Paper Group NANR 75
Detecting and Resolving Shell Nouns in German. Closing Brackets with Recurrent Neural Networks. Comparing Pretrained Multilingual Word Embeddings on an Ontology Alignment Task. Applications of NLG in practical conversational AI settings. Proceedings of the Workshop on NLG for Human–Robot Interaction. SHPR-Net: Deep Semantic Hand Pose Regression Fr …
Detecting and Resolving Shell Nouns in German
| Title | Detecting and Resolving Shell Nouns in German |
| Authors | Adam Roussel |
| Abstract | This paper describes the design and evaluation of a system for the automatic detection and resolution of shell nouns in German. Shell nouns are general nouns, such as fact, question, or problem, whose full interpretation relies on a content phrase located elsewhere in a text, which these nouns simultaneously serve to characterize and encapsulate. To accomplish this, the system uses a series of lexico-syntactic patterns in order to extract shell noun candidates and their content in parallel. Each pattern has its own classifier, which makes the final decision as to whether or not a link is to be established and the shell noun resolved. Overall, about 26.2{%} of the annotated shell noun instances were correctly identified by the system, and of these cases, about 72.5{%} are assigned the correct content phrase. Though it remains difficult to identify shell noun instances reliably (recall is accordingly low in this regard), this system usually assigns the right content to correctly classified cases. cases. |
| Tasks | Question Answering, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0707/ |
| https://www.aclweb.org/anthology/W18-0707 | |
| PWC | https://paperswithcode.com/paper/detecting-and-resolving-shell-nouns-in-german |
| Repo | |
| Framework | |
Closing Brackets with Recurrent Neural Networks
| Title | Closing Brackets with Recurrent Neural Networks |
| Authors | Natalia Skachkova, Thomas Trost, Dietrich Klakow |
| Abstract | Many natural and formal languages contain words or symbols that require a matching counterpart for making an expression well-formed. The combination of opening and closing brackets is a typical example of such a construction. Due to their commonness, the ability to follow such rules is important for language modeling. Currently, recurrent neural networks (RNNs) are extensively used for this task. We investigate whether they are capable of learning the rules of opening and closing brackets by applying them to synthetic Dyck languages that consist of different types of brackets. We provide an analysis of the statistical properties of these languages as a baseline and show strengths and limits of Elman-RNNs, GRUs and LSTMs in experiments on random samples of these languages. In terms of perplexity and prediction accuracy, the RNNs get close to the theoretical baseline in most cases. |
| Tasks | Language Modelling |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5425/ |
| https://www.aclweb.org/anthology/W18-5425 | |
| PWC | https://paperswithcode.com/paper/closing-brackets-with-recurrent-neural |
| Repo | |
| Framework | |
Comparing Pretrained Multilingual Word Embeddings on an Ontology Alignment Task
| Title | Comparing Pretrained Multilingual Word Embeddings on an Ontology Alignment Task |
| Authors | Dagmar Gromann, Thierry Declerck |
| Abstract | |
| Tasks | Multilingual Word Embeddings, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1034/ |
| https://www.aclweb.org/anthology/L18-1034 | |
| PWC | https://paperswithcode.com/paper/comparing-pretrained-multilingual-word |
| Repo | |
| Framework | |
Applications of NLG in practical conversational AI settings
| Title | Applications of NLG in practical conversational AI settings |
| Authors | S Wubben, er |
| Abstract | |
| Tasks | Slot Filling, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6701/ |
| https://www.aclweb.org/anthology/W18-6701 | |
| PWC | https://paperswithcode.com/paper/applications-of-nlg-in-practical |
| Repo | |
| Framework | |
Proceedings of the Workshop on NLG for Human–Robot Interaction
| Title | Proceedings of the Workshop on NLG for Human–Robot Interaction |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6900/ |
| https://www.aclweb.org/anthology/W18-6900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-nlg-for |
| Repo | |
| Framework | |
SHPR-Net: Deep Semantic Hand Pose Regression From Point Clouds
| Title | SHPR-Net: Deep Semantic Hand Pose Regression From Point Clouds |
| Authors | Xinghao Chen, Guijin Wang, Cairong Zhang, Tae-Kyun Kim, Xiangyang Ji |
| Abstract | 3D hand pose estimation is an essential problem for human computer interaction. Most of the existing depth-based hand pose estimation methods consume 2D depth map or 3D volume via 2D/3D convolutional neural networks (CNNs). In this paper, we propose a deep Semantic Hand Pose Regression network (SHPR-Net) for hand pose estimation from point sets, which consists of two subnetworks: a semantic segmentation subnetwork and a hand pose regression subnetwork. The semantic segmentation network assigns semantic labels for each point in the point set. The pose regression network integrates the semantic priors with both input and late fusion strategy and regresses the final hand pose. Two transformation matrices are learned from the point set and applied to transform the input point cloud and inversely transform the output pose respectively, which makes the SHPR-Net more robust to geometric transformations. Experiments on NYU, ICVL and MSRA hand pose datasets demonstrate that our SHPRNet achieves high performance on par with start-of-the-art methods. We also show that our method can be naturally extended to hand pose estimation from multi-view depth data and achieves further improvement on NYU dataset. |
| Tasks | Hand Pose Estimation, Pose Estimation, Semantic Segmentation |
| Published | 2018-08-06 |
| URL | https://ieeexplore.ieee.org/document/8425735/ |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8425735&tag=1 | |
| PWC | https://paperswithcode.com/paper/shpr-net-deep-semantic-hand-pose-regression |
| Repo | |
| Framework | |
Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework
| Title | Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework |
| Authors | Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani, Tamas Keviczky |
| Abstract | Ordinary differential equations, and in general a dynamical system viewpoint, have seen a resurgence of interest in developing fast optimization methods, mainly thanks to the availability of well-established analysis tools. In this study, we pursue a similar objective and propose a class of hybrid control systems that adopts a 2nd-order differential equation as its continuous flow. A distinctive feature of the proposed differential equation in comparison with the existing literature is a state-dependent, time-invariant damping term that acts as a feedback control input. Given a user-defined scalar $\alpha$, it is shown that the proposed control input steers the state trajectories to the global optimizer of a desired objective function with a guaranteed rate of convergence $\mathcal{O}(e^{-\alpha t})$. Our framework requires that the objective function satisfies the so called Polyak–{Ł}ojasiewicz inequality. Furthermore, a discretization method is introduced such that the resulting discrete dynamical system possesses an exponential rate of convergence. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2320 |
| http://proceedings.mlr.press/v80/kolarijani18a/kolarijani18a.pdf | |
| PWC | https://paperswithcode.com/paper/fast-gradient-based-methods-with-exponential |
| Repo | |
| Framework | |
DeepVS: A Deep Learning Based Video Saliency Prediction Approach
| Title | DeepVS: A Deep Learning Based Video Saliency Prediction Approach |
| Authors | Lai Jiang, Mai Xu, Tie Liu, Minglang Qiao, Zulin Wang |
| Abstract | In this paper, we propose a novel deep learning based video saliency prediction method, named DeepVS. Specifically, we establish a large-scale eye-tracking database of videos (LEDOV), which includes 32 subjects’ fixations on 538 videos. We find from LEDOV that human attention is more likely to be attracted by objects, particularly the moving objects or the moving parts of objects. Hence, an object-to-motion convolutional neural network (OM-CNN) is developed to predict the intra-frame saliency for DeepVS, which is composed of the objectness and motion subnets. In OM-CNN, cross-net mask and hierarchical feature normalization are proposed to combine the spatial features of the objectness subnet and the temporal features of the motion subnet. We further find from our database that there exists a temporal correlation of human attention with a smooth saliency transition across video frames. We thus propose saliency-structured convolutional long short-term memory (SS-ConvLSTM) network, using the extracted features from OM-CNN as the input. Consequently, the inter-frame saliency maps of a video can be generated, which consider both structured output with center-bias and cross-frame transitions of human attention maps. Finally, the experimental results show that DeepVS advances the state-of-the-art in video saliency prediction. |
| Tasks | Eye Tracking, Saliency Prediction |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Lai_Jiang_DeepVS_A_Deep_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Lai_Jiang_DeepVS_A_Deep_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deepvs-a-deep-learning-based-video-saliency |
| Repo | |
| Framework | |
Computing Kantorovich-Wasserstein Distances on d-dimensional histograms using (d+1)-partite graphs
| Title | Computing Kantorovich-Wasserstein Distances on d-dimensional histograms using (d+1)-partite graphs |
| Authors | Gennaro Auricchio, Federico Bassetti, Stefano Gualandi, Marco Veneroni |
| Abstract | This paper presents a novel method to compute the exact Kantorovich-Wasserstein distance between a pair of $d$-dimensional histograms having $n$ bins each. We prove that this problem is equivalent to an uncapacitated minimum cost flow problem on a $(d+1)$-partite graph with $(d+1)n$ nodes and $dn^{\frac{d+1}{d}}$ arcs, whenever the cost is separable along the principal $d$-dimensional directions. We show numerically the benefits of our approach by computing the Kantorovich-Wasserstein distance of order 2 among two sets of instances: gray scale images and $d$-dimensional biomedical histograms. On these types of instances, our approach is competitive with state-of-the-art optimal transport algorithms. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7821-computing-kantorovich-wasserstein-distances-on-d-dimensional-histograms-using-d1-partite-graphs |
| http://papers.nips.cc/paper/7821-computing-kantorovich-wasserstein-distances-on-d-dimensional-histograms-using-d1-partite-graphs.pdf | |
| PWC | https://paperswithcode.com/paper/computing-kantorovich-wasserstein-distances |
| Repo | |
| Framework | |
Constrained Cross-Entropy Method for Safe Reinforcement Learning
| Title | Constrained Cross-Entropy Method for Safe Reinforcement Learning |
| Authors | Min Wen, Ufuk Topcu |
| Abstract | We study a safe reinforcement learning problem in which the constraints are defined as the expected cost over finite-length trajectories. We propose a constrained cross-entropy-based method to solve this problem. The method explicitly tracks its performance with respect to constraint satisfaction and thus is well-suited for safety-critical applications. We show that the asymptotic behavior of the proposed algorithm can be almost-surely described by that of an ordinary differential equation. Then we give sufficient conditions on the properties of this differential equation to guarantee the convergence of the proposed algorithm. At last, we show with simulation experiments that the proposed algorithm can effectively learn feasible policies without assumptions on the feasibility of initial policies, even with non-Markovian objective functions and constraint functions. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7974-constrained-cross-entropy-method-for-safe-reinforcement-learning |
| http://papers.nips.cc/paper/7974-constrained-cross-entropy-method-for-safe-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-cross-entropy-method-for-safe |
| Repo | |
| Framework | |
Indoor RGB-D Compass From a Single Line and Plane
| Title | Indoor RGB-D Compass From a Single Line and Plane |
| Authors | Pyojin Kim, Brian Coltin, H. Jin Kim |
| Abstract | We propose a novel approach to estimate the three degrees of freedom (DoF) drift-free rotational motion of an RGB-D camera from only a single line and plane in the Manhattan world (MW). Previous approaches exploit the surface normal vectors and vanishing points to achieve accurate 3-DoF rotation estimation. However, they require multiple orthogonal planes or many consistent lines to be visible throughout the entire rotation estimation process; otherwise, these approaches fail. To overcome these limitations, we present a new method that estimates absolute camera orientation from only a single line and a single plane in RANSAC, which corresponds to the theoretical minimal sampling for 3-DoF rotation estimation. Once we find an initial rotation estimate, we refine the camera orientation by minimizing the average orthogonal distance from the endpoints of the lines parallel to the MW axes. We demonstrate the effectiveness of the proposed algorithm through an extensive evaluation on a variety of RGB-D datasets and compare with other state-of-the-art methods. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Kim_Indoor_RGB-D_Compass_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Kim_Indoor_RGB-D_Compass_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/indoor-rgb-d-compass-from-a-single-line-and |
| Repo | |
| Framework | |
From sensors to sense: Integrated heterogeneous ontologies for Natural Language Generation
| Title | From sensors to sense: Integrated heterogeneous ontologies for Natural Language Generation |
| Authors | Mihai Pomarlan, Robert Porzel, John Bateman, Rainer Malaka |
| Abstract | We propose the combination of a robotics ontology (KnowRob) with a linguistically motivated one (GUM) under the upper ontology DUL. We use the DUL Event, Situation, Description pattern to formalize reasoning techniques to convert between a robot{'}s beliefstate and its linguistic utterances. We plan to employ these techniques to equip robots with a reason-aloud ability, through which they can explain their actions as they perform them, in natural language, at a level of granularity appropriate to the user, their query and the context at hand. |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6904/ |
| https://www.aclweb.org/anthology/W18-6904 | |
| PWC | https://paperswithcode.com/paper/from-sensors-to-sense-integrated |
| Repo | |
| Framework | |
Finding “It”: Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos
| Title | Finding “It”: Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos |
| Authors | De-An Huang, Shyamal Buch, Lucio Dery, Animesh Garg, Li Fei-Fei, Juan Carlos Niebles |
| Abstract | Grounding textual phrases in visual content with standalone image-sentence pairs is a challenging task. When we consider grounding in instructional videos, this problem becomes profoundly more complex: the latent temporal structure of instructional videos breaks independence assumptions and necessitates contextual understanding for resolving ambiguous visual-linguistic cues. Furthermore, dense annotations and video data scale mean supervised approaches are prohibitively costly. In this work, we propose to tackle this new task with a weakly-supervised framework for reference-aware visual grounding in instructional videos, where only the temporal alignment between the transcription and the video segment are available for supervision. We introduce the visually grounded action graph, a structured representation capturing the latent dependency between grounding and references in video. For optimization, we propose a new reference-aware multiple instance learning (RA-MIL) objective for weak supervision of grounding in videos. We evaluate our approach over unconstrained videos from YouCookII and RoboWatch, augmented with new reference-grounding test set annotations. We demonstrate that our jointly optimized, reference-aware approach simultaneously improves visual grounding, reference-resolution, and generalization to unseen instructional video categories. |
| Tasks | Multiple Instance Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Huang_Finding_It_Weakly-Supervised_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Finding_It_Weakly-Supervised_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/finding-it-weakly-supervised-reference-aware |
| Repo | |
| Framework | |
Normalization in Context: Inter-Annotator Agreement for Meaning-Based Target Hypothesis Annotation
| Title | Normalization in Context: Inter-Annotator Agreement for Meaning-Based Target Hypothesis Annotation |
| Authors | Adriane Boyd |
| Abstract | |
| Tasks | Reading Comprehension |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-7102/ |
| https://www.aclweb.org/anthology/W18-7102 | |
| PWC | https://paperswithcode.com/paper/normalization-in-context-inter-annotator |
| Repo | |
| Framework | |
Long Term Memory Network for Combinatorial Optimization Problems
| Title | Long Term Memory Network for Combinatorial Optimization Problems |
| Authors | Hazem A. A. Nomer, Abdallah Aboutahoun, Ashraf Elsayed |
| Abstract | This paper introduces a framework for solving combinatorial optimization problems by learning from input-output examples of optimization problems. We introduce a new memory augmented neural model in which the memory is not resettable (i.e the information stored in the memory after processing an input example is kept for the next seen examples). We used deep reinforcement learning to train a memory controller agent to store useful memories. Our model was able to outperform hand-crafted solver on Binary Linear Programming (Binary LP). The proposed model is tested on different Binary LP instances with large number of variables (up to 1000 variables) and constrains (up to 700 constrains). |
| Tasks | Combinatorial Optimization |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=Bk_fs6gA- |
| https://openreview.net/pdf?id=Bk_fs6gA- | |
| PWC | https://paperswithcode.com/paper/long-term-memory-network-for-combinatorial |
| Repo | |
| Framework | |
