Paper Group ANR 1135
ChronoMID - Cross-Modal Neural Networks for 3-D Temporal Medical Imaging Data. Leveraging Dependency Forest for Neural Medical Relation Extraction. Variational Temporal Abstraction. Using Semantic Role Knowledge for Relevance Ranking of Key Phrases inDocuments: An Unsupervised Approach. A Probabilistic Generative Model of Linguistic Typology. RAP-N …
ChronoMID - Cross-Modal Neural Networks for 3-D Temporal Medical Imaging Data
| Title | ChronoMID - Cross-Modal Neural Networks for 3-D Temporal Medical Imaging Data |
| Authors | Alexander G. Rakowski, Petar Veličković, Enrico Dall’Ara, Pietro Liò |
| Abstract | ChronoMID builds on the success of cross-modal convolutional neural networks (X-CNNs), making the novel application of the technique to medical imaging data. Specifically, this paper presents and compares alternative approaches - timestamps and difference images - to incorporate temporal information for the classification of bone disease in mice, applied to micro-CT scans of mouse tibiae. Whilst much previous work on diseases and disease classification has been based on mathematical models incorporating domain expertise and the explicit encoding of assumptions, the approaches given here utilise the growing availability of computing resources to analyse large datasets and uncover subtle patterns in both space and time. After training on a balanced set of over 75000 images, all models incorporating temporal features outperformed a state-of-the-art CNN baseline on an unseen, balanced validation set comprising over 20000 images. The top-performing model achieved 99.54% accuracy, compared to 73.02% for the CNN baseline. |
| Tasks | |
| Published | 2019-01-12 |
| URL | http://arxiv.org/abs/1901.03906v1 |
| http://arxiv.org/pdf/1901.03906v1.pdf | |
| PWC | https://paperswithcode.com/paper/chronomid-cross-modal-neural-networks-for-3-d |
| Repo | |
| Framework | |
Leveraging Dependency Forest for Neural Medical Relation Extraction
| Title | Leveraging Dependency Forest for Neural Medical Relation Extraction |
| Authors | Linfeng Song, Yue Zhang, Daniel Gildea, Mo Yu, Zhiguo Wang, Jinsong Su |
| Abstract | Medical relation extraction discovers relations between entity mentions in text, such as research articles. For this task, dependency syntax has been recognized as a crucial source of features. Yet in the medical domain, 1-best parse trees suffer from relatively low accuracies, diminishing their usefulness. We investigate a method to alleviate this problem by utilizing dependency forests. Forests contain many possible decisions and therefore have higher recall but more noise compared with 1-best outputs. A graph neural network is used to represent the forests, automatically distinguishing the useful syntactic information from parsing noise. Results on two biomedical benchmarks show that our method outperforms the standard tree-based methods, giving the state-of-the-art results in the literature. |
| Tasks | Medical Relation Extraction, Relation Extraction |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04123v2 |
| https://arxiv.org/pdf/1911.04123v2.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-dependency-forest-for-neural-1 |
| Repo | |
| Framework | |
Variational Temporal Abstraction
| Title | Variational Temporal Abstraction |
| Authors | Taesup Kim, Sungjin Ahn, Yoshua Bengio |
| Abstract | We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state transition hierarchically. We also propose to apply this model to implement the jumpy-imagination ability in imagination-augmented agent-learning in order to improve the efficiency of the imagination. In experiments, we demonstrate that our proposed method can model 2D and 3D visual sequence datasets with interpretable temporal structure discovery and that its application to jumpy imagination enables more efficient agent-learning in a 3D navigation task. |
| Tasks | |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.00775v1 |
| https://arxiv.org/pdf/1910.00775v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-temporal-abstraction |
| Repo | |
| Framework | |
Using Semantic Role Knowledge for Relevance Ranking of Key Phrases inDocuments: An Unsupervised Approach
| Title | Using Semantic Role Knowledge for Relevance Ranking of Key Phrases inDocuments: An Unsupervised Approach |
| Authors | Prateeti Mohapatra, Neelamadhav Gantayat, Gargi B. Dasgupta |
| Abstract | In this paper, we investigate the integration of sentence position and semantic role of words in a PageRank system to build a key phrase ranking method. We present the evaluation results of our approach on three scientific articles. We show that semantic role information, when integrated with a PageRank system, can become a new lexical feature. Our approach had an overall improvement on all the data sets over the state-of-art baseline approaches. |
| Tasks | |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03313v1 |
| https://arxiv.org/pdf/1908.03313v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-semantic-role-knowledge-for-relevance |
| Repo | |
| Framework | |
A Probabilistic Generative Model of Linguistic Typology
| Title | A Probabilistic Generative Model of Linguistic Typology |
| Authors | Johannes Bjerva, Yova Kementchedjhieva, Ryan Cotterell, Isabelle Augenstein |
| Abstract | In the principles-and-parameters framework, the structural features of languages depend on parameters that may be toggled on or off, with a single parameter often dictating the status of multiple features. The implied covariance between features inspires our probabilisation of this line of linguistic inquiry—we develop a generative model of language based on exponential-family matrix factorisation. By modelling all languages and features within the same architecture, we show how structural similarities between languages can be exploited to predict typological features with near-perfect accuracy, outperforming several baselines on the task of predicting held-out features. Furthermore, we show that language embeddings pre-trained on monolingual text allow for generalisation to unobserved languages. This finding has clear practical and also theoretical implications: the results confirm what linguists have hypothesised, i.e.~that there are significant correlations between typological features and languages. |
| Tasks | |
| Published | 2019-03-26 |
| URL | https://arxiv.org/abs/1903.10950v3 |
| https://arxiv.org/pdf/1903.10950v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-probabilistic-generative-model-of |
| Repo | |
| Framework | |
RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection
| Title | RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection |
| Authors | Chao-Wei Huang, Ting-Rui Chiang, Shang-Yu Su, Yun-Nung Chen |
| Abstract | The response selection has been an emerging research topic due to the growing interest in dialogue modeling, where the goal of the task is to select an appropriate response for continuing dialogues. To further push the end-to-end dialogue model toward real-world scenarios, the seventh Dialog System Technology Challenge (DSTC7) proposed a challenging track based on real chatlog datasets. The competition focuses on dialogue modeling with several advanced characteristics: (1) natural language diversity, (2) capability of precisely selecting a proper response from a large set of candidates or the scenario without any correct answer, and (3) knowledge grounding. This paper introduces recurrent attention pooling networks (RAP-Net), a novel framework for response selection, which can well estimate the relevance between the dialogue contexts and the candidates. The proposed RAP-Net is shown to be effective and can be generalized across different datasets and settings in the DSTC7 experiments. |
| Tasks | |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.08905v1 |
| http://arxiv.org/pdf/1903.08905v1.pdf | |
| PWC | https://paperswithcode.com/paper/rap-net-recurrent-attention-pooling-networks |
| Repo | |
| Framework | |
SuPer: A Surgical Perception Framework for Endoscopic Tissue Manipulation with Surgical Robotics
| Title | SuPer: A Surgical Perception Framework for Endoscopic Tissue Manipulation with Surgical Robotics |
| Authors | Yang Li, Florian Richter, Jingpei Lu, Emily K. Funk, Ryan K. Orosco, Jianke Zhu, Michael C. Yip |
| Abstract | Traditional control and task automation have been successfully demonstrated in a variety of structured, controlled environments through the use of highly specialized modeled robotic systems in conjunction with multiple sensors. However, the application of autonomy in endoscopic surgery is very challenging, particularly in soft tissue work, due to the lack of high-quality images and the unpredictable, constantly deforming environment. In this work, we propose a novel surgical perception framework, SuPer, for surgical robotic control. This framework continuously collects 3D geometric information that allows for mapping a deformable surgical field while tracking rigid instruments within the field. To achieve this, a model-based tracker is employed to localize the surgical tool with a kinematic prior in conjunction with a model-free tracker to reconstruct the deformable environment and provide an estimated point cloud as a mapping of the environment. The proposed framework was implemented on the da Vinci Surgical System in real-time with an end-effector controller where the target configurations are set and regulated through the framework. Our proposed framework successfully completed soft tissue manipulation tasks with high accuracy. The demonstration of this novel framework is promising for the future of surgical autonomy. In addition, we provide our dataset for further surgical research. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.05405v2 |
| https://arxiv.org/pdf/1909.05405v2.pdf | |
| PWC | https://paperswithcode.com/paper/super-a-surgical-perception-framework-for |
| Repo | |
| Framework | |
Learning functionals via LSTM neural networks for predicting vessel dynamics in extreme sea states
| Title | Learning functionals via LSTM neural networks for predicting vessel dynamics in extreme sea states |
| Authors | José del Águila Ferrandis, Michael Triantafyllou, Chryssostomos Chryssostomidis, George Karniadakis |
| Abstract | Predicting motions of vessels in extreme sea states represents one of the most challenging problems in naval hydrodynamics. It involves computing complex nonlinear wave-body interactions, hence taxing heavily computational resources. Here, we put forward a new simulation paradigm by training recurrent type neural networks (RNNs) that take as input the stochastic wave elevation at a certain sea state and output the main vessel motions, e.g., pitch, heave and roll. We first compare the performance of standard RNNs versus GRU and LSTM neural networks (NNs) and show that LSTM NNs lead to the best performance. We then examine the testing error of two representative vessels, a catamaran in sea state 1 and a battleship in sea state 8. We demonstrate that good accuracy is achieved for both cases in predicting the vessel motions for unseen wave elevations. We train the NNs with expensive CFD simulations offline, but upon training, the prediction of the vessel dynamics online can be obtained at a fraction of a second. This work is motivated by the universal approximation theorem for functionals [1], and it is the first implementation of such theory to realistic engineering problems. |
| Tasks | |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.13382v1 |
| https://arxiv.org/pdf/1912.13382v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-functionals-via-lstm-neural-networks |
| Repo | |
| Framework | |
Evidence Propagation and Consensus Formation in Noisy Environments
| Title | Evidence Propagation and Consensus Formation in Noisy Environments |
| Authors | Michael Crosscombe, Jonathan Lawry, Palina Bartashevich |
| Abstract | We study the effectiveness of consensus formation in multi-agent systems where there is both belief updating based on direct evidence and also belief combination between agents. In particular, we consider the scenario in which a population of agents collaborate on the best-of-n problem where the aim is to reach a consensus about which is the best (alternatively, true) state from amongst a set of states, each with a different quality value (or level of evidence). Agents’ beliefs are represented within Dempster-Shafer theory by mass functions and we investigate the macro-level properties of four well-known belief combination operators for this multi-agent consensus formation problem: Dempster’s rule, Yager’s rule, Dubois & Prade’s operator and the averaging operator. The convergence properties of the operators are considered and simulation experiments are conducted for different evidence rates and noise levels. Results show that a combination of updating on direct evidence and belief combination between agents results in better consensus to the best state than does evidence updating alone. We also find that in this framework the operators are robust to noise. Broadly, Yager’s rule is shown to be the better operator under various parameter values, i.e. convergence to the best state, robustness to noise, and scalability. |
| Tasks | |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.04840v2 |
| https://arxiv.org/pdf/1905.04840v2.pdf | |
| PWC | https://paperswithcode.com/paper/evidence-propagation-and-consensus-formation |
| Repo | |
| Framework | |
Gradient Boosted Feature Selection
| Title | Gradient Boosted Feature Selection |
| Authors | Zhixiang Eddie Xu, Gao Huang, Kilian Q. Weinberger, Alice X. Zheng |
| Abstract | A feature selection algorithm should ideally satisfy four conditions: reliably extract relevant features; be able to identify non-linear feature interactions; scale linearly with the number of features and dimensions; allow the incorporation of known sparsity structure. In this work we propose a novel feature selection algorithm, Gradient Boosted Feature Selection (GBFS), which satisfies all four of these requirements. The algorithm is flexible, scalable, and surprisingly straight-forward to implement as it is based on a modification of Gradient Boosted Trees. We evaluate GBFS on several real world data sets and show that it matches or out-performs other state of the art feature selection algorithms. Yet it scales to larger data set sizes and naturally allows for domain-specific side information. |
| Tasks | Feature Selection |
| Published | 2019-01-13 |
| URL | http://arxiv.org/abs/1901.04055v1 |
| http://arxiv.org/pdf/1901.04055v1.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-boosted-feature-selection |
| Repo | |
| Framework | |
Towards Combinational Relation Linking over Knowledge Graphs
| Title | Towards Combinational Relation Linking over Knowledge Graphs |
| Authors | Weiguo Zheng, Mei Zhang |
| Abstract | Given a natural language phrase, relation linking aims to find a relation (predicate or property) from the underlying knowledge graph to match the phrase. It is very useful in many applications, such as natural language question answering, personalized recommendation and text summarization. However, the previous relation linking algorithms usually produce a single relation for the input phrase and pay little attention to a more general and challenging problem, i.e., combinational relation linking that extracts a subgraph pattern to match the compound phrase (e.g. mother-in-law). In this paper, we focus on the task of combinational relation linking over knowledge graphs. To resolve the problem, we design a systematic method based on the data-driven relation assembly technique, which is performed under the guidance of meta patterns. We also introduce external knowledge to enhance the system understanding ability. Finally, we conduct extensive experiments over the real knowledge graph to study the performance of the proposed method. |
| Tasks | Knowledge Graphs, Question Answering, Text Summarization |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09879v2 |
| https://arxiv.org/pdf/1910.09879v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-combinational-relation-linking-over |
| Repo | |
| Framework | |
D-Point Trigonometric Path Planning based on Q-Learning in Uncertain Environments
| Title | D-Point Trigonometric Path Planning based on Q-Learning in Uncertain Environments |
| Authors | Ehsan Jeihaninejad, Azam Rabiee |
| Abstract | Finding the optimum path for a robot for moving from start to the goal position through obstacles is still a challenging issue. This paper presents a novel path planning method, named D-point trigonometric, based on Q-learning algorithm for dynamic and uncertain environments, in which all the obstacles and the target are moving. We define a new state, action and reward functions for the Q-learning by which the agent can find the best action in every state to reach the goal in the most appropriate path. The D-point approach minimizes the possible number of states. Moreover, the experiments in Unity3D confirmed the high convergence speed, the high hit rate, as well as the low dependency on environmental parameters of the proposed method compared with an opponent approach. |
| Tasks | Q-Learning |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12020v1 |
| https://arxiv.org/pdf/1910.12020v1.pdf | |
| PWC | https://paperswithcode.com/paper/d-point-trigonometric-path-planning-based-on |
| Repo | |
| Framework | |
Deep Hierarchical Reinforcement Learning Based Recommendations via Multi-goals Abstraction
| Title | Deep Hierarchical Reinforcement Learning Based Recommendations via Multi-goals Abstraction |
| Authors | Dongyang Zhao, Liang Zhang, Bo Zhang, Lizhou Zheng, Yongjun Bao, Weipeng Yan |
| Abstract | The recommender system is an important form of intelligent application, which assists users to alleviate from information redundancy. Among the metrics used to evaluate a recommender system, the metric of conversion has become more and more important. The majority of existing recommender systems perform poorly on the metric of conversion due to its extremely sparse feedback signal. To tackle this challenge, we propose a deep hierarchical reinforcement learning based recommendation framework, which consists of two components, i.e., high-level agent and low-level agent. The high-level agent catches long-term sparse conversion signals, and automatically sets abstract goals for low-level agent, while the low-level agent follows the abstract goals and interacts with real-time environment. To solve the inherent problem in hierarchical reinforcement learning, we propose a novel deep hierarchical reinforcement learning algorithm via multi-goals abstraction (HRL-MG). Our proposed algorithm contains three characteristics: 1) the high-level agent generates multiple goals to guide the low-level agent in different stages, which reduces the difficulty of approaching high-level goals; 2) different goals share the same state encoder parameters, which increases the update frequency of the high-level agent and thus accelerates the convergence of our proposed algorithm; 3) an appreciate benefit assignment function is designed to allocate rewards in each goal so as to coordinate different goals in a consistent direction. We evaluate our proposed algorithm based on a real-world e-commerce dataset and validate its effectiveness. |
| Tasks | Hierarchical Reinforcement Learning, Recommendation Systems |
| Published | 2019-03-22 |
| URL | http://arxiv.org/abs/1903.09374v1 |
| http://arxiv.org/pdf/1903.09374v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-hierarchical-reinforcement-learning-1 |
| Repo | |
| Framework | |
Mutual Linear Regression-based Discrete Hashing
| Title | Mutual Linear Regression-based Discrete Hashing |
| Authors | Xingbo Liu, Xiushan Nie, Yilong Yin |
| Abstract | Label information is widely used in hashing methods because of its effectiveness of improving the precision. The existing hashing methods always use two different projections to represent the mutual regression between hash codes and class labels. In contrast to the existing methods, we propose a novel learning-based hashing method termed stable supervised discrete hashing with mutual linear regression (S2DHMLR) in this study, where only one stable projection is used to describe the linear correlation between hash codes and corresponding labels. To the best of our knowledge, this strategy has not been used for hashing previously. In addition, we further use a boosting strategy to improve the final performance of the proposed method without adding extra constraints and with little extra expenditure in terms of time and space. Extensive experiments conducted on three image benchmarks demonstrate the superior performance of the proposed method. |
| Tasks | |
| Published | 2019-03-15 |
| URL | http://arxiv.org/abs/1904.00744v1 |
| http://arxiv.org/pdf/1904.00744v1.pdf | |
| PWC | https://paperswithcode.com/paper/mutual-linear-regression-based-discrete |
| Repo | |
| Framework | |
RLOC: Neurobiologically Inspired Hierarchical Reinforcement Learning Algorithm for Continuous Control of Nonlinear Dynamical Systems
| Title | RLOC: Neurobiologically Inspired Hierarchical Reinforcement Learning Algorithm for Continuous Control of Nonlinear Dynamical Systems |
| Authors | Ekaterina Abramova, Luke Dickens, Daniel Kuhn, Aldo Faisal |
| Abstract | Nonlinear optimal control problems are often solved with numerical methods that require knowledge of system’s dynamics which may be difficult to infer, and that carry a large computational cost associated with iterative calculations. We present a novel neurobiologically inspired hierarchical learning framework, Reinforcement Learning Optimal Control, which operates on two levels of abstraction and utilises a reduced number of controllers to solve nonlinear systems with unknown dynamics in continuous state and action spaces. Our approach is inspired by research at two levels of abstraction: first, at the level of limb coordination human behaviour is explained by linear optimal feedback control theory. Second, in cognitive tasks involving learning symbolic level action selection, humans learn such problems using model-free and model-based reinforcement learning algorithms. We propose that combining these two levels of abstraction leads to a fast global solution of nonlinear control problems using reduced number of controllers. Our framework learns the local task dynamics from naive experience and forms locally optimal infinite horizon Linear Quadratic Regulators which produce continuous low-level control. A top-level reinforcement learner uses the controllers as actions and learns how to best combine them in state space while maximising a long-term reward. A single optimal control objective function drives high-level symbolic learning by providing training signals on desirability of each selected controller. We show that a small number of locally optimal linear controllers are able to solve global nonlinear control problems with unknown dynamics when combined with a reinforcement learner in this hierarchical framework. Our algorithm competes in terms of computational cost and solution quality with sophisticated control algorithms and we illustrate this with solutions to benchmark problems. |
| Tasks | Continuous Control, Hierarchical Reinforcement Learning |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.03064v1 |
| http://arxiv.org/pdf/1903.03064v1.pdf | |
| PWC | https://paperswithcode.com/paper/rloc-neurobiologically-inspired-hierarchical |
| Repo | |
| Framework | |
