Paper Group NAWR 9
TARGER: Neural Argument Mining at Your Fingertips. Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives. Evaluating shallow and deep learning strategies for the 2018 n2c2 shared task on clinical text classification. Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dim …
TARGER: Neural Argument Mining at Your Fingertips
| Title | TARGER: Neural Argument Mining at Your Fingertips |
| Authors | Artem Chernodub, Oleksiy Oliynyk, Philipp Heidenreich, Alex Bondarenko, er, Matthias Hagen, Chris Biemann, Alex Panchenko, er |
| Abstract | We present TARGER, an open source neural argument mining framework for tagging arguments in free input texts and for keyword-based retrieval of arguments from an argument-tagged web-scale corpus. The currently available models are pre-trained on three recent argument mining datasets and enable the use of neural argument mining without any reproducibility effort on the user{'}s side. The open source code ensures portability to other domains and use cases. |
| Tasks | Argument Mining |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-3031/ |
| https://www.aclweb.org/anthology/P19-3031 | |
| PWC | https://paperswithcode.com/paper/targer-neural-argument-mining-at-your |
| Repo | https://github.com/achernodub/targer |
| Framework | pytorch |
Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives
| Title | Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives |
| Authors | Wang Chi Cheung |
| Abstract | We consider an agent who is involved in an online Markov decision process, and receives a vector of outcomes every round. The agent aims to simultaneously optimize multiple objectives associated with the multi-dimensional outcomes. Due to state transitions, it is challenging to balance the vectorial outcomes for achieving near-optimality. In particular, contrary to the single objective case, stationary policies are generally sub-optimal. We propose a no-regret algorithm based on the Frank-Wolfe algorithm (Frank and Wolfe 1956), UCRL2 (Jaksch et al. 2010), as well as a crucial and novel gradient threshold procedure. The procedure involves carefully delaying gradient updates, and returns a non-stationary policy that diversifies the outcomes for optimizing the objectives. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8361-regret-minimization-for-reinforcement-learning-with-vectorial-feedback-and-complex-objectives |
| http://papers.nips.cc/paper/8361-regret-minimization-for-reinforcement-learning-with-vectorial-feedback-and-complex-objectives.pdf | |
| PWC | https://paperswithcode.com/paper/regret-minimization-for-reinforcement-1 |
| Repo | https://github.com/wangchimit/mdp_q |
| Framework | none |
Evaluating shallow and deep learning strategies for the 2018 n2c2 shared task on clinical text classification
| Title | Evaluating shallow and deep learning strategies for the 2018 n2c2 shared task on clinical text classification |
| Authors | Michel Oleynik, Amila Kugic, Zdenko Kasáč, Markus Kreuzthaler |
| Abstract | Objective: Automated clinical phenotyping is challenging because word-based features quickly turn it into a high-dimensional problem, in which the small, privacy-restricted, training datasets might lead to overfitting. Pretrained embeddings might solve this issue by reusing input representation schemes trained on a larger dataset. We sought to evaluate shallow and deep learning text classifiers and the impact of pretrained embeddings in a small clinical dataset. Materials and Methods: We participated in the 2018 National NLP Clinical Challenges (n2c2) Shared Task on cohort selection and received an annotated dataset with medical narratives of 202 patients for multilabel binary text classification. We set our baseline to a majority classifier, to which we compared a rule-based classifier and orthogonal machine learning strategies: support vector machines, logistic regression, and long short-term memory neural networks. We evaluated logistic regression and long short-term memory using both self-trained and pretrained BioWordVec word embeddings as input representation schemes. Results: Rule-based classifier showed the highest overall micro F1 score (0.9100), with which we finished first in the challenge. Shallow machine learning strategies showed lower overall micro F1 scores, but still higher than deep learning strategies and the baseline. We could not show a difference in classification efficiency between self-trained and pretrained embeddings. Discussion: Clinical context, negation, and value-based criteria hindered shallow machine learning approaches, while deep learning strategies could not capture the term diversity due to the small training dataset. Conclusion: Shallow methods for clinical phenotyping can still outperform deep learning methods in small imbalanced data, even when supported by pretrained embeddings. |
| Tasks | Text Classification, Word Embeddings |
| Published | 2019-09-12 |
| URL | https://doi.org/10.1093/jamia/ocz149 |
| https://academic.oup.com/jamia/advance-article-pdf/doi/10.1093/jamia/ocz149/30000809/ocz149.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-shallow-and-deep-learning |
| Repo | https://github.com/bst-mug/n2c2 |
| Framework | none |
Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
| Title | Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions |
| Authors | Peng Chen, Keyi Wu, Joshua Chen, Tom O’Leary-Roseberry, Omar Ghattas |
| Abstract | We propose a projected Stein variational Newton (pSVN) method for high-dimensional Bayesian inference. To address the curse of dimensionality, we exploit the intrinsic low-dimensional geometric structure of the posterior distribution in the high-dimensional parameter space via its Hessian (of the log posterior) operator and perform a parallel update of the parameter samples projected into a low-dimensional subspace by an SVN method. The subspace is adaptively constructed using the eigenvectors of the averaged Hessian at the current samples. We demonstrate fast convergence of the proposed method, complexity independent of the parameter and sample dimensions, and parallel scalability. |
| Tasks | Bayesian Inference |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9649-projected-stein-variational-newton-a-fast-and-scalable-bayesian-inference-method-in-high-dimensions |
| http://papers.nips.cc/paper/9649-projected-stein-variational-newton-a-fast-and-scalable-bayesian-inference-method-in-high-dimensions.pdf | |
| PWC | https://paperswithcode.com/paper/projected-stein-variational-newton-a-fast-and |
| Repo | https://github.com/cpempire/pSVN |
| Framework | none |
Explore-Exploit Graph Traversal for Image Retrieval
| Title | Explore-Exploit Graph Traversal for Image Retrieval |
| Authors | Cheng Chang, Guangwei Yu, Chundi Liu, Maksims Volkovs |
| Abstract | We propose a novel graph-based approach for image retrieval. Given a nearest neighbor graph produced by the global descriptor model, we traverse it by alternating between exploit and explore steps. The exploit step maximally utilizes the immediate neighborhood of each vertex, while the explore step traverses vertices that are farther away in the descriptor space. By combining these two steps we can better capture the underlying image manifold, and successfully retrieve relevant images that are visually dissimilar to the query. Our traversal algorithm is conceptually simple, has few tunable parameters and can be implemented with basic data structures. This enables fast real-time inference for previously unseen queries with minimal memory overhead. Despite relative simplicity, we show highly competitive results on multiple public benchmarks, including the largest image retrieval dataset that is currently publicly available. Full code for this work is available here: https://github.com/layer6ai-labs/egt. |
| Tasks | Image Retrieval |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Chang_Explore-Exploit_Graph_Traversal_for_Image_Retrieval_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Chang_Explore-Exploit_Graph_Traversal_for_Image_Retrieval_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/explore-exploit-graph-traversal-for-image |
| Repo | https://github.com/layer6ai-labs/egt |
| Framework | none |
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization
| Title | Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization |
| Authors | Daochang Liu, Tingting Jiang, Yizhou Wang |
| Abstract | Temporal action localization is crucial for understanding untrimmed videos. In this work, we first identify two underexplored problems posed by the weak supervision for temporal action localization, namely action completeness modeling and action-context separation. Then by presenting a novel network architecture and its training strategy, the two problems are explicitly looked into. Specifically, to model the completeness of actions, we propose a multi-branch neural network in which branches are enforced to discover distinctive action parts. Complete actions can be therefore localized by fusing activations from different branches. And to separate action instances from their surrounding context, we generate hard negative data for training using the prior that motionless video clips are unlikely to be actions. Experiments performed on datasets THUMOS’14 and ActivityNet show that our framework outperforms state-of-the-art methods. In particular, the average mAP on ActivityNet v1.2 is significantly improved from 18.0% to 22.4%. Our code will be released soon. |
| Tasks | Action Localization, Temporal Action Localization, Weakly Supervised Action Localization, Weakly-supervised Temporal Action Localization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Completeness_Modeling_and_Context_Separation_for_Weakly_Supervised_Temporal_Action_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Completeness_Modeling_and_Context_Separation_for_Weakly_Supervised_Temporal_Action_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/completeness-modeling-and-context-separation |
| Repo | https://github.com/Finspire13/CMCS-Temporal-Action-Localization |
| Framework | pytorch |
Coordinated hippocampal-entorhinal replay as structural inference
| Title | Coordinated hippocampal-entorhinal replay as structural inference |
| Authors | Talfan Evans, Neil Burgess |
| Abstract | Constructing and maintaining useful representations of sensory experience is essential for reasoning about ones environment. High-level associative (topological) maps can be useful for efficient planning and are easily constructed from experience. Conversely, embedding new experiences within a metric structure allows them to be integrated with existing ones and novel associations to be implicitly inferred. Neurobiologically, the synaptic associations between hippocampal place cells and entorhinal grid cells are thought to represent associative and metric structures, respectively. Learning the place-grid cell associations can therefore be interpreted as learning a mapping between these two spaces. Here, we show how this map could be constructed by probabilistic message-passing through the hippocampal-entorhinal system, where messages are scheduled to reduce the propagation of redundant information. We propose that this offline inference corresponds to coordinated hippocampal-entorhinal replay during sharp wave ripples. Our results also suggest that the metric map will contain local distortions that reflect the inferred structure of the environment according to associative experience, explaining observed grid deformations. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8450-coordinated-hippocampal-entorhinal-replay-as-structural-inference |
| http://papers.nips.cc/paper/8450-coordinated-hippocampal-entorhinal-replay-as-structural-inference.pdf | |
| PWC | https://paperswithcode.com/paper/coordinated-hippocampal-entorhinal-replay-as |
| Repo | https://github.com/talfanevans/Coordinated_replay_for_structural_inference_NeurIPS_2019 |
| Framework | none |
Efficient Featurized Image Pyramid Network for Single Shot Detector
| Title | Efficient Featurized Image Pyramid Network for Single Shot Detector |
| Authors | Yanwei Pang, Tiancai Wang, Rao Muhammad Anwer, Fahad Shahbaz Khan, Ling Shao |
| Abstract | Single-stage object detectors have recently gained popularity due to their combined advantage of high detection accuracy and real-time speed. However, while promising results have been achieved by these detectors on standard-sized objects, their performance on small objects is far from satisfactory. To detect very small/large objects, classical pyramid representation can be exploited, where an image pyramid is used to build a feature pyramid (featurized image pyramid), enabling detection across a range of scales. Existing single-stage detectors avoid such a featurized image pyramid representation due to its memory and time complexity. In this paper, we introduce a light-weight architecture to efficiently produce featurized image pyramid in a single-stage detection framework. The resulting multi-scale features are then injected into the prediction layers of the detector using an attention module. The performance of our detector is validated on two benchmarks: PASCAL VOC and MS COCO. For a 300x300 input, our detector operates at 111 frames per second (FPS) on a Titan X GPU, providing state-of-the-art detection accuracy on PASCAL VOC 2007 testset. On the MS COCO testset, our detector achieves state-of-the-art results surpassing all existing single-stage methods in the case of single-scale inference. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Pang_Efficient_Featurized_Image_Pyramid_Network_for_Single_Shot_Detector_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Pang_Efficient_Featurized_Image_Pyramid_Network_for_Single_Shot_Detector_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-featurized-image-pyramid-network |
| Repo | https://github.com/vaesl/LFIP.git |
| Framework | none |
Open-Unmix - A Reference Implementation for Music Source Separation
| Title | Open-Unmix - A Reference Implementation for Music Source Separation |
| Authors | Fabian-Robert Stöter, Stefan Uhlich, Antoine Liutkus, and YukiMitsufuji |
| Abstract | Music source separation is the task of decomposing music into its constitutive components,e.g., yielding separated stems for the vocals, bass, and drums. Such a separation has manyapplications ranging from rearranging/repurposing the stems (remixing, repanning, upmixing)to full extraction (karaoke, sample creation, audio restoration). Music separation has a longhistory of scientific activity as it is known to be a very challenging problem. In recent years,deep learning-based systems - for the first time - yielded high-quality separations that alsolead to increased commercial interest. However, until now, no open-source implementationthat achieves state-of-the-art results is available.Open-Unmixcloses this gap by providinga reference implementation based on deep neural networks. It serves two main purposes.Firstly, to accelerate academic research asOpen-Unmixprovides implementations for themost popular deep learning frameworks, giving researchers a flexible way to reproduce results.Secondly, we provide a pre-trained model for end users and even artists to try and use sourceseparation. Furthermore, we designedOpen-Unmixto be one core component in an openecosystem on music separation, where we already provide open datasets, software utilities,and open evaluation to foster reproducible research as the basis of future development. |
| Tasks | Music Source Separation |
| Published | 2019-09-08 |
| URL | https://joss.theoj.org/papers/10.21105/joss.01667 |
| https://www.theoj.org/joss-papers/joss.01667/10.21105.joss.01667.pdf | |
| PWC | https://paperswithcode.com/paper/open-unmix-a-reference-implementation-for |
| Repo | https://github.com/sigsep/open-unmix-pytorch |
| Framework | pytorch |
A Study of Incorrect Paraphrases in Crowdsourced User Utterances
| Title | A Study of Incorrect Paraphrases in Crowdsourced User Utterances |
| Authors | Mohammad-Ali Yaghoub-Zadeh-Fard, Boualem Benatallah, Moshe Chai Barukh, Shayan Zamanirad |
| Abstract | Developing bots demands highquality training samples, typically in the form of user utterances and their associated intents. Given the fuzzy nature of human language, such datasets ideally must cover all possible utterances of each single intent. Crowdsourcing has widely been used to collect such inclusive datasets by paraphrasing an initial utterance. However, the quality of this approach often suffers from various issues, particularly language errors produced by unqualified crowd workers. More so, since workers are tasked to write open-ended text, it is very challenging to automatically asses the quality of paraphrased utterances. In this paper, we investigate common crowdsourced paraphrasing issues, and propose an annotated dataset called Para-Quality, for detecting the quality issues. We also investigate existing tools and services to provide baselines for detecting each category of issues. In all, this work presents a data-driven view of incorrect paraphrases during the bot development process, and we pave the way towards automatic detection of unqualified paraphrases. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1026/ |
| https://www.aclweb.org/anthology/N19-1026 | |
| PWC | https://paperswithcode.com/paper/a-study-of-incorrect-paraphrases-in |
| Repo | https://github.com/mysilver/ParaQuality |
| Framework | none |
Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction
| Title | Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction |
| Authors | Difan Zou, Pan Xu, Quanquan Gu |
| Abstract | Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) algorithms have received increasing attention in both theory and practice. In this paper, we propose a Stochastic Recursive Variance-Reduced gradient HMC (SRVR-HMC) algorithm. It makes use of a semi-stochastic gradient estimator that recursively accumulates the gradient information to reduce the variance of the stochastic gradient. We provide a convergence analysis of SRVR-HMC for sampling from a class of non-log-concave distributions and show that SRVR-HMC converges faster than all existing HMC-type algorithms based on underdamped Langevin dynamics. Thorough experiments on synthetic and real-world datasets validate our theory and demonstrate the superiority of SRVR-HMC. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8639-stochastic-gradient-hamiltonian-monte-carlo-methods-with-recursive-variance-reduction |
| http://papers.nips.cc/paper/8639-stochastic-gradient-hamiltonian-monte-carlo-methods-with-recursive-variance-reduction.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-gradient-hamiltonian-monte-carlo-3 |
| Repo | https://github.com/knowzou/SRVR |
| Framework | none |
Deeper Profiles and Cascaded Recurrent and Convolutional Neural Networks for state-of-the-art Protein Secondary Structure Prediction
| Title | Deeper Profiles and Cascaded Recurrent and Convolutional Neural Networks for state-of-the-art Protein Secondary Structure Prediction |
| Authors | Mirko Torrisi, Manaz Kaleel, Gianluca Pollastri |
| Abstract | Protein Secondary Structure prediction has been a central topic of research in Bioinformatics for decades. In spite of this, even the most sophisticated ab initio SS predictors are not able to reach the theoretical limit of three-state prediction accuracy (88–90%), while only a few predict more than the 3 traditional Helix, Strand and Coil classes. In this study we present tests on different models trained both on single sequence and evolutionary profile-based inputs and develop a new state-of-the-art system with Porter 5. Porter 5 is composed of ensembles of cascaded Bidirectional Recurrent Neural Networks and Convolutional Neural Networks, incorporates new input encoding techniques and is trained on a large set of protein structures. Porter 5 achieves 84% accuracy (81% SOV) when tested on 3 classes and 73% accuracy (70% SOV) on 8 classes on a large independent set. In our tests Porter 5 is 2% more accurate than its previous version and outperforms or matches the most recent predictors of secondary structure we tested. When Porter 5 is retrained on SCOPe based sets that eliminate homology between training/testing samples we obtain similar results. Porter is available as a web server and standalone program at http://distilldeep.ucd.ie/porter/ alongside all the datasets and alignments. |
| Tasks | Protein Secondary Structure Prediction |
| Published | 2019-10-12 |
| URL | https://doi.org/10.1038/s41598-019-48786-x |
| https://www.nature.com/articles/s41598-019-48786-x.pdf | |
| PWC | https://paperswithcode.com/paper/deeper-profiles-and-cascaded-recurrent-and |
| Repo | https://github.com/mircare/Porter5 |
| Framework | none |
Global-to-Local Generative Model for 3D Shapes
| Title | Global-to-Local Generative Model for 3D Shapes |
| Authors | Hao Wang, Nadav Schor, Ruizhen Hu, Haibin Huang, Daniel Cohen-Or, Hui Huang |
| Abstract | We introduce a generative model for 3D man-made shapes. The presented method takes a global-to-local (G2L) approach. An adversarial network (GAN) is built first to construct the overall structure of the shape, segmented and labeled into parts. A novel conditional auto-encoder (AE) is then augmented to act as a part-level refiner. The GAN, associated with additional local discriminators and quality losses, synthesizes a voxel-based model, and assigns the voxels with part labels that are represented in separate channels. The AE is trained to amend the initial synthesis of the parts, yielding more plausible part geometries. We also introduce new means to measure and evaluate the performance of an adversarial generative model. We demonstrate that our global-to-local generative model produces significantly better results than a plain three-dimensional GAN, in terms of both their shape variety and the distribution with respect to the training data. |
| Tasks | |
| Published | 2019-01-10 |
| URL | https://dl.acm.org/citation.cfm?id=3275025 |
| http://202.182.120.255/file/upload_file/image/research/att201810171620/G2L.pdf | |
| PWC | https://paperswithcode.com/paper/global-to-local-generative-model-for-3d |
| Repo | https://github.com/Hao-HUST/G2LGAN |
| Framework | tf |
A hybrid method of Exponential Smoothing and Recurrent Neural Networks for time series forecasting
| Title | A hybrid method of Exponential Smoothing and Recurrent Neural Networks for time series forecasting |
| Authors | Slawek Smyl |
| Abstract | This paper presents the winning submission of the M4 forecasting competition. The submission utilizes a Dynamic Computational Graph Neural Network system that enables mixing of a standard Exponential Smoothing model with advanced Long Short Term Memory networks into a common framework. The result is a hybrid and hierarchical forecasting method. Keywords: Forecasting competitions, M4, Dynamic Computational Graphs, Automatic Differentiation, Long Short Term Memory (LSTM) networks, Exponential Smoothing |
| Tasks | Time Series, Time Series Forecasting |
| Published | 2019-07-18 |
| URL | https://www.sciencedirect.com/science/article/pii/S0169207019301153 |
| https://github.com/slaweks17/ES_RNN/blob/master/A_hybrid_method_of_exponential_smoothing_and_recurrent_neural_networks_for_time_series_forecasting.pdf | |
| PWC | https://paperswithcode.com/paper/a-hybrid-method-of-exponential-smoothing-and |
| Repo | https://github.com/slaweks17/ES_RNN |
| Framework | none |
ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees
| Title | ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees |
| Authors | Hao He, Hao Wang, Guang-He Lee, Yonglong Tian |
| Abstract | Probabilistic modelling is a principled framework to perform model aggregation, which has been a primary mechanism to combat mode collapse in the context of Generative Adversarial Networks (GAN). In this paper, we propose a novel probabilistic framework for GANs, ProbGAN, which iteratively learns a distribution over generators with a carefully crafted prior. Learning is efficiently triggered by a tailored stochastic gradient Hamiltonian Monte Carlo with a novel gradient approximation to perform Bayesian inference. Our theoretical analysis further reveals that our treatment is the first probabilistic framework that yields an equilibrium where generator distributions are faithful to the data distribution. Empirical evidence on synthetic high-dimensional multi-modal data and image databases (CIFAR-10, STL-10, and ImageNet) demonstrates the superiority of our method over both start-of-the-art multi-generator GANs and other probabilistic treatment for GANs. |
| Tasks | Bayesian Inference |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1l7bnR5Ym |
| https://openreview.net/pdf?id=H1l7bnR5Ym | |
| PWC | https://paperswithcode.com/paper/probgan-towards-probabilistic-gan-with |
| Repo | https://github.com/hehaodele/ProbGAN |
| Framework | pytorch |
