Paper Group NANR 233
What Causes the Differences in Communication Styles? A Multicultural Study on Directness and Elaborateness. SenSALDO: Creating a Sentiment Lexicon for Swedish. UWB at SemEval-2018 Task 3: Irony detection in English tweets. Proceedings 14th Joint ACL - ISO Workshop on Interoperable Semantic Annotation. Proximal Graphical Event Models. Explicit Induc …
What Causes the Differences in Communication Styles? A Multicultural Study on Directness and Elaborateness
| Title | What Causes the Differences in Communication Styles? A Multicultural Study on Directness and Elaborateness |
| Authors | Juliana Miehle, Wolfgang Minker, Stefan Ultes |
| Abstract | |
| Tasks | Dialogue Management, Spoken Dialogue Systems |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1625/ |
| https://www.aclweb.org/anthology/L18-1625 | |
| PWC | https://paperswithcode.com/paper/what-causes-the-differences-in-communication |
| Repo | |
| Framework | |
SenSALDO: Creating a Sentiment Lexicon for Swedish
| Title | SenSALDO: Creating a Sentiment Lexicon for Swedish |
| Authors | Jacobo Rouces, Nina Tahmasebi, Lars Borin, Stian R{\o}dven Eide |
| Abstract | |
| Tasks | Opinion Mining, Sentiment Analysis, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1662/ |
| https://www.aclweb.org/anthology/L18-1662 | |
| PWC | https://paperswithcode.com/paper/sensaldo-creating-a-sentiment-lexicon-for |
| Repo | |
| Framework | |
UWB at SemEval-2018 Task 3: Irony detection in English tweets
| Title | UWB at SemEval-2018 Task 3: Irony detection in English tweets |
| Authors | Tom{'a}{\v{s}} Hercig |
| Abstract | This paper describes our system created for the SemEval-2018 Task 3: Irony detection in English tweets. Our strongly constrained system uses only the provided training data without any additional external resources. Our system is based on Maximum Entropy classifier and various features using parse tree, POS tags, and morphological features. Even without additional lexicons and word embeddings we achieved fourth place in Subtask A and seventh in Subtask B in terms of accuracy. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1084/ |
| https://www.aclweb.org/anthology/S18-1084 | |
| PWC | https://paperswithcode.com/paper/uwb-at-semeval-2018-task-3-irony-detection-in |
| Repo | |
| Framework | |
Proceedings 14th Joint ACL - ISO Workshop on Interoperable Semantic Annotation
| Title | Proceedings 14th Joint ACL - ISO Workshop on Interoperable Semantic Annotation |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4700/ |
| https://www.aclweb.org/anthology/W18-4700 | |
| PWC | https://paperswithcode.com/paper/proceedings-14th-joint-acl-iso-workshop-on |
| Repo | |
| Framework | |
Proximal Graphical Event Models
| Title | Proximal Graphical Event Models |
| Authors | Debarun Bhattacharjya, Dharmashankar Subramanian, Tian Gao |
| Abstract | Event datasets include events that occur irregularly over the timeline and are prevalent in numerous domains. We introduce proximal graphical event models (PGEM) as a representation of such datasets. PGEMs belong to a broader family of models that characterize relationships between various types of events, where the rate of occurrence of an event type depends only on whether or not its parents have occurred in the most recent history. The main advantage over the state of the art models is that they are entirely data driven and do not require additional inputs from the user, which can require knowledge of the domain such as choice of basis functions or hyperparameters in graphical event models. We theoretically justify our learning of optimal windows for parental history and the choices of parental sets, and the algorithm are sound and complete in terms of parent structure learning. We present additional efficient heuristics for learning PGEMs from data, demonstrating their effectiveness on synthetic and real datasets. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8036-proximal-graphical-event-models |
| http://papers.nips.cc/paper/8036-proximal-graphical-event-models.pdf | |
| PWC | https://paperswithcode.com/paper/proximal-graphical-event-models |
| Repo | |
| Framework | |
Explicit Induction Bias for Transfer Learning with Convolutional Networks
| Title | Explicit Induction Bias for Transfer Learning with Convolutional Networks |
| Authors | Xuhong LI, Yves GRANDVALET, Franck DAVOINE |
| Abstract | In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which are at least partially relevant for solving the target task, but would be difficult to extract from the limited amount of data available on the target task. However, besides the initialization with the pre-trained model and the early stopping, there is no mechanism in fine-tuning for retaining the features learned on the source task. In this paper, we investigate several regularization schemes that explicitly promote the similarity of the final solution with the initial model. We eventually recommend a simple $L^2$ penalty using the pre-trained model as a reference, and we show that this approach behaves much better than the standard scheme using weight decay on a partially frozen network. |
| Tasks | Transfer Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rye7IMbAZ |
| https://openreview.net/pdf?id=rye7IMbAZ | |
| PWC | https://paperswithcode.com/paper/explicit-induction-bias-for-transfer-learning |
| Repo | |
| Framework | |
Deep Material-Aware Cross-Spectral Stereo Matching
| Title | Deep Material-Aware Cross-Spectral Stereo Matching |
| Authors | Tiancheng Zhi, Bernardo R. Pires, Martial Hebert, Srinivasa G. Narasimhan |
| Abstract | Cross-spectral imaging provides strong benefits for recognition and detection tasks. Often, multiple cameras are used for cross-spectral imaging, thus requiring image alignment, or disparity estimation in a stereo setting. Increasingly, multi-camera cross-spectral systems are embedded in active RGBD devices (e.g. RGB-NIR cameras in Kinect and iPhone X). Hence, stereo matching also provides an opportunity to obtain depth without an active projector source. However, matching images from different spectral bands is challenging because of large appearance variations. We develop a novel deep learning framework to simultaneously transform images across spectral bands and estimate disparity. A material-aware loss function is incorporated within the disparity prediction network to handle regions with unreliable matching such as light sources, glass windshields and glossy surfaces. No depth supervision is required by our method. To evaluate our method, we used a vehicle-mounted RGB-NIR stereo system to collect 13.7 hours of video data across a range of areas in and around a city. Experiments show that our method achieves strong performance and reaches real-time speed. |
| Tasks | Disparity Estimation, Stereo Matching, Stereo Matching Hand |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhi_Deep_Material-Aware_Cross-Spectral_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhi_Deep_Material-Aware_Cross-Spectral_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-material-aware-cross-spectral-stereo |
| Repo | |
| Framework | |
Linearization of excitatory synaptic integration at no extra cost
| Title | Linearization of excitatory synaptic integration at no extra cost |
| Authors | Danielle Morel, Chandan Singh, William B Levy |
| Abstract | In many theories of neural computation, linearly summed synaptic activation is a pervasive assumption for the computations performed by individual neurons. Indeed, for certain nominally optimal models, linear summation is required. However, the biophysical mechanisms needed to produce linear summation may add to the energy-cost of neural processing. Thus, the benefits provided by linear summation may be outweighed by the energy-costs. Using voltage-gated conductances in a relatively simple neuron model, this paper quantifies the cost of linearizing dendritically localized synaptic activation. Different combinations of voltage-gated conductances were examined, and many are found to produce linearization; here, four of these models are presented. Comparing the energy-costs to a purely passive model, reveals minimal or even no additional costs in some cases. |
| Tasks | |
| Published | 2018-01-25 |
| URL | https://link.springer.com/article/10.1007/s10827-017-0673-5 |
| https://link.springer.com/article/10.1007/s10827-017-0673-5 | |
| PWC | https://paperswithcode.com/paper/linearization-of-excitatory-synaptic |
| Repo | |
| Framework | |
Modeling Input Uncertainty in Neural Network Dependency Parsing
| Title | Modeling Input Uncertainty in Neural Network Dependency Parsing |
| Authors | Rob van der Goot, Gertjan van Noord |
| Abstract | Recently introduced neural network parsers allow for new approaches to circumvent data sparsity issues by modeling character level information and by exploiting raw data in a semi-supervised setting. Data sparsity is especially prevailing when transferring to non-standard domains. In this setting, lexical normalization has often been used in the past to circumvent data sparsity. In this paper, we investigate whether these new neural approaches provide similar functionality as lexical normalization, or whether they are complementary. We provide experimental results which show that a separate normalization component improves performance of a neural network parser even if it has access to character level information as well as external word embeddings. Further improvements are obtained by a straightforward but novel approach in which the top-N best candidates provided by the normalization component are available to the parser. |
| Tasks | Dependency Parsing, Lexical Normalization, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1542/ |
| https://www.aclweb.org/anthology/D18-1542 | |
| PWC | https://paperswithcode.com/paper/modeling-input-uncertainty-in-neural-network |
| Repo | |
| Framework | |
HEI: Hunter Events Interface A platform based on services for the detection and reasoning about events
| Title | HEI: Hunter Events Interface A platform based on services for the detection and reasoning about events |
| Authors | Antonio Sorgente, Antonio Calabrese, Gianluca Coda, Paolo Vanacore, Francesco Mele |
| Abstract | In this paper we present the definition and implementation of the Hunter Events Interface (HEI) System. The HEI System is a system for events annotation and temporal reasoning in Natural Language Texts and media, mainly oriented to texts of historical and cultural contents available on the Web. In this work we assume that events are defined through various components: actions, participants, locations, and occurrence intervals. The HEI system, through independent services, locates (annotates) the various components, and successively associates them to a specific event. The objective of this work is to build a system integrating services for the identification of events, the discovery of their connections, and the evaluation of their consistency. We believe this interface is useful to develop applications that use the notion of story, to integrate data of digital cultural archives, and to build systems of fruition in the same field. The HEI system has been partially developed within the TrasTest project |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4310/ |
| https://www.aclweb.org/anthology/W18-4310 | |
| PWC | https://paperswithcode.com/paper/hei-hunter-events-interface-a-platform-based |
| Repo | |
| Framework | |
Multispectral Image Intrinsic Decomposition via Subspace Constraint
| Title | Multispectral Image Intrinsic Decomposition via Subspace Constraint |
| Authors | Qian Huang, Weixin Zhu, Yang Zhao, Linsen Chen, Yao Wang, Tao Yue, Xun Cao |
| Abstract | Multispectral images contain many clues of surface characteristics of the objects, thus can be used in many computer vision tasks, e.g., recolorization and segmentation. However, due to the complex geometry structure of natural scenes, the spectra curves of the same surface can look very different under different illuminations and from different angles. In this paper, a new Multispectral Image Intrinsic Decomposition model (MIID) is presented to decompose the shading and reflectance from a single multispectral image. We extend the Retinex model, which is proposed for RGB image intrinsic decomposition, for multispectral domain. Based on this, a subspace constraint is introduced to both the shading and reflectance spectral space to reduce the ill-posedness of the problem and make the problem solvable. A dataset of 22 scenes is given with the ground truth of shadings and reflectance to facilitate objective evaluations. The experiments demonstrate the effectiveness of the proposed method. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Huang_Multispectral_Image_Intrinsic_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Multispectral_Image_Intrinsic_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multispectral-image-intrinsic-decomposition-1 |
| Repo | |
| Framework | |
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
| Title | Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1000/ |
| https://www.aclweb.org/anthology/D18-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2018-conference-on-1 |
| Repo | |
| Framework | |
Cheap DNN Pruning with Performance Guarantees
| Title | Cheap DNN Pruning with Performance Guarantees |
| Authors | Konstantinos Pitas, Mike Davies, Pierre Vandergheynst |
| Abstract | Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers often with little or no drop in classification accuracy. However most of the existing pruning schemes either have to be applied during training or require a costly retraining procedure after pruning to regain classification accuracy. In this paper we propose a cheap pruning algorithm based on difference of convex (DC) optimisation. We also provide theoretical analysis for the growth in the Generalisation Error (GE) of the new pruned network. Our method can be used with any convex regulariser and allows for a controlled degradation in classification accuracy while being orders of magnitude faster than competing approaches. Experiments on common feedforward neural networks show that for sparsity levels above 90% our method achieves 10% higher classification accuracy compared to Hard Thresholding. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SJtChcgAW |
| https://openreview.net/pdf?id=SJtChcgAW | |
| PWC | https://paperswithcode.com/paper/cheap-dnn-pruning-with-performance-guarantees |
| Repo | |
| Framework | |
Stock price prediction using support vector regression on daily and up to the minute prices
| Title | Stock price prediction using support vector regression on daily and up to the minute prices |
| Authors | Bruno Miranda, HenriqueVinicius, AmorimSobreiro, HerbertKimura |
| Abstract | The purpose of predictive stock price systems is to provide abnormal returns for financial market operators and serve as a basis for risk management tools. Although the Efficient Market Hypothesis (EMH) states that it is not possible to anticipate market movements consistently, the use of computationally intensive systems that employ machine learning algorithms is increasingly common in the development of stock trading mechanisms. Several studies, using daily stock prices, have presented predictive system applications trained on fixed periods without considering new model updates. In this context, this study uses a machine learning technique called Support Vector Regression (SVR) to predict stock prices for large and small capitalisations and in three different markets, employing prices with both daily and up-to-the-minute frequencies. Prediction errors are measured, and the model is compared to the random walk model proposed by the EMH. The results suggest that the SVR has predictive power, especially when using a strategy of updating the model periodically. There are also indicative results of increased predictions precision during lower volatility periods. |
| Tasks | Stock Price Prediction |
| Published | 2018-09-01 |
| URL | https://www.sciencedirect.com/science/article/pii/S2405918818300060 |
| https://www.sciencedirect.com/science/article/pii/S2405918818300060/pdfft?md5=0751f9a24ce1ede7ae0662d4f51fc7e5&pid=1-s2.0-S2405918818300060-main.pdf | |
| PWC | https://paperswithcode.com/paper/stock-price-prediction-using-support-vector |
| Repo | |
| Framework | |
Automatic Extraction of Causal Relations from Text using Linguistically Informed Deep Neural Networks
| Title | Automatic Extraction of Causal Relations from Text using Linguistically Informed Deep Neural Networks |
| Authors | Tirthankar Dasgupta, Rupsa Saha, Lipika Dey, Abir Naskar |
| Abstract | In this paper we have proposed a linguistically informed recursive neural network architecture for automatic extraction of cause-effect relations from text. These relations can be expressed in arbitrarily complex ways. The architecture uses word level embeddings and other linguistic features to detect causal events and their effects mentioned within a sentence. The extracted events and their relations are used to build a causal-graph after clustering and appropriate generalization, which is then used for predictive purposes. We have evaluated the performance of the proposed extraction model with respect to two baseline systems,one a rule-based classifier, and the other a conditional random field (CRF) based supervised model. We have also compared our results with related work reported in the past by other authors on SEMEVAL data set, and found that the proposed bi-directional LSTM model enhanced with an additional linguistic layer performs better. We have also worked extensively on creating new annotated datasets from publicly available data, which we are willing to share with the community. |
| Tasks | Feature Engineering |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5035/ |
| https://www.aclweb.org/anthology/W18-5035 | |
| PWC | https://paperswithcode.com/paper/automatic-extraction-of-causal-relations-from |
| Repo | |
| Framework | |
