Paper Group ANR 85
UMDSub at SemEval-2018 Task 2: Multilingual Emoji Prediction Multi-channel Convolutional Neural Network on Subword Embedding. UniMorph 2.0: Universal Morphology. Abstractive Text Summarization by Incorporating Reader Comments. Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces. From probabilistic graphical mod …
UMDSub at SemEval-2018 Task 2: Multilingual Emoji Prediction Multi-channel Convolutional Neural Network on Subword Embedding
| Title | UMDSub at SemEval-2018 Task 2: Multilingual Emoji Prediction Multi-channel Convolutional Neural Network on Subword Embedding |
| Authors | Zhenduo Wang, Ted Pedersen |
| Abstract | This paper describes the UMDSub system that participated in Task 2 of SemEval-2018. We developed a system that predicts an emoji given the raw text in a English tweet. The system is a Multi-channel Convolutional Neural Network based on subword embeddings for the representation of tweets. This model improves on character or word based methods by about 2%. Our system placed 21st of 48 participating systems in the official evaluation. |
| Tasks | |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.10274v1 |
| http://arxiv.org/pdf/1805.10274v1.pdf | |
| PWC | https://paperswithcode.com/paper/umdsub-at-semeval-2018-task-2-multilingual |
| Repo | |
| Framework | |
UniMorph 2.0: Universal Morphology
| Title | UniMorph 2.0: Universal Morphology |
| Authors | Christo Kirov, Ryan Cotterell, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sabrina J. Mielke, Arya D. McCarthy, Sandra Kübler, David Yarowsky, Jason Eisner, Mans Hulden |
| Abstract | The Universal Morphology UniMorph project is a collaborative effort to improve how NLP handles complex morphology across the world’s languages. The project releases annotated morphological data using a universal tagset, the UniMorph schema. Each inflected form is associated with a lemma, which typically carries its underlying lexical meaning, and a bundle of morphological features from our schema. Additional supporting data and tools are also released on a per-language basis when available. UniMorph is based at the Center for Language and Speech Processing (CLSP) at Johns Hopkins University in Baltimore, Maryland and is sponsored by the DARPA LORELEI program. This paper details advances made to the collection, annotation, and dissemination of project resources since the initial UniMorph release described at LREC 2016. lexical resources} } |
| Tasks | |
| Published | 2018-10-25 |
| URL | https://arxiv.org/abs/1810.11101v2 |
| https://arxiv.org/pdf/1810.11101v2.pdf | |
| PWC | https://paperswithcode.com/paper/unimorph-20-universal-morphology |
| Repo | |
| Framework | |
Abstractive Text Summarization by Incorporating Reader Comments
| Title | Abstractive Text Summarization by Incorporating Reader Comments |
| Authors | Shen Gao, Xiuying Chen, Piji Li, Zhaochun Ren, Lidong Bing, Dongyan Zhao, Rui Yan |
| Abstract | In neural abstractive summarization field, conventional sequence-to-sequence based models often suffer from summarizing the wrong aspect of the document with respect to the main aspect. To tackle this problem, we propose the task of reader-aware abstractive summary generation, which utilizes the reader comments to help the model produce better summary about the main aspect. Unlike traditional abstractive summarization task, reader-aware summarization confronts two main challenges: (1) Comments are informal and noisy; (2) jointly modeling the news document and the reader comments is challenging. To tackle the above challenges, we design an adversarial learning model named reader-aware summary generator (RASG), which consists of four components: (1) a sequence-to-sequence based summary generator; (2) a reader attention module capturing the reader focused aspects; (3) a supervisor modeling the semantic gap between the generated summary and reader focused aspects; (4) a goal tracker producing the goal for each generation step. The supervisor and the goal tacker are used to guide the training of our framework in an adversarial manner. Extensive experiments are conducted on our large-scale real-world text summarization dataset, and the results show that RASG achieves the state-of-the-art performance in terms of both automatic metrics and human evaluations. The experimental results also demonstrate the effectiveness of each module in our framework. We release our large-scale dataset for further research. |
| Tasks | Abstractive Text Summarization, Reader-Aware Summarization, Text Summarization |
| Published | 2018-12-13 |
| URL | http://arxiv.org/abs/1812.05407v1 |
| http://arxiv.org/pdf/1812.05407v1.pdf | |
| PWC | https://paperswithcode.com/paper/abstractive-text-summarization-by |
| Repo | |
| Framework | |
Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces
| Title | Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces |
| Authors | Isabelle Augenstein, Sebastian Ruder, Anders Søgaard |
| Abstract | We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of sequence classification tasks with disparate label spaces. We outperform strong single and multi-task baselines and achieve a new state-of-the-art for topic-based sentiment analysis. |
| Tasks | Multi-Task Learning, Sentiment Analysis |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.09913v2 |
| http://arxiv.org/pdf/1802.09913v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-of-pairwise-sequence |
| Repo | |
| Framework | |
From probabilistic graphical models to generalized tensor networks for supervised learning
| Title | From probabilistic graphical models to generalized tensor networks for supervised learning |
| Authors | Ivan Glasser, Nicola Pancotti, J. Ignacio Cirac |
| Abstract | Tensor networks have found a wide use in a variety of applications in physics and computer science, recently leading to both theoretical insights as well as practical algorithms in machine learning. In this work we explore the connection between tensor networks and probabilistic graphical models, and show that it motivates the definition of generalized tensor networks where information from a tensor can be copied and reused in other parts of the network. We discuss the relationship between generalized tensor network architectures used in quantum physics, such as string-bond states, and architectures commonly used in machine learning. We provide an algorithm to train these networks in a supervised-learning context and show that they overcome the limitations of regular tensor networks in higher dimensions, while keeping the computation efficient. A method to combine neural networks and tensor networks as part of a common deep learning architecture is also introduced. We benchmark our algorithm for several generalized tensor network architectures on the task of classifying images and sounds, and show that they outperform previously introduced tensor-network algorithms. The models we consider also have a natural implementation on a quantum computer and may guide the development of near-term quantum machine learning architectures. |
| Tasks | Quantum Machine Learning, Tensor Networks |
| Published | 2018-06-15 |
| URL | https://arxiv.org/abs/1806.05964v2 |
| https://arxiv.org/pdf/1806.05964v2.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-learning-with-generalized-tensor |
| Repo | |
| Framework | |
Amnestic Forgery: an Ontology of Conceptual Metaphors
| Title | Amnestic Forgery: an Ontology of Conceptual Metaphors |
| Authors | Aldo Gangemi, Mehwish Alam, Valentina Presutti |
| Abstract | This paper presents Amnestic Forgery, an ontology for metaphor semantics, based on MetaNet, which is inspired by the theory of Conceptual Metaphor. Amnestic Forgery reuses and extends the Framester schema, as an ideal ontology design framework to deal with both semiotic and referential aspects of frames, roles, mappings, and eventually blending. The description of the resource is supplied by a discussion of its applications, with examples taken from metaphor generation, and the referential problems of metaphoric mappings. Both schema and data are available from the Framester SPARQL endpoint. |
| Tasks | |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.12115v1 |
| http://arxiv.org/pdf/1805.12115v1.pdf | |
| PWC | https://paperswithcode.com/paper/amnestic-forgery-an-ontology-of-conceptual |
| Repo | |
| Framework | |
Towards Quantum Machine Learning with Tensor Networks
| Title | Towards Quantum Machine Learning with Tensor Networks |
| Authors | William Huggins, Piyush Patel, K. Birgitta Whaley, E. Miles Stoudenmire |
| Abstract | Machine learning is a promising application of quantum computing, but challenges remain as near-term devices will have a limited number of physical qubits and high error rates. Motivated by the usefulness of tensor networks for machine learning in the classical context, we propose quantum computing approaches to both discriminative and generative learning, with circuits based on tree and matrix product state tensor networks that could have benefits for near-term devices. The result is a unified framework where classical and quantum computing can benefit from the same theoretical and algorithmic developments, and the same model can be trained classically then transferred to the quantum setting for additional optimization. Tensor network circuits can also provide qubit-efficient schemes where, depending on the architecture, the number of physical qubits required scales only logarithmically with, or independently of the input or output data sizes. We demonstrate our proposals with numerical experiments, training a discriminative model to perform handwriting recognition using a optimization procedure that could be carried out on quantum hardware, and testing the noise resilience of the trained model. |
| Tasks | Quantum Machine Learning, Tensor Networks |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11537v2 |
| http://arxiv.org/pdf/1803.11537v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-quantum-machine-learning-with-tensor |
| Repo | |
| Framework | |
Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networks
| Title | Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networks |
| Authors | Christian Stab, Tristan Miller, Iryna Gurevych |
| Abstract | Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches to argument mining are designed for use only with specific text types and fall short when applied to heterogeneous texts. In this paper, we propose a new sentential annotation scheme that is reliably applicable by crowd workers to arbitrary Web texts. We source annotations for over 25,000 instances covering eight controversial topics. The results of cross-topic experiments show that our attention-based neural network generalizes best to unseen topics and outperforms vanilla BiLSTM models by 6% in accuracy and 11% in F-score. |
| Tasks | Argument Mining |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1802.05758v1 |
| http://arxiv.org/pdf/1802.05758v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-topic-argument-mining-from |
| Repo | |
| Framework | |
Distributed $k$-Clustering for Data with Heavy Noise
| Title | Distributed $k$-Clustering for Data with Heavy Noise |
| Authors | Xiangyu Guo, Shi Li |
| Abstract | In this paper, we consider the $k$-center/median/means clustering with outliers problems (or the $(k, z)$-center/median/means problems) in the distributed setting. Most previous distributed algorithms have their communication costs linearly depending on $z$, the number of outliers. Recently Guha et al. overcame this dependence issue by considering bi-criteria approximation algorithms that output solutions with $2z$ outliers. For the case where $z$ is large, the extra $z$ outliers discarded by the algorithms might be too large, considering that the data gathering process might be costly. In this paper, we improve the number of outliers to the best possible $(1+\epsilon)z$, while maintaining the $O(1)$-approximation ratio and independence of communication cost on $z$. The problems we consider include the $(k, z)$-center problem, and $(k, z)$-median/means problems in Euclidean metrics. Implementation of the our algorithm for $(k, z)$-center shows that it outperforms many previous algorithms, both in terms of the communication cost and quality of the output solution. |
| Tasks | |
| Published | 2018-10-18 |
| URL | http://arxiv.org/abs/1810.07852v2 |
| http://arxiv.org/pdf/1810.07852v2.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-k-clustering-for-data-with-heavy |
| Repo | |
| Framework | |
Robust Super-Level Set Estimation using Gaussian Processes
| Title | Robust Super-Level Set Estimation using Gaussian Processes |
| Authors | Andrea Zanette, Junzi Zhang, Mykel J. Kochenderfer |
| Abstract | This paper focuses on the problem of determining as large a region as possible where a function exceeds a given threshold with high probability. We assume that we only have access to a noise-corrupted version of the function and that function evaluations are costly. To select the next query point, we propose maximizing the expected volume of the domain identified as above the threshold as predicted by a Gaussian process, robustified by a variance term. We also give asymptotic guarantees on the exploration effect of the algorithm, regardless of the prior misspecification. We show by various numerical examples that our approach also outperforms existing techniques in the literature in practice. |
| Tasks | Gaussian Processes |
| Published | 2018-11-25 |
| URL | http://arxiv.org/abs/1811.09977v1 |
| http://arxiv.org/pdf/1811.09977v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-super-level-set-estimation-using |
| Repo | |
| Framework | |
Safe Navigation with Human Instructions in Complex Scenes
| Title | Safe Navigation with Human Instructions in Complex Scenes |
| Authors | Zhe Hu, Jia Pan, Tingxiang Fan, Ruigang Yang, Dinesh Manocha |
| Abstract | In this paper, we present a robotic navigation algorithm with natural language interfaces, which enables a robot to safely walk through a changing environment with moving persons by following human instructions such as “go to the restaurant and keep away from people”. We first classify human instructions into three types: the goal, the constraints, and uninformative phrases. Next, we provide grounding for the extracted goal and constraint items in a dynamic manner along with the navigation process, to deal with the target objects that are too far away for sensor observation and the appearance of moving obstacles like humans. In particular, for a goal phrase (e.g., “go to the restaurant”), we ground it to a location in a predefined semantic map and treat it as a goal for a global motion planner, which plans a collision-free path in the workspace for the robot to follow. For a constraint phrase (e.g., “keep away from people”), we dynamically add the corresponding constraint into a local planner by adjusting the values of a local costmap according to the results returned by the object detection module. The updated costmap is then used to compute a local collision avoidance control for the safe navigation of the robot. By combining natural language processing, motion planning, and computer vision, our developed system is demonstrated to be able to successfully follow natural language navigation instructions to achieve navigation tasks in both simulated and real-world scenarios. Videos are available at https://sites.google.com/view/snhi |
| Tasks | Motion Planning, Object Detection |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04280v1 |
| http://arxiv.org/pdf/1809.04280v1.pdf | |
| PWC | https://paperswithcode.com/paper/safe-navigation-with-human-instructions-in |
| Repo | |
| Framework | |
NIPS - Not Even Wrong? A Systematic Review of Empirically Complete Demonstrations of Algorithmic Effectiveness in the Machine Learning and Artificial Intelligence Literature
| Title | NIPS - Not Even Wrong? A Systematic Review of Empirically Complete Demonstrations of Algorithmic Effectiveness in the Machine Learning and Artificial Intelligence Literature |
| Authors | Franz J Király, Bilal Mateen, Raphael Sonabend |
| Abstract | Objective: To determine the completeness of argumentative steps necessary to conclude effectiveness of an algorithm in a sample of current ML/AI supervised learning literature. Data Sources: Papers published in the Neural Information Processing Systems (NeurIPS, n'ee NIPS) journal where the official record showed a 2017 year of publication. Eligibility Criteria: Studies reporting a (semi-)supervised model, or pre-processing fused with (semi-)supervised models for tabular data. Study Appraisal: Three reviewers applied the assessment criteria to determine argumentative completeness. The criteria were split into three groups, including: experiments (e.g real and/or synthetic data), baselines (e.g uninformed and/or state-of-art) and quantitative comparison (e.g. performance quantifiers with confidence intervals and formal comparison of the algorithm against baselines). Results: Of the 121 eligible manuscripts (from the sample of 679 abstracts), 99% used real-world data and 29% used synthetic data. 91% of manuscripts did not report an uninformed baseline and 55% reported a state-of-art baseline. 32% reported confidence intervals for performance but none provided references or exposition for how these were calculated. 3% reported formal comparisons. Limitations: The use of one journal as the primary information source may not be representative of all ML/AI literature. However, the NeurIPS conference is recognised to be amongst the top tier concerning ML/AI studies, so it is reasonable to consider its corpus to be representative of high-quality research. Conclusion: Using the 2017 sample of the NeurIPS supervised learning corpus as an indicator for the quality and trustworthiness of current ML/AI research, it appears that complete argumentative chains in demonstrations of algorithmic effectiveness are rare. |
| Tasks | |
| Published | 2018-12-18 |
| URL | http://arxiv.org/abs/1812.07519v1 |
| http://arxiv.org/pdf/1812.07519v1.pdf | |
| PWC | https://paperswithcode.com/paper/nips-not-even-wrong-a-systematic-review-of |
| Repo | |
| Framework | |
Adaptive Extreme Learning Machine for Recurrent Beta-basis Function Neural Network Training
| Title | Adaptive Extreme Learning Machine for Recurrent Beta-basis Function Neural Network Training |
| Authors | Naima Chouikhi, Adel M. Alimi |
| Abstract | Beta Basis Function Neural Network (BBFNN) is a special kind of kernel basis neural networks. It is a feedforward network typified by the use of beta function as a hidden activation function. Beta is a flexible transfer function representing richer forms than the common existing functions. As in every network, the architecture setting as well as the learning method are two main gauntlets faced by BBFNN. In this paper, new architecture and training algorithm are proposed for the BBFNN. An Extreme Learning Machine (ELM) is used as a training approach of BBFNN with the aim of quickening the training process. The peculiarity of ELM is permitting a certain decrement of the computing time and complexity regarding the already used BBFNN learning algorithms such as backpropagation, OLS, etc. For the architectural design, a recurrent structure is added to the common BBFNN architecture in order to make it more able to deal with complex, non linear and time varying problems. Throughout this paper, the conceived recurrent ELM-trained BBFNN is tested on a number of tasks related to time series prediction, classification and regression. Experimental results show noticeable achievements of the proposed network compared to common feedforward and recurrent networks trained by ELM and using hyperbolic tangent as activation function. These achievements are in terms of accuracy and robustness against data breakdowns such as noise signals. |
| Tasks | Time Series, Time Series Prediction |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1810.13135v1 |
| http://arxiv.org/pdf/1810.13135v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-extreme-learning-machine-for |
| Repo | |
| Framework | |
Face Recognition Based on Sequence of Images
| Title | Face Recognition Based on Sequence of Images |
| Authors | Jacek Komorowski, Przemyslaw Rokita |
| Abstract | This paper presents a face recognition method based on a sequence of images. Face shape is reconstructed from images using a combination of structure-from-motion and multi-view stereo methods. The reconstructed 3D face model is compared against models held in a gallery. The novel element in the presented approach is the fact, that the reconstruction is based only on input images and doesn’t require a generic, deformable face model. Experimental verification of the proposed method is also included. |
| Tasks | Face Recognition |
| Published | 2018-09-28 |
| URL | http://arxiv.org/abs/1809.11069v1 |
| http://arxiv.org/pdf/1809.11069v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-recognition-based-on-sequence-of-images |
| Repo | |
| Framework | |
Generative Models for Stochastic Processes Using Convolutional Neural Networks
| Title | Generative Models for Stochastic Processes Using Convolutional Neural Networks |
| Authors | Fernando Fernandes Neto |
| Abstract | The present paper aims to demonstrate the usage of Convolutional Neural Networks as a generative model for stochastic processes, enabling researchers from a wide range of fields (such as quantitative finance and physics) to develop a general tool for forecasts and simulations without the need to identify/assume a specific system structure or estimate its parameters. |
| Tasks | |
| Published | 2018-01-09 |
| URL | http://arxiv.org/abs/1801.03523v1 |
| http://arxiv.org/pdf/1801.03523v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-models-for-stochastic-processes |
| Repo | |
| Framework | |
