Paper Group NANR 213
Roll Call Vote Prediction with Knowledge Augmented Models. IxaMed at PharmacoNER Challenge 2019. Measure Country-Level Socio-Economic Indicators with Streaming News: An Empirical Study. AutoML Strategy Based on Grammatical Evolution: A Case Study about Knowledge Discovery from Text. Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder i …
Roll Call Vote Prediction with Knowledge Augmented Models
| Title | Roll Call Vote Prediction with Knowledge Augmented Models |
| Authors | Pallavi Patil, Kriti Myer, Ronak Zala, Arpit Singh, Sheshera Mysore, Andrew McCallum, Adrian Benton, Am Stent, a |
| Abstract | The official voting records of United States congresspeople are preserved as roll call votes. Prediction of voting behavior of politicians for whom no voting record exists, such as individuals running for office, is important for forecasting key political decisions. Prior work has relied on past votes cast to predict future votes, and thus fails to predict voting patterns for politicians without voting records. We address this by augmenting a prior state of the art model with multiple sources of external knowledge so as to enable prediction on unseen politicians. The sources of knowledge we use are news text and Freebase, a manually curated knowledge base. We propose augmentations based on unigram features for news text, and a knowledge base embedding method followed by a neural network composition for relations from Freebase. Empirical evaluation of these approaches indicate that the proposed models outperform the prior system for politicians with complete historical voting records by 1.0{%} point of accuracy (8.7{%} error reduction) and for politicians without voting records by 33.4{%} points of accuracy (66.7{%} error reduction). We also show that the knowledge base augmented approach outperforms the news text augmented approach by 4.2{%} points of accuracy. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1053/ |
| https://www.aclweb.org/anthology/K19-1053 | |
| PWC | https://paperswithcode.com/paper/roll-call-vote-prediction-with-knowledge |
| Repo | |
| Framework | |
IxaMed at PharmacoNER Challenge 2019
| Title | IxaMed at PharmacoNER Challenge 2019 |
| Authors | Xabier Lahuerta, Iakes Goenaga, Koldo Gojenola, Aitziber Atutxa Salazar, Maite Oronoz |
| Abstract | The aim of this paper is to present our approach (IxaMed) in the PharmacoNER 2019 task. The task consists of identifying chemical, drug, and gene/protein mentions from clinical case studies written in Spanish. The evaluation of the task is divided in two scenarios: one corresponding to the detection of named entities and one corresponding to the indexation of named entities that have been previously identified. In order to identify named entities we have made use of a Bi-LSTM with a CRF on top in combination with different types of word embeddings. We have achieved our best result (86.81 F-Score) combining pretrained word embeddings of Wikipedia and Electronic Health Records (50M words) with contextual string embeddings of Wikipedia and Electronic Health Records. On the other hand, for the indexation of the named entities we have used the Levenshtein distance obtaining a 85.34 F-Score as our best result. |
| Tasks | Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5704/ |
| https://www.aclweb.org/anthology/D19-5704 | |
| PWC | https://paperswithcode.com/paper/ixamed-at-pharmaconer-challenge-2019 |
| Repo | |
| Framework | |
Measure Country-Level Socio-Economic Indicators with Streaming News: An Empirical Study
| Title | Measure Country-Level Socio-Economic Indicators with Streaming News: An Empirical Study |
| Authors | Bonan Min, Xiaoxi Zhao |
| Abstract | Socio-economic conditions are difficult to measure. For example, the U.S. Bureau of Labor Statistics needs to conduct large-scale household surveys regularly to track the unemployment rate, an indicator widely used by economists and policymakers. We argue that events reported in streaming news can be used as {``}micro-sensors{''} for measuring socio-economic conditions. Similar to collecting surveys and then counting answers, it is possible to measure a socio-economic indicator by counting related events. In this paper, we propose Event-Centric Indicator Measure (ECIM), a novel approach to measure socio-economic indicators with events. We empirically demonstrate strong correlation between ECIM values to several representative indicators in socio-economic research. | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1121/ |
| https://www.aclweb.org/anthology/D19-1121 | |
| PWC | https://paperswithcode.com/paper/measure-country-level-socio-economic |
| Repo | |
| Framework | |
AutoML Strategy Based on Grammatical Evolution: A Case Study about Knowledge Discovery from Text
| Title | AutoML Strategy Based on Grammatical Evolution: A Case Study about Knowledge Discovery from Text |
| Authors | Suilan Estevez-Velarde, Yoan Guti{'e}rrez, Andr{'e}s Montoyo, Yudivi{'a}n Almeida-Cruz |
| Abstract | The process of extracting knowledge from natural language text poses a complex problem that requires both a combination of machine learning techniques and proper feature selection. Recent advances in Automatic Machine Learning (AutoML) provide effective tools to explore large sets of algorithms, hyper-parameters and features to find out the most suitable combination of them. This paper proposes a novel AutoML strategy based on probabilistic grammatical evolution, which is evaluated on the health domain by facing the knowledge discovery challenge in Spanish text documents. Our approach achieves state-of-the-art results and provides interesting insights into the best combination of parameters and algorithms to use when dealing with this challenge. Source code is provided for the research community. |
| Tasks | AutoML, Feature Selection |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1428/ |
| https://www.aclweb.org/anthology/P19-1428 | |
| PWC | https://paperswithcode.com/paper/automl-strategy-based-on-grammatical |
| Repo | |
| Framework | |
Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in Dialogue Generation
| Title | Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in Dialogue Generation |
| Authors | Min Zeng, Yisen Wang, Yuan Luo |
| Abstract | Variational encoder-decoders have achieved well-recognized performance in the dialogue generation task. Existing works simply assume the Gaussian priors of the latent variable, which are incapable of representing complex latent variables effectively. To address the issues, we propose to use the Dirichlet distribution with flexible structures to characterize the latent variables in place of the traditional Gaussian distribution, called Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder model (Dir-VHRED). Based on which, we further find that there is redundancy among the dimensions of latent variable, and the lengths and sentence patterns of the responses can be strongly correlated to each dimension of the latent variable. Therefore, controllable responses can be generated through specifying the value of each dimension of the latent variable. Experimental results on benchmarks show that our proposed Dir-VHRED yields substantial improvements on negative log-likelihood, word-embedding-based and human evaluations. |
| Tasks | Dialogue Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1124/ |
| https://www.aclweb.org/anthology/D19-1124 | |
| PWC | https://paperswithcode.com/paper/dirichlet-latent-variable-hierarchical |
| Repo | |
| Framework | |
Co-Operation as an Asymmetric Form of Human-Computer Creativity. Case: Peace Machine
| Title | Co-Operation as an Asymmetric Form of Human-Computer Creativity. Case: Peace Machine |
| Authors | Mika H{"a}m{"a}l{"a}inen, Timo Honkela |
| Abstract | This theoretical paper identifies a need for a definition of asymmetric co-creativity where creativity is expected from the computational agent but not from the human user. Our co-operative creativity framework takes into account that the computational agent has a message to convey in a co-operative fashion, which introduces a trade-off on how creative the computer can be. The requirements of co-operation are identified from an interdisciplinary point of view. We divide co-operative creativity in message creativity, contextual creativity and communicative creativity. Finally these notions are applied in the context of the Peace Machine system concept. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4105/ |
| https://www.aclweb.org/anthology/W19-4105 | |
| PWC | https://paperswithcode.com/paper/co-operation-as-an-asymmetric-form-of-human |
| Repo | |
| Framework | |
WIQA: A dataset for ``What if…’’ reasoning over procedural text
| Title | WIQA: A dataset for ``What if…’’ reasoning over procedural text | |
| Authors | T, Niket on, Bhavana Dalvi, Keisuke Sakaguchi, Peter Clark, Antoine Bosselut |
| Abstract | We introduce WIQA, the first large-scale dataset of {}What if...{''} questions over procedural text. WIQA contains a collection of paragraphs, each annotated with multiple influence graphs describing how one change affects another, and a large (40k) collection of {}What if…?{''} multiple-choice questions derived from these. For example, given a paragraph about beach erosion, would stormy weather hasten or decelerate erosion? WIQA contains three kinds of questions: perturbations to steps mentioned in the paragraph; external (out-of-paragraph) perturbations requiring commonsense knowledge; and irrelevant (no effect) perturbations. We find that state-of-the-art models achieve 73.8{%} accuracy, well below the human performance of 96.3{%}. We analyze the challenges, in particular tracking chains of influences, and present the dataset as an open challenge to the community. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1629/ |
| https://www.aclweb.org/anthology/D19-1629 | |
| PWC | https://paperswithcode.com/paper/wiqa-a-dataset-for-what-if-reasoning-over-1 |
| Repo | |
| Framework | |
A Hybrid Model for Globally Coherent Story Generation
| Title | A Hybrid Model for Globally Coherent Story Generation |
| Authors | Fangzhou Zhai, Vera Demberg, Pavel Shkadzko, Wei Shi, Asad Sayeed |
| Abstract | Automatically generating globally coherent stories is a challenging problem. Neural text generation models have been shown to perform well at generating fluent sentences from data, but they usually fail to keep track of the overall coherence of the story after a couple of sentences. Existing work that incorporates a text planning module succeeded in generating recipes and dialogues, but appears quite data-demanding. We propose a novel story generation approach that generates globally coherent stories from a fairly small corpus. The model exploits a symbolic text planning module to produce text plans, thus reducing the demand of data; a neural surface realization module then generates fluent text conditioned on the text plan. Human evaluation showed that our model outperforms various baselines by a wide margin and generates stories which are fluent as well as globally coherent. |
| Tasks | Text Generation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3404/ |
| https://www.aclweb.org/anthology/W19-3404 | |
| PWC | https://paperswithcode.com/paper/a-hybrid-model-for-globally-coherent-story |
| Repo | |
| Framework | |
Sentence-Level Agreement for Neural Machine Translation
| Title | Sentence-Level Agreement for Neural Machine Translation |
| Authors | Mingming Yang, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Min Zhang, Tiejun Zhao |
| Abstract | The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references. In NMT, there is a natural correspondence between the source sentence and the target sentence. However, this relationship has only been represented using the entire neural network and the training objective is computed in word-level. In this paper, we propose a sentence-level agreement module to directly minimize the difference between the representation of source and target sentence. The proposed agreement module can be integrated into NMT as an additional training objective function and can also be used to enhance the representation of the source sentences. Empirical results on the NIST Chinese-to-English and WMT English-to-German tasks show the proposed agreement module can significantly improve the NMT performance. |
| Tasks | Machine Translation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1296/ |
| https://www.aclweb.org/anthology/P19-1296 | |
| PWC | https://paperswithcode.com/paper/sentence-level-agreement-for-neural-machine |
| Repo | |
| Framework | |
Dimensionality Reduction for Representing the Knowledge of Probabilistic Models
| Title | Dimensionality Reduction for Representing the Knowledge of Probabilistic Models |
| Authors | Marc T Law, Jake Snell, Amir-massoud Farahmand, Raquel Urtasun, Richard S Zemel |
| Abstract | Most deep learning models rely on expressive high-dimensional representations to achieve good performance on tasks such as classification. However, the high dimensionality of these representations makes them difficult to interpret and prone to over-fitting. We propose a simple, intuitive and scalable dimension reduction framework that takes into account the soft probabilistic interpretation of standard deep models for classification. When applying our framework to visualization, our representations more accurately reflect inter-class distances than standard visualization techniques such as t-SNE. We show experimentally that our framework improves generalization performance to unseen categories in zero-shot learning. We also provide a finite sample error upper bound guarantee for the method. |
| Tasks | Dimensionality Reduction, Zero-Shot Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SygD-hCcF7 |
| https://openreview.net/pdf?id=SygD-hCcF7 | |
| PWC | https://paperswithcode.com/paper/dimensionality-reduction-for-representing-the |
| Repo | |
| Framework | |
Detecting Topological Defects in 2D Active Nematics Using Convolutional Neural Networks
| Title | Detecting Topological Defects in 2D Active Nematics Using Convolutional Neural Networks |
| Authors | Ruoshi Liu, Michael M. Norton, Seth Fraden, Pengyu Hong |
| Abstract | Active matter consists of active agents which transform energy extracted from surroundings into momentum, producing a variety of collective phenomena. A model, synthetic active system composed of microtubule polymers driven by protein motors spontaneously forms a liquid-crystalline nematic phase. Extensile stress created by the protein motors precipitates continuous buckling and folding of the microtubules creating motile topological defects and turbulent fluid flows. Defect motion is determined by the rheological properties of the material; however, these remain largely unquantified. Measuring defects dynamics can yield fundamental insights into active nematics, a class of materials that include bacterial films and animal cells. Current methods for defect detection lack robustness and precision, and require fine-tuning for datasets with different visual quality. In this study, we applied Deep Learning to train a defect detector to automatically analyze microscopy videos of the microtubule active nematic. Experimental results indicate that our method is robust and accurate. It is expected to significantly increase the amount of video data that can be processed. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HklVTi09tm |
| https://openreview.net/pdf?id=HklVTi09tm | |
| PWC | https://paperswithcode.com/paper/detecting-topological-defects-in-2d-active |
| Repo | |
| Framework | |
Ray-Space Projection Model for Light Field Camera
| Title | Ray-Space Projection Model for Light Field Camera |
| Authors | Qi Zhang, Jinbo Ling, Qing Wang, Jingyi Yu |
| Abstract | Light field essentially represents the collection of rays in space. The rays captured by multiple light field cameras form subsets of full rays in 3D space and can be transformed to each other. However, most previous approaches model the projection from an arbitrary point in 3D space to corresponding pixel on the sensor. There are few models on describing the ray sampling and transformation among multiple light field cameras. In the paper, we propose a novel ray-space projection model to transform sets of rays captured by multiple light field cameras in term of the Plucker coordinates. We first derive a 6x6 ray-space intrinsic matrix based on multi-projection-center (MPC) model. A homogeneous ray-space projection matrix and a fundamental matrix are then proposed to establish ray-ray correspondences among multiple light fields. Finally, based on the ray-space projection matrix, a novel camera calibration method is proposed to verify the proposed model. A linear constraint and a ray-ray cost function are established for linear initial solution and non-linear optimization respectively. Experimental results on both synthetic and real light field data have verified the effectiveness and robustness of the proposed model. |
| Tasks | Calibration |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Ray-Space_Projection_Model_for_Light_Field_Camera_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Ray-Space_Projection_Model_for_Light_Field_Camera_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/ray-space-projection-model-for-light-field |
| Repo | |
| Framework | |
Graph Convolutional Tracking
| Title | Graph Convolutional Tracking |
| Authors | Junyu Gao, Tianzhu Zhang, Changsheng Xu |
| Abstract | Tracking by siamese networks has achieved favorable performance in recent years. However, most of existing siamese methods do not take full advantage of spatial-temporal target appearance modeling under different contextual situations. In fact, the spatial-temporal information can provide diverse features to enhance the target representation, and the context information is important for online adaption of target localization. To comprehensively leverage the spatial-temporal structure of historical target exemplars and get benefit from the context information, in this work, we present a novel Graph Convolutional Tracking (GCT) method for high-performance visual tracking. Specifically, the GCT jointly incorporates two types of Graph Convolutional Networks (GCNs) into a siamese framework for target appearance modeling. Here, we adopt a spatial-temporal GCN to model the structured representation of historical target exemplars. Furthermore, a context GCN is designed to utilize the context of the current frame to learn adaptive features for target localization. Extensive results on 4 challenging benchmarks show that our GCT method performs favorably against state-of-the-art trackers while running around 50 frames per second. |
| Tasks | Visual Tracking |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Gao_Graph_Convolutional_Tracking_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Gao_Graph_Convolutional_Tracking_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/graph-convolutional-tracking |
| Repo | |
| Framework | |
Guided Evolutionary Strategies: Escaping the curse of dimensionality in random search
| Title | Guided Evolutionary Strategies: Escaping the curse of dimensionality in random search |
| Authors | Niru Maheswaranathan, Luke Metz, George Tucker, Dami Choi, Jascha Sohl-Dickstein |
| Abstract | Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the true gradient) is available instead. This arises when an approximate gradient is easier to compute than the full gradient (e.g. in meta-learning or unrolled optimization), or when a true gradient is intractable and is replaced with a surrogate (e.g. in certain reinforcement learning applications or training networks with discrete variables). We propose Guided Evolutionary Strategies, a method for optimally using surrogate gradient directions along with random search. We define a search distribution for evolutionary strategies that is elongated along a subspace spanned by the surrogate gradients. This allows us to estimate a descent direction which can then be passed to a first-order optimizer. We analytically and numerically characterize the tradeoffs that result from tuning how strongly the search distribution is stretched along the guiding subspace, and use this to derive a setting of the hyperparameters that works well across problems. Finally, we apply our method to example problems including truncated unrolled optimization and training neural networks with discrete variables, demonstrating improvement over both standard evolutionary strategies and first-order methods (that directly follow the surrogate gradient). We provide a demo of Guided ES at: redacted URL |
| Tasks | Meta-Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1xFxh0cKX |
| https://openreview.net/pdf?id=B1xFxh0cKX | |
| PWC | https://paperswithcode.com/paper/guided-evolutionary-strategies-escaping-the-1 |
| Repo | |
| Framework | |
Learning to Explore Intrinsic Saliency for Stereoscopic Video
| Title | Learning to Explore Intrinsic Saliency for Stereoscopic Video |
| Authors | Qiudan Zhang, Xu Wang, Shiqi Wang, Shikai Li, Sam Kwong, Jianmin Jiang |
| Abstract | The human visual system excels at biasing the stereoscopic visual signals by the attention mechanisms. Traditional methods relying on the low-level features and depth relevant information for stereoscopic video saliency prediction have fundamental limitations. For example, it is cumbersome to model the interactions between multiple visual cues including spatial, temporal, and depth information as a result of the sophistication. In this paper, we argue that the high-level features are crucial and resort to the deep learning framework to learn the saliency map of stereoscopic videos. Driven by spatio-temporal coherence from consecutive frames, the model first imitates the mechanism of saliency by taking advantage of the 3D convolutional neural network. Subsequently, the saliency originated from the intrinsic depth is derived based on the correlations between left and right views in a data-driven manner. Finally, a Convolutional Long Short-Term Memory (Conv-LSTM) based fusion network is developed to model the instantaneous interactions between spatio-temporal and depth attributes, such that the ultimate stereoscopic saliency maps over time are produced. Moreover, we establish a new large-scale stereoscopic video saliency dataset (SVS) including 175 stereoscopic video sequences and their fixation density annotations, aiming to comprehensively study the intrinsic attributes for stereoscopic video saliency detection. Extensive experiments show that our proposed model can achieve superior performance compared to the state-of-the-art methods on the newly built dataset for stereoscopic videos. |
| Tasks | Saliency Detection, Saliency Prediction, Video Saliency Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Learning_to_Explore_Intrinsic_Saliency_for_Stereoscopic_Video_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Learning_to_Explore_Intrinsic_Saliency_for_Stereoscopic_Video_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-explore-intrinsic-saliency-for |
| Repo | |
| Framework | |
