study, in which an annotation method based on Questions under Discussion (QuD) is applied to Italian data. The results of our inter-annotator agreement analysis show that the QUD-based approach, originally spelled out for English and German, can successfully be transferred cross-linguistically, supporting good agreement for the annotation of central information structure notions such as focus and non-at-issueness. Our annotation and interannotator agreement study on Italian authentic data confirms the cross-linguistic applicability of the QuD-based approach. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4014/ |
| https://www.aclweb.org/anthology/W19-4014 | |
| PWC | https://paperswithcode.com/paper/annotating-information-structure-in-italian |
| Repo | |
| Framework | |
ParallelDots at SemEval-2019 Task 3: Domain Adaptation with feature embeddings for Contextual Emotion Analysis
| Title | ParallelDots at SemEval-2019 Task 3: Domain Adaptation with feature embeddings for Contextual Emotion Analysis |
| Authors | Akansha Jain, Ishita Aggarwal, Ankit Singh |
| Abstract | This paper describes our proposed system {&} experiments performed to detect contextual emotion in texts for SemEval 2019 Task 3. We exploit sentiment information, syntactic patterns {&} semantic relatedness to capture diverse aspects of the text. Word level embeddings such as Glove, FastText, Emoji along with sentence level embeddings like Skip-Thought, DeepMoji {&} Unsupervised Sentiment Neuron were used as input features to our architecture. We democratize the learning using ensembling of models with different parameters to produce the final output. This paper discusses comparative analysis of the significance of these embeddings and our approach for the task. |
| Tasks | Domain Adaptation, Emotion Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2029/ |
| https://www.aclweb.org/anthology/S19-2029 | |
| PWC | https://paperswithcode.com/paper/paralleldots-at-semeval-2019-task-3-domain |
| Repo | |
| Framework | |
THU_NGN at SemEval-2019 Task 3: Dialog Emotion Classification using Attentional LSTM-CNN
| Title | THU_NGN at SemEval-2019 Task 3: Dialog Emotion Classification using Attentional LSTM-CNN |
| Authors | Suyu Ge, Tao Qi, Chuhan Wu, Yongfeng Huang |
| Abstract | With the development of the Internet, dialog systems are widely used in online platforms to provide personalized services for their users. It is important to understand the emotions through conversations to improve the quality of dialog systems. To facilitate the researches on dialog emotion recognition, the SemEval-2019 Task 3 named EmoContext is proposed. This task aims to classify the emotions of user utterance along with two short turns of dialogues into four categories. In this paper, we propose an attentional LSTM-CNN model to participate in this shared task. We use a combination of convolutional neural networks and long-short term neural networks to capture both local and long-distance contextual information in conversations. In addition, we apply attention mechanism to recognize and attend to important words within conversations. Besides, we propose to use ensemble strategies by combing the variants of our model with different pre-trained word embeddings via weighted voting. Our model achieved 0.7542 micro-F1 score in the final test data, ranking 15{^{}}th out of 165 teams. |
| Tasks | Emotion Classification, Emotion Recognition, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2059/ |
| https://www.aclweb.org/anthology/S19-2059 | |
| PWC | https://paperswithcode.com/paper/thu_ngn-at-semeval-2019-task-3-dialog-emotion |
| Repo | |
| Framework | |
Radial Basis Feature Transformation to Arm CNNs Against Adversarial Attacks
| Title | Radial Basis Feature Transformation to Arm CNNs Against Adversarial Attacks |
| Authors | Saeid Asgari Taghanaki, Shekoofeh Azizi, Ghassan Hamarneh |
| Abstract | The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations. To tackle this problem, in this paper, we propose a nonlinear radial basis convolutional feature transformation by learning the Mahalanobis distance function that maps the input convolutional features from the same class into tight clusters. In such a space, the clusters become compact and well-separated, which prevent small adversarial perturbations from forcing a sample to cross the decision boundary. We test the proposed method on three publicly available image classification and segmentation data-sets namely, MNIST, ISBI ISIC skin lesion, and NIH ChestX-ray14. We evaluate the robustness of our method to different gradient (targeted and untargeted) and non-gradient based attacks and compare it to several non-gradient masking defense strategies. Our results demonstrate that the proposed method can boost the performance of deep convolutional neural networks against adversarial perturbations without accuracy drop on clean data. |
| Tasks | Image Classification |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Hklgis0cF7 |
| https://openreview.net/pdf?id=Hklgis0cF7 | |
| PWC | https://paperswithcode.com/paper/radial-basis-feature-transformation-to-arm |
| Repo | |
| Framework | |
Graph-Based Semi-Supervised Learning for Natural Language Understanding
| Title | Graph-Based Semi-Supervised Learning for Natural Language Understanding |
| Authors | Zimeng Qiu, Eunah Cho, Xiaochun Ma, William Campbell |
| Abstract | Semi-supervised learning is an efficient method to augment training data automatically from unlabeled data. Development of many natural language understanding (NLU) applications has a challenge where unlabeled data is relatively abundant while labeled data is rather limited. In this work, we propose transductive graph-based semi-supervised learning models as well as their inductive variants for NLU. We evaluate the approach{'}s applicability using publicly available NLU data and models. In order to find similar utterances and construct a graph, we use a paraphrase detection model. Results show that applying the inductive graph-based semi-supervised learning can improve the error rate of the NLU model by 5{%}. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5318/ |
| https://www.aclweb.org/anthology/D19-5318 | |
| PWC | https://paperswithcode.com/paper/graph-based-semi-supervised-learning-for-1 |
| Repo | |
| Framework | |
STAR-Caps: Capsule Networks with Straight-Through Attentive Routing
| Title | STAR-Caps: Capsule Networks with Straight-Through Attentive Routing |
| Authors | Karim Ahmed, Lorenzo Torresani |
| Abstract | Capsule networks have been shown to be powerful models for image classification, thanks to their ability to represent and capture viewpoint variations of an object. However, the high computational complexity of capsule networks that stems from the recurrent dynamic routing poses a major drawback making their use for large-scale image classification challenging. In this work, we propose Star-Caps a capsule-based network that exploits a straight-through attentive routing to address the drawbacks of capsule networks. By utilizing attention modules augmented by differentiable binary routers, the proposed mechanism estimates the routing coefficients between capsules without recurrence, as opposed to prior related work. Subsequently, the routers utilize straight-through estimators to make binary decisions to either connect or disconnect the route between capsules, allowing stable and faster performance. The experiments conducted on several image classification datasets, including MNIST, SmallNorb, CIFAR-10, CIFAR-100, and ImageNet show that Star-Caps outperforms the baseline capsule networks. |
| Tasks | Image Classification |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9110-star-caps-capsule-networks-with-straight-through-attentive-routing |
| http://papers.nips.cc/paper/9110-star-caps-capsule-networks-with-straight-through-attentive-routing.pdf | |
| PWC | https://paperswithcode.com/paper/star-caps-capsule-networks-with-straight |
| Repo | |
| Framework | |
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts
| Title | Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-4000/ |
| https://www.aclweb.org/anthology/P19-4000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-57th-conference-of-the-3 |
| Repo | |
| Framework | |
GEval: Tool for Debugging NLP Datasets and Models
| Title | GEval: Tool for Debugging NLP Datasets and Models |
| Authors | Filip Grali{'n}ski, Anna Wr{'o}blewska, Tomasz Stanis{\l}awek, Kamil Grabowski, Tomasz G{'o}recki |
| Abstract | This paper presents a simple but general and effective method to debug the output of machine learning (ML) supervised models, including neural networks. The algorithm looks for features that lower the evaluation metric in such a way that it cannot be ascribed to chance (as measured by their p-values). Using this method {–} implemented as MLEval tool {–} you can find: (1) anomalies in test sets, (2) issues in preprocessing, (3) problems in the ML model itself. It can give you an insight into what can be improved in the datasets and/or the model. The same method can be used to compare ML models or different versions of the same model. We present the tool, the theory behind it and use cases for text-based models of various types. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4826/ |
| https://www.aclweb.org/anthology/W19-4826 | |
| PWC | https://paperswithcode.com/paper/geval-tool-for-debugging-nlp-datasets-and |
| Repo | |
| Framework | |
G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
| Title | G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space |
| Authors | Qi Meng, Shuxin Zheng, Huishuai Zhang, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu |
| Abstract | It is well known that neural networks with rectified linear units (ReLU) activation functions are positively scale-invariant. Conventional algorithms like stochastic gradient descent optimize the neural networks in the vector space of weights, which is, however, not positively scale-invariant. This mismatch may lead to problems during the optimization process. Then, a natural question is: \emph{can we construct a new vector space that is positively scale-invariant and sufficient to represent ReLU neural networks so as to better facilitate the optimization process }? In this paper, we provide our positive answer to this question. First, we conduct a formal study on the positive scaling operators which forms a transformation group, denoted as $\mathcal{G}$. We prove that the value of a path (i.e. the product of the weights along the path) in the neural network is invariant to positive scaling and the value vector of all the paths is sufficient to represent the neural networks under mild conditions. Second, we show that one can identify some basis paths out of all the paths and prove that the linear span of their value vectors (denoted as $\mathcal{G}$-space) is an invariant space with lower dimension under the positive scaling group. Finally, we design stochastic gradient descent algorithm in $\mathcal{G}$-space (abbreviated as $\mathcal{G}$-SGD) to optimize the value vector of the basis paths of neural networks with little extra cost by leveraging back-propagation. Our experiments show that $\mathcal{G}$-SGD significantly outperforms the conventional SGD algorithm in optimizing ReLU networks on benchmark datasets. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SyxfEn09Y7 |
| https://openreview.net/pdf?id=SyxfEn09Y7 | |
| PWC | https://paperswithcode.com/paper/g-sgd-optimizing-relu-neural-networks-in-its |
| Repo | |
| Framework | |
A Novel System for Extractive Clinical Note Summarization using EHR Data
| Title | A Novel System for Extractive Clinical Note Summarization using EHR Data |
| Authors | Jennifer Liang, Ching-Huei Tsou, Ananya Poddar |
| Abstract | While much data within a patient{'}s electronic health record (EHR) is coded, crucial information concerning the patient{'}s care and management remain buried in unstructured clinical notes, making it difficult and time-consuming for physicians to review during their usual clinical workflow. In this paper, we present our clinical note processing pipeline, which extends beyond basic medical natural language processing (NLP) with concept recognition and relation detection to also include components specific to EHR data, such as structured data associated with the encounter, sentence-level clinical aspects, and structures of the clinical notes. We report on the use of this pipeline in a disease-specific extractive text summarization task on clinical notes, focusing primarily on progress notes by physicians and nurse practitioners. We show how the addition of EHR-specific components to the pipeline resulted in an improvement in our overall system performance and discuss the potential impact of EHR-specific components on other higher-level clinical NLP tasks. |
| Tasks | Text Summarization |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1906/ |
| https://www.aclweb.org/anthology/W19-1906 | |
| PWC | https://paperswithcode.com/paper/a-novel-system-for-extractive-clinical-note |
| Repo | |
| Framework | |
Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match
| Title | Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match |
| Authors | Amin Karbasi, Hamed Hassani, Aryan Mokhtari, Zebang Shen |
| Abstract | In this paper, we develop \scg~(\text{SCG}{$++$}), the first efficient variant of a conditional gradient method for maximizing a continuous submodular function subject to a convex constraint. Concretely, for a monotone and continuous DR-submodular function, \SCGPP achieves a tight $[(1-1/e)\OPT -\epsilon]$ solution while using $O(1/\epsilon^2)$ stochastic gradients and $O(1/\epsilon)$ calls to the linear optimization oracle. The best previously known algorithms either achieve a suboptimal $[(1/2)\OPT -\epsilon]$ solution with $O(1/\epsilon^2)$ stochastic gradients or the tight $[(1-1/e)\OPT -\epsilon]$ solution with suboptimal $O(1/\epsilon^3)$ stochastic gradients. We further provide an information-theoretic lower bound to showcase the necessity of $\OM({1}/{\epsilon^2})$ stochastic oracle queries in order to achieve $[(1-1/e)\OPT -\epsilon]$ for monotone and DR-submodular functions. This result shows that our proposed \SCGPP enjoys optimality in terms of both approximation guarantee, i.e., $(1-1/e)$ approximation factor, and stochastic gradient evaluations, i.e., $O(1/\epsilon^2)$ calls to the stochastic oracle. By using stochastic continuous optimization as an interface, we also show that it is possible to obtain the $[(1-1/e)\OPT-\epsilon]$ tight approximation guarantee for maximizing a monotone but stochastic submodular set function subject to a general matroid constraint after at most $\mathcal{O}(n^2/\epsilon^2)$ calls to the stochastic function value, where $n$ is the number of elements in the ground set. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9466-stochastic-continuous-greedy-when-upper-and-lower-bounds-match |
| http://papers.nips.cc/paper/9466-stochastic-continuous-greedy-when-upper-and-lower-bounds-match.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-continuous-greedy-when-upper-and |
| Repo | |
| Framework | |
Accurate Human Gesture Sensing With Coarse-Grained RF Signatures
| Title | Accurate Human Gesture Sensing With Coarse-Grained RF Signatures |
| Authors | Hongyu Sun, Zheng Lu, Chin-Ling Chen, Jie Cao, Zhenjiang Tan |
| Abstract | RF-based gesture sensing and recognition has increasingly attracted intense academic and industrial interest due to its various device-free applications in daily life, such as elder monitoring, mobile games. State-of-the-art approaches achieved accurate gesture sensing by using fine-grained RF signatures (such as CSI, Doppler effect) while could not achieve the same accuracy with coarse-grained RF signatures such as received signal strength (RSS). This paper presents rRuler, a novel feature extraction method which aims to get fine-grained human gesture features with coarse-grained RSS readings, which means rought ruler could measure fine things. In order to further verify the performance of rRuler, we further propose rRuler-HMM, a hidden Markov model (HMM) based human gesture sensing and prediction algorithm which utilizes the features extracted by rRuler as input. We implemented rRuler and rRuler-HMM using TI Sensortag platforms and off-the-shelf (CTOS) laptops in an indoor environment, extensively performance evaluations show that rRuler and rRuler-HMM stand out for their low cost and high practicability, and the average gesture sensing accuracy of rRuler-HMM can achieve 95.71% in NLoS scenario and 97.14% in LoS scenario, respectively, which is similar to the performance that fine-grained RF signatures based approaches could achieve. |
| Tasks | RF-based Gesture Recognition |
| Published | 2019-06-17 |
| URL | https://doi.org/10.1109/ACCESS.2019.2923574 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8737967 | |
| PWC | https://paperswithcode.com/paper/accurate-human-gesture-sensing-with-coarse |
| Repo | |
| Framework | |
Optimizing Network Structure for 3D Human Pose Estimation
| Title | Optimizing Network Structure for 3D Human Pose Estimation |
| Authors | Hai Ci, Chunyu Wang, Xiaoxuan Ma, Yizhou Wang |
| Abstract | A human pose is naturally represented as a graph where the joints are the nodes and the bones are the edges. So it is natural to apply Graph Convolutional Network (GCN) to estimate 3D poses from 2D poses. In this work, we propose a generic formulation where both GCN and Fully Connected Network (FCN) are its special cases. From this formulation, we discover that GCN has limited representation power when used for estimating 3D poses. We overcome the limitation by introducing Locally Connected Network (LCN) which is naturally implemented by this generic formulation. It notably improves the representation capability over GCN. In addition, since every joint is only connected to a few joints in its neighborhood, it has strong generalization power. The experiments on public datasets show it: (1) outperforms the state-of-the-arts; (2) is less data hungry than alternative models; (3) generalizes well to unseen actions and datasets. |
| Tasks | 3D Human Pose Estimation, Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Ci_Optimizing_Network_Structure_for_3D_Human_Pose_Estimation_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Ci_Optimizing_Network_Structure_for_3D_Human_Pose_Estimation_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-network-structure-for-3d-human |
| Repo | |
| Framework | |
