Paper Group NAWR 6
EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis. PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs. SupWSD: A Flexible Toolkit for Supervised Word Sense Disambiguation. Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs …
EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis
| Title | EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis |
| Authors | Sven Buechel, Udo Hahn |
| Abstract | We describe EmoBank, a corpus of 10k English sentences balancing multiple genres, which we annotated with dimensional emotion metadata in the Valence-Arousal-Dominance (VAD) representation format. EmoBank excels with a bi-perspectival and bi-representational design. On the one hand, we distinguish between writer{'}s and reader{'}s emotions, on the other hand, a subset of the corpus complements dimensional VAD annotations with categorical ones based on Basic Emotions. We find evidence for the supremacy of the reader{'}s perspective in terms of IAA and rating intensity, and achieve close-to-human performance when mapping between dimensional and categorical formats. |
| Tasks | Emotion Recognition, Sentiment Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2092/ |
| https://www.aclweb.org/anthology/E17-2092 | |
| PWC | https://paperswithcode.com/paper/emobank-studying-the-impact-of-annotation |
| Repo | https://github.com/JULIELab/EmoBank |
| Framework | none |
PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
| Title | PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs |
| Authors | Yunbo Wang Mingsheng Long Jianmin Wang Zhifeng Gao Philip S. Yu |
| Abstract | The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical frames, where spatial appearances and temporal variations are two crucial structures. This paper models these structures by presenting a predictive recurrent neural network (PredRNN). This architecture is enlightened by the idea that spatiotemporal predictive learning should memorize both spatial appearances and temporal variations in a unified memory pool. Concretely, memory states are no longer constrained inside each LSTM unit. Instead, they are allowed to zigzag in two directions: across stacked RNN layers vertically and through all RNN states horizontally. The core of this network is a new Spatiotemporal LSTM (ST-LSTM) unit that extracts and memorizes spatial and temporal representations simultaneously. PredRNN achieves the state-of-the-art prediction performance on three video prediction datasets and is a more general framework, that can be easily extended to other predictive learning tasks by integrating with other architectures. |
| Tasks | Video Prediction |
| Published | 2017-12-01 |
| URL | https://papers.nips.cc/paper/6689-predrnn-recurrent-neural-networks-for-predictive-learning-using-spatiotemporal-lstms |
| https://papers.nips.cc/paper/6689-predrnn-recurrent-neural-networks-for-predictive-learning-using-spatiotemporal-lstms | |
| PWC | https://paperswithcode.com/paper/predrnn-recurrent-neural-networks-for-1 |
| Repo | https://github.com/igloooo/weather-forecasting-video-prediction |
| Framework | pytorch |
SupWSD: A Flexible Toolkit for Supervised Word Sense Disambiguation
| Title | SupWSD: A Flexible Toolkit for Supervised Word Sense Disambiguation |
| Authors | Pap, Simone rea, Aless Raganato, ro, Claudio Delli Bovi |
| Abstract | In this demonstration we present SupWSD, a Java API for supervised Word Sense Disambiguation (WSD). This toolkit includes the implementation of a state-of-the-art supervised WSD system, together with a Natural Language Processing pipeline for preprocessing and feature extraction. Our aim is to provide an easy-to-use tool for the research community, designed to be modular, fast and scalable for training and testing on large datasets. The source code of SupWSD is available at \url{http://github.com/SI3P/SupWSD}. |
| Tasks | Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-2018/ |
| https://www.aclweb.org/anthology/D17-2018 | |
| PWC | https://paperswithcode.com/paper/supwsd-a-flexible-toolkit-for-supervised-word |
| Repo | https://github.com/SI3P/SupWSD |
| Framework | none |
Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs
| Title | Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs |
| Authors | Fern Alva-Manchego, o, Joachim Bingel, Gustavo Paetzold, Carolina Scarton, Lucia Specia |
| Abstract | Current research in text simplification has been hampered by two central problems: (i) the small amount of high-quality parallel simplification data available, and (ii) the lack of explicit annotations of simplification operations, such as deletions or substitutions, on existing data. While the recently introduced Newsela corpus has alleviated the first problem, simplifications still need to be learned directly from parallel text using black-box, end-to-end approaches rather than from explicit annotations. These complex-simple parallel sentence pairs often differ to such a high degree that generalization becomes difficult. End-to-end models also make it hard to interpret what is actually learned from data. We propose a method that decomposes the task of TS into its sub-problems. We devise a way to automatically identify operations in a parallel corpus and introduce a sequence-labeling approach based on these annotations. Finally, we provide insights on the types of transformations that different approaches can model. |
| Tasks | Machine Translation, Sentence Compression, Text Simplification |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1030/ |
| https://www.aclweb.org/anthology/I17-1030 | |
| PWC | https://paperswithcode.com/paper/learning-how-to-simplify-from-explicit |
| Repo | https://github.com/ghpaetzold/massalign |
| Framework | none |
Deep Convolutional Neural Networks for Thermal Infrared Object Tracking
| Title | Deep Convolutional Neural Networks for Thermal Infrared Object Tracking |
| Authors | QiaoLiu, Xiaohuan Lu, Zhenyu He, Chunkai Zhang, WenSheng Chen |
| Abstract | Unlike the visual object tracking, thermal infrared object tracking can track a target object in total darkness. Therefore, it has broad applications, such as in rescue and video surveillance at night. However, there are few studies in this field mainly because thermal infrared images have several unwanted attributes, which make it difficult to obtain the discriminative features of the target. Considering the powerful representational ability of convolutional neural networks and their successful application in visual tracking, we transfer the pre-trained convolutional neural networks based on visible images to thermal infrared tracking. We observe that the features from the fully-connected layer are not suitable for thermal infrared tracking due to the lack of spatial information of the target, while the features from the convolution layers are. Besides, the features from a single convolution layer are not robust to various challenges. Based on this observation, we propose a correlation filter based ensemble tracker with multi-layer convolutional features for thermal infrared tracking (MCFTS). Firstly, we use pre-trained convolutional neural networks to extract the features of the multiple convolution layers of the thermal infrared target. Then, a correlation filter is used to construct multiple weak trackers with the corresponding convolution layer features. These weak trackers give the response maps of the target’s location. Finally, we propose an ensemble method that coalesces these response maps to get a stronger one. Furthermore, a simple but effective scale estimation strategy is exploited to boost the tracking accuracy. To evaluate the performance of the proposed tracker, we carry out experiments on two thermal infrared tracking benchmarks: VOT-TIR 2015 and VOT-TIR 2016. The experimental results demonstrate that our tracker is effective and achieves promising performance. |
| Tasks | Object Tracking, Thermal Infrared Object Tracking, Visual Object Tracking, Visual Tracking |
| Published | 2017-10-15 |
| URL | https://www.sciencedirect.com/science/article/abs/pii/S0950705117303544 |
| https://www.researchgate.net/publication/318714772_Deep_Convolutional_Neural_Networks_for_Thermal_Infrared_Object_Tracking | |
| PWC | https://paperswithcode.com/paper/deep-convolutional-neural-networks-for-12 |
| Repo | https://github.com/QiaoLiuHit/MCFTS |
| Framework | none |
The BECauSE Corpus 2.0: Annotating Causality and Overlapping Relations
| Title | The BECauSE Corpus 2.0: Annotating Causality and Overlapping Relations |
| Authors | Jesse Dunietz, Lori Levin, Jaime Carbonell |
| Abstract | Language of cause and effect captures an essential component of the semantics of a text. However, causal language is also intertwined with other semantic relations, such as temporal precedence and correlation. This makes it difficult to determine when causation is the primary intended meaning. This paper presents BECauSE 2.0, a new version of the BECauSE corpus with exhaustively annotated expressions of causal language, but also seven semantic relations that are frequently co-present with causation. The new corpus shows high inter-annotator agreement, and yields insights both about the linguistic expressions of causation and about the process of annotating co-present semantic relations. |
| Tasks | Decision Making |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0812/ |
| https://www.aclweb.org/anthology/W17-0812 | |
| PWC | https://paperswithcode.com/paper/the-because-corpus-20-annotating-causality |
| Repo | https://github.com/duncanka/BECauSE |
| Framework | none |
Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising
| Title | Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising |
| Authors | Bihan Wen, Yanjun Li, Luke Pfister, Yoram Bresler |
| Abstract | Recent works on adaptive sparse and low-rank signal modeling have demonstrated their usefulness, especially in image/video processing applications. While a patch-based sparse model imposes local structure, low-rankness of the grouped patches exploits non-local correlation. Applying either approach alone usually limits performance in various low-level vision tasks. In this work, we propose a novel video denoising method, based on an online tensor reconstruction scheme with a joint adaptive sparse and low-rank model, dubbed SALT. An efficient and unsupervised online unitary sparsifying transform learning method is introduced to impose adaptive sparsity on the fly. We develop an efficient 3D spatio-temporal data reconstruction framework based on the proposed online learning method, which exhibits low latency and can potentially handle streaming videos. To the best of our knowledge, this is the first work that combines adaptive sparsity and low-rankness for video denoising, and the first work of solving the proposed problem in an online fashion. We demonstrate video denoising results over commonly used videos from public datasets. Numerical experiments show that the proposed video denoising method outperforms competing methods. |
| Tasks | Denoising, Video Denoising |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Wen_Joint_Adaptive_Sparsity_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Wen_Joint_Adaptive_Sparsity_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/joint-adaptive-sparsity-and-low-rankness-on |
| Repo | https://github.com/wenbihan/salt_iccv2017 |
| Framework | none |
Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short
| Title | Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short |
| Authors | Jay Pujara, Eriq Augustine, Lise Getoor |
| Abstract | Knowledge graph (KG) embedding techniques use structured relationships between entities to learn low-dimensional representations of entities and relations. One prominent goal of these approaches is to improve the quality of knowledge graphs by removing errors and adding missing facts. Surprisingly, most embedding techniques have been evaluated on benchmark datasets consisting of dense and reliable subsets of human-curated KGs, which tend to be fairly complete and have few errors. In this paper, we consider the problem of applying embedding techniques to KGs extracted from text, which are often incomplete and contain errors. We compare the sparsity and unreliability of different KGs and perform empirical experiments demonstrating how embedding approaches degrade as sparsity and unreliability increase. |
| Tasks | Knowledge Graph Embeddings, Knowledge Graphs, Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1184/ |
| https://www.aclweb.org/anthology/D17-1184 | |
| PWC | https://paperswithcode.com/paper/sparsity-and-noise-where-knowledge-graph |
| Repo | https://github.com/linqs/pujara-emnlp17 |
| Framework | none |
Neural Att entive Session-based Recommendation
| Title | Neural Att entive Session-based Recommendation |
| Authors | Jing Li, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Tao Lian, Jun Ma |
| Abstract | Given e-commerce scenarios that user profiles are invisible, sessionbased recommendation is proposed to generate recommendation results from short sessions. Previous work only considers the user’s sequential behavior in the current session, whereas the user’s main purpose in the current session is not emphasized. In this paper, we propose a novel neural networks framework, i.e., Neural Attentive Recommendation Machine (NARM), to tackle this problem. Specifically, we explore a hybrid encoder with an attention mechanism to model the user’s sequential behavior and capture the user’s main purpose in the current session, which are combined as a unified session representation later. We then compute the recommendation scores for each candidate item with a bi-linear matching scheme based on this unified session representation. We train NARM by jointly learning the item and session representations as well as their matchings. We carried out extensive experiments on two benchmark datasets. Our experimental results show that NARM outperforms state-of-the-art baselines on both datasets. Furthermore, we also find that NARM achieves a significant improvement on long sessions, which demonstrates its advantages in modeling the user’s sequential behavior and main purpose simultaneously |
| Tasks | Session-Based Recommendations |
| Published | 2017-11-03 |
| URL | https://arxiv.org/abs/1711.04725 |
| https://arxiv.org/pdf/1711.04725.pdf | |
| PWC | https://paperswithcode.com/paper/neural-att-entive-session-based |
| Repo | https://github.com/lijingsdu/sessionRec_NARM |
| Framework | none |
ENCASE: An ENsemble ClASsifiEr for ECG classification using expert features and deep neural networks
| Title | ENCASE: An ENsemble ClASsifiEr for ECG classification using expert features and deep neural networks |
| Authors | Shenda Hong, Meng Wu, Yuxi Zhou, Qingyun Wang, Junyuan Shang, Hongyan Li, Junqing Xie |
| Abstract | We propose ENCASE to combine expert features and DNNs (Deep Neural Networks) together for ECG classification. We first explore and implement expert features from statistical area, signal processing area and medical area. Then, we build DNNs to automatically extract deep features. Besides, we propose a new algorithm to find the most representative wave (called centerwave) among long ECG record, and extract features from centerwave. Finally, we combine these features together and put them into ensemble classifiers. Experiment on 4-class ECG data classification reports 0.84 F1 score, which is much better than any of the single model. |
| Tasks | Arrhythmia Detection, ECG Classification, Time Series Classification |
| Published | 2017-09-24 |
| URL | http://prucka.com/2017CinC/pdf/178-245.pdf |
| http://prucka.com/2017CinC/pdf/178-245.pdf | |
| PWC | https://paperswithcode.com/paper/encase-an-ensemble-classifier-for-ecg |
| Repo | https://github.com/hsd1503/ENCASE |
| Framework | tf |
Designing Illuminant Spectral Power Distributions for Surface Classification
| Title | Designing Illuminant Spectral Power Distributions for Surface Classification |
| Authors | Henryk Blasinski, Joyce Farrell, Brian Wandell |
| Abstract | There are many scientific, medical and industrial imaging applications where users have full control of the scene illumination and color reproduction is not the primary objective For example, it is possible to co-design sensors and spectral illumination in order to classify and detect changes in biological tissues, organic and inorganic materials, and object surface properties. In this paper, we propose two different approaches to illuminant spectrum selection for surface classification. In the supervised framework we formulate a biconvex optimization problem where we alternate between optimizing support vector classifier weights and optimal illuminants. We also describe a sparse Principal Component Analysis (PCA) dimensionality reduction approach that can be used with unlabeled data. We efficiently solve the non-convex PCA problem using a convex relaxation and Alternating Direction Method of Multipliers (ADMM). We compare the classification accuracy of a monochrome imaging sensor with optimized illuminants to the classification accuracy of conventional RGB cameras with natural broadband illumination. |
| Tasks | Dimensionality Reduction |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Blasinski_Designing_Illuminant_Spectral_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Blasinski_Designing_Illuminant_Spectral_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/designing-illuminant-spectral-power |
| Repo | https://github.com/hblasins/optIll |
| Framework | none |
Position-aware Attention and Supervised Data Improve Slot Filling
| Title | Position-aware Attention and Supervised Data Improve Slot Filling |
| Authors | Yuhao Zhang, Victor Zhong, Danqi Chen, Gabor Angeli, Christopher D. Manning |
| Abstract | Organized relational knowledge in the form of {``}knowledge graphs{''} is important for many applications. However, the ability to populate knowledge bases with facts automatically extracted from documents has improved frustratingly slowly. This paper simultaneously addresses two issues that have held back prior work. We first propose an effective new model, which combines an LSTM sequence model with a form of entity position-aware attention that is better suited to relation extraction. Then we build TACRED, a large (119,474 examples) supervised relation extraction dataset obtained via crowdsourcing and targeted towards TAC KBP relations. The combination of better supervised data and a more appropriate high-capacity model enables much better relation extraction performance. When the model trained on this new dataset replaces the previous relation extraction component of the best TAC KBP 2015 slot filling system, its F1 score increases markedly from 22.2{%} to 26.7{%}. | |
| Tasks | Knowledge Base Population, Knowledge Graphs, Relation Extraction, Slot Filling |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1004/ |
| https://www.aclweb.org/anthology/D17-1004 | |
| PWC | https://paperswithcode.com/paper/position-aware-attention-and-supervised-data |
| Repo | https://github.com/yuhaozhang/tacred-relation |
| Framework | pytorch |
Abstract Meaning Representation Parsing using LSTM Recurrent Neural Networks
| Title | Abstract Meaning Representation Parsing using LSTM Recurrent Neural Networks |
| Authors | William Foland, James H. Martin |
| Abstract | |
| Tasks | Amr Parsing, Part-Of-Speech Tagging, Structured Prediction |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/papers/P17-1043/p17-1043 |
| https://www.aclweb.org/anthology/P17-1043 | |
| PWC | https://paperswithcode.com/paper/abstract-meaning-representation-parsing-using |
| Repo | https://github.com/BillFoland/daisyluAMR |
| Framework | tf |
Domain-Specific New Words Detection in Chinese
| Title | Domain-Specific New Words Detection in Chinese |
| Authors | Ao Chen, Maosong Sun |
| Abstract | With the explosive growth of Internet, more and more domain-specific environments appear, such as forums, blogs, MOOCs and etc. Domain-specific words appear in these areas and always play a critical role in the domain-specific NLP tasks. This paper aims at extracting Chinese domain-specific new words automatically. The extraction of domain-specific new words has two parts including both new words in this domain and the especially important words. In this work, we propose a joint statistical model to perform these two works simultaneously. Compared to traditional new words detection models, our model doesn{'}t need handcraft features which are labor intensive. Experimental results demonstrate that our joint model achieves a better performance compared with the state-of-the-art methods. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1005/ |
| https://www.aclweb.org/anthology/S17-1005 | |
| PWC | https://paperswithcode.com/paper/domain-specific-new-words-detection-in |
| Repo | https://github.com/dreamszl/dtopwords |
| Framework | none |
On Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks
| Title | On Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks |
| Authors | Songyang Zhang, Xiaoming Liu, Jun Xiao |
| Abstract | RNN-based approaches have achieved outstanding performance on action recognition with skeleton inputs. Currently these methods limit their inputs to coordinates of joints and improve the accuracy mainly by extending RNN models to spatial domains in various ways. While such models explore relations between different parts directly from joint coordinates, we provide a simple universal spatial modeling method perpendicular to the RNN model enhancement. Specifically, we select a set of simple geometric features, motivated by the evolution of previous work. With experiments on a 3-layer LSTM framework, we observe that the geometric relational features based on distances between joints and selected lines outperform other features and achieve state-of-art results on four datasets. Further, we show the sparsity of input gate weights in the first LSTM layer trained by geometric features and demonstrate that utilizing joint-line distances as input require less data for training. |
| Tasks | Skeleton Based Action Recognition |
| Published | 2017-03-01 |
| URL | https://doi.org/10.1109/WACV.2017.24 |
| http://cvlab.cse.msu.edu/pdfs/Zhang_Liu_Xiao_WACV2017.pdf | |
| PWC | https://paperswithcode.com/paper/on-geometric-features-for-skeleton-based |
| Repo | https://github.com/Sy-Zhang/Geometric-Feature-Release |
| Framework | none |
