Paper Group ANR 254
Word Sense Disambiguation using a Bidirectional LSTM. Spectral community detection in heterogeneous large networks. Ground Truth Bias in External Cluster Validity Indices. Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization. Probabilistic Modeling of Progressive Filtering. PrASP Report. State Space representation of non-stati …
Word Sense Disambiguation using a Bidirectional LSTM
| Title | Word Sense Disambiguation using a Bidirectional LSTM |
| Authors | Mikael Kågebäck, Hans Salomonsson |
| Abstract | In this paper we present a clean, yet effective, model for word sense disambiguation. Our approach leverage a bidirectional long short-term memory network which is shared between all words. This enables the model to share statistical strength and to scale well with vocabulary size. The model is trained end-to-end, directly from the raw text to sense labels, and makes effective use of word order. We evaluate our approach on two standard datasets, using identical hyperparameter settings, which are in turn tuned on a third set of held out data. We employ no external resources (e.g. knowledge graphs, part-of-speech tagging, etc), language specific features, or hand crafted rules, but still achieve statistically equivalent results to the best state-of-the-art systems, that employ no such limitations. |
| Tasks | Word Sense Disambiguation |
| Published | 2016-06-11 |
| URL | http://arxiv.org/abs/1606.03568v2 |
| http://arxiv.org/pdf/1606.03568v2.pdf | |
| PWC | https://paperswithcode.com/paper/word-sense-disambiguation-using-a |
| Repo | |
| Framework | |
Spectral community detection in heterogeneous large networks
| Title | Spectral community detection in heterogeneous large networks |
| Authors | Hafiz Tiomoko Ali, Romain Couillet |
| Abstract | In this article, we study spectral methods for community detection based on $ \alpha$-parametrized normalized modularity matrix hereafter called $ {\bf L}\alpha $ in heterogeneous graph models. We show, in a regime where community detection is not asymptotically trivial, that $ {\bf L}\alpha $ can be well approximated by a more tractable random matrix which falls in the family of spiked random matrices. The analysis of this equivalent spiked random matrix allows us to improve spectral methods for community detection and assess their performances in the regime under study. In particular, we prove the existence of an optimal value $ \alpha_{\rm opt} $ of the parameter $ \alpha $ for which the detection of communities is best ensured and we provide an on-line estimation of $ \alpha_{\rm opt} $ only based on the knowledge of the graph adjacency matrix. Unlike classical spectral methods for community detection where clustering is performed on the eigenvectors associated with extreme eigenvalues, we show through our theoretical analysis that a regularization should instead be performed on those eigenvectors prior to clustering in heterogeneous graphs. Finally, through a deeper study of the regularized eigenvectors used for clustering, we assess the performances of our new algorithm for community detection. Numerical simulations in the course of the article show that our methods outperform state-of-the-art spectral methods on dense heterogeneous graphs. |
| Tasks | Community Detection |
| Published | 2016-11-03 |
| URL | http://arxiv.org/abs/1611.01096v1 |
| http://arxiv.org/pdf/1611.01096v1.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-community-detection-in-heterogeneous |
| Repo | |
| Framework | |
Ground Truth Bias in External Cluster Validity Indices
| Title | Ground Truth Bias in External Cluster Validity Indices |
| Authors | Yang Lei, James C. Bezdek, Simone Romano, Nguyen Xuan Vinh, Jeffrey Chan, James Bailey |
| Abstract | It has been noticed that some external CVIs exhibit a preferential bias towards a larger or smaller number of clusters which is monotonic (directly or inversely) in the number of clusters in candidate partitions. This type of bias is caused by the functional form of the CVI model. For example, the popular Rand index (RI) exhibits a monotone increasing (NCinc) bias, while the Jaccard Index (JI) index suffers from a monotone decreasing (NCdec) bias. This type of bias has been previously recognized in the literature. In this work, we identify a new type of bias arising from the distribution of the ground truth (reference) partition against which candidate partitions are compared. We call this new type of bias ground truth (GT) bias. This type of bias occurs if a change in the reference partition causes a change in the bias status (e.g., NCinc, NCdec) of a CVI. For example, NCinc bias in the RI can be changed to NCdec bias by skewing the distribution of clusters in the ground truth partition. It is important for users to be aware of this new type of biased behaviour, since it may affect the interpretations of CVI results. The objective of this article is to study the empirical and theoretical implications of GT bias. To the best of our knowledge, this is the first extensive study of such a property for external cluster validity indices. |
| Tasks | |
| Published | 2016-06-17 |
| URL | http://arxiv.org/abs/1606.05596v1 |
| http://arxiv.org/pdf/1606.05596v1.pdf | |
| PWC | https://paperswithcode.com/paper/ground-truth-bias-in-external-cluster |
| Repo | |
| Framework | |
Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
| Title | Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization |
| Authors | Chelsea Finn, Sergey Levine, Pieter Abbeel |
| Abstract | Reinforcement learning can acquire complex behaviors from high-level specifications. However, defining a cost function that can be optimized effectively and encodes the correct task is challenging in practice. We explore how inverse optimal control (IOC) can be used to learn behaviors from demonstrations, with applications to torque control of high-dimensional robotic systems. Our method addresses two key challenges in inverse optimal control: first, the need for informative features and effective regularization to impose structure on the cost, and second, the difficulty of learning the cost function under unknown dynamics for high-dimensional continuous systems. To address the former challenge, we present an algorithm capable of learning arbitrary nonlinear cost functions, such as neural networks, without meticulous feature engineering. To address the latter challenge, we formulate an efficient sample-based approximation for MaxEnt IOC. We evaluate our method on a series of simulated tasks and real-world robotic manipulation problems, demonstrating substantial improvement over prior methods both in terms of task complexity and sample efficiency. |
| Tasks | Feature Engineering |
| Published | 2016-03-01 |
| URL | http://arxiv.org/abs/1603.00448v3 |
| http://arxiv.org/pdf/1603.00448v3.pdf | |
| PWC | https://paperswithcode.com/paper/guided-cost-learning-deep-inverse-optimal |
| Repo | |
| Framework | |
Probabilistic Modeling of Progressive Filtering
| Title | Probabilistic Modeling of Progressive Filtering |
| Authors | Giuliano Armano |
| Abstract | Progressive filtering is a simple way to perform hierarchical classification, inspired by the behavior that most humans put into practice while attempting to categorize an item according to an underlying taxonomy. Each node of the taxonomy being associated with a different category, one may visualize the categorization process by looking at the item going downwards through all the nodes that accept it as belonging to the corresponding category. This paper is aimed at modeling the progressive filtering technique from a probabilistic perspective, in a hierarchical text categorization setting. As a result, the designer of a system based on progressive filtering should be facilitated in the task of devising, training, and testing it. |
| Tasks | Text Categorization |
| Published | 2016-11-03 |
| URL | http://arxiv.org/abs/1611.01080v1 |
| http://arxiv.org/pdf/1611.01080v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-modeling-of-progressive |
| Repo | |
| Framework | |
PrASP Report
| Title | PrASP Report |
| Authors | Matthias Nickles |
| Abstract | This technical report describes the usage, syntax, semantics and core algorithms of the probabilistic inductive logic programming framework PrASP. PrASP is a research software which integrates non-monotonic reasoning based on Answer Set Programming (ASP), probabilistic inference and parameter learning. In contrast to traditional approaches to Probabilistic (Inductive) Logic Programming, our framework imposes only little restrictions on probabilistic logic programs. In particular, PrASP allows for ASP as well as First-Order Logic syntax, and for the annotation of formulas with point probabilities as well as interval probabilities. A range of widely configurable inference algorithms can be combined in a pipeline-like fashion, in order to cover a variety of use cases. |
| Tasks | |
| Published | 2016-12-30 |
| URL | http://arxiv.org/abs/1612.09591v1 |
| http://arxiv.org/pdf/1612.09591v1.pdf | |
| PWC | https://paperswithcode.com/paper/prasp-report |
| Repo | |
| Framework | |
State Space representation of non-stationary Gaussian Processes
| Title | State Space representation of non-stationary Gaussian Processes |
| Authors | Alessio Benavoli, Marco Zaffalon |
| Abstract | The state space (SS) representation of Gaussian processes (GP) has recently gained a lot of interest. The main reason is that it allows to compute GPs based inferences in O(n), where $n$ is the number of observations. This implementation makes GPs suitable for Big Data. For this reason, it is important to provide a SS representation of the most important kernels used in machine learning. The aim of this paper is to show how to exploit the transient behaviour of SS models to map non-stationary kernels to SS models. |
| Tasks | Gaussian Processes |
| Published | 2016-01-07 |
| URL | http://arxiv.org/abs/1601.01544v1 |
| http://arxiv.org/pdf/1601.01544v1.pdf | |
| PWC | https://paperswithcode.com/paper/state-space-representation-of-non-stationary |
| Repo | |
| Framework | |
Digital Advertising Traffic Operation: Machine Learning for Process Discovery
| Title | Digital Advertising Traffic Operation: Machine Learning for Process Discovery |
| Authors | Massimiliano Dal Mas |
| Abstract | In a Web Advertising Traffic Operation it’s necessary to manage the day-to-day trafficking, pacing and optimization of digital and paid social campaigns. The data analyst on Traffic Operation can not only quickly provide answers but also speaks the language of the Process Manager and visually displays the discovered process problems. In order to solve a growing number of complaints in the customer service process, the weaknesses in the process itself must be identified and communicated to the department. With the help of Process Mining for the CRM data it is possible to identify unwanted loops and delays in the process. With this paper we propose a process discovery based on Machine Learning technique to automatically discover variations and detect at first glance what the problem is, and undertake corrective measures. |
| Tasks | |
| Published | 2016-12-30 |
| URL | http://arxiv.org/abs/1701.00001v1 |
| http://arxiv.org/pdf/1701.00001v1.pdf | |
| PWC | https://paperswithcode.com/paper/digital-advertising-traffic-operation-machine |
| Repo | |
| Framework | |
Matching-Based Selection with Incomplete Lists for Decomposition Multi-Objective Optimization
| Title | Matching-Based Selection with Incomplete Lists for Decomposition Multi-Objective Optimization |
| Authors | Mengyuan Wu, Ke Li, Sam Kwong, Yu Zhou, Qingfu Zhang |
| Abstract | The balance between convergence and diversity is a key issue of evolutionary multi-objective optimization. The recently proposed stable matching-based selection provides a new perspective to handle this balance under the framework of decomposition multi-objective optimization. In particular, the stable matching between subproblems and solutions, which achieves an equilibrium between their mutual preferences, implicitly strikes a balance between the convergence and diversity. Nevertheless, the original stable matching model has a high risk of matching a solution with a unfavorable subproblem which finally leads to an imbalanced selection result. In this paper, we propose an adaptive two-level stable matching-based selection for decomposition multi-objective optimization. Specifically, borrowing the idea of stable matching with incomplete lists, we match each solution with one of its favorite subproblems by restricting the length of its preference list during the first-level stable matching. During the second-level stable matching, the remaining subproblems are thereafter matched with their favorite solutions according to the classic stable matching model. In particular, we develop an adaptive mechanism to automatically set the length of preference list for each solution according to its local competitiveness. The performance of our proposed method is validated and compared with several state-of-the-art evolutionary multi-objective optimization algorithms on 62 benchmark problem instances. Empirical results fully demonstrate the competitive performance of our proposed method on problems with complicated Pareto sets and those with more than three objectives. |
| Tasks | |
| Published | 2016-08-30 |
| URL | http://arxiv.org/abs/1608.08607v2 |
| http://arxiv.org/pdf/1608.08607v2.pdf | |
| PWC | https://paperswithcode.com/paper/matching-based-selection-with-incomplete |
| Repo | |
| Framework | |
Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video
| Title | Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video |
| Authors | Hao Jiang, Kristen Grauman |
| Abstract | Understanding the camera wearer’s activity is central to egocentric vision, yet one key facet of that activity is inherently invisible to the camera–the wearer’s body pose. Prior work focuses on estimating the pose of hands and arms when they come into view, but this 1) gives an incomplete view of the full body posture, and 2) prevents any pose estimate at all in many frames, since the hands are only visible in a fraction of daily life activities. We propose to infer the “invisible pose” of a person behind the egocentric camera. Given a single video, our efficient learning-based approach returns the full body 3D joint positions for each frame. Our method exploits cues from the dynamic motion signatures of the surrounding scene–which changes predictably as a function of body pose–as well as static scene structures that reveal the viewpoint (e.g., sitting vs. standing). We further introduce a novel energy minimization scheme to infer the pose sequence. It uses soft predictions of the poses per time instant together with a non-parametric model of human pose dynamics over longer windows. Our method outperforms an array of possible alternatives, including deep learning approaches for direct pose regression from images. |
| Tasks | |
| Published | 2016-03-24 |
| URL | http://arxiv.org/abs/1603.07763v1 |
| http://arxiv.org/pdf/1603.07763v1.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-invisible-poses-estimating-3d-body |
| Repo | |
| Framework | |
Sequencing Chess
| Title | Sequencing Chess |
| Authors | A. Atashpendar, T. Schilling, Th. Voigtmann |
| Abstract | We analyze the structure of the state space of chess by means of transition path sampling Monte Carlo simulation. Based on the typical number of moves required to transpose a given configuration of chess pieces into another, we conclude that the state space consists of several pockets between which transitions are rare. Skilled players explore an even smaller subset of positions that populate some of these pockets only very sparsely. These results suggest that the usual measures to estimate both, the size of the state space and the size of the tree of legal moves, are not unique indicators of the complexity of the game, but that topological considerations are equally important. |
| Tasks | |
| Published | 2016-09-14 |
| URL | http://arxiv.org/abs/1609.04648v1 |
| http://arxiv.org/pdf/1609.04648v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequencing-chess |
| Repo | |
| Framework | |
Read, Tag, and Parse All at Once, or Fully-neural Dependency Parsing
| Title | Read, Tag, and Parse All at Once, or Fully-neural Dependency Parsing |
| Authors | Jan Chorowski, Michał Zapotoczny, Paweł Rychlikowski |
| Abstract | We present a dependency parser implemented as a single deep neural network that reads orthographic representations of words and directly generates dependencies and their labels. Unlike typical approaches to parsing, the model doesn’t require part-of-speech (POS) tagging of the sentences. With proper regularization and additional supervision achieved with multitask learning we reach state-of-the-art performance on Slavic languages from the Universal Dependencies treebank: with no linguistic features other than characters, our parser is as accurate as a transition- based system trained on perfect POS tags. |
| Tasks | Dependency Parsing, Part-Of-Speech Tagging |
| Published | 2016-09-12 |
| URL | http://arxiv.org/abs/1609.03441v2 |
| http://arxiv.org/pdf/1609.03441v2.pdf | |
| PWC | https://paperswithcode.com/paper/read-tag-and-parse-all-at-once-or-fully |
| Repo | |
| Framework | |
Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
| Title | Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps |
| Authors | Jiewei Cao, Lingqiao Liu, Peng Wang, Zi Huang, Chunhua Shen, Heng Tao Shen |
| Abstract | Instance retrieval requires one to search for images that contain a particular object within a large corpus. Recent studies show that using image features generated by pooling convolutional layer feature maps (CFMs) of a pretrained convolutional neural network (CNN) leads to promising performance for this task. However, due to the global pooling strategy adopted in those works, the generated image feature is less robust to image clutter and tends to be contaminated by the irrelevant image patterns. In this article, we alleviate this drawback by proposing a novel reranking algorithm using CFMs to refine the retrieval result obtained by existing methods. Our key idea, called query adaptive matching (QAM), is to first represent the CFMs of each image by a set of base regions which can be freely combined into larger regions-of-interest. Then the similarity between the query and a candidate image is measured by the best similarity score that can be attained by comparing the query feature and the feature pooled from a combined region. We show that the above procedure can be cast as an optimization problem and it can be solved efficiently with an off-the-shelf solver. Besides this general framework, we also propose two practical ways to create the base regions. One is based on the property of the CFM and the other one is based on a multi-scale spatial pyramid scheme. Through extensive experiments, we show that our reranking approaches bring substantial performance improvement and by applying them we can outperform the state of the art on several instance retrieval benchmarks. |
| Tasks | |
| Published | 2016-06-22 |
| URL | http://arxiv.org/abs/1606.06811v1 |
| http://arxiv.org/pdf/1606.06811v1.pdf | |
| PWC | https://paperswithcode.com/paper/where-to-focus-query-adaptive-matching-for |
| Repo | |
| Framework | |
Understanding the Abstract Dialectical Framework (Preliminary Report)
| Title | Understanding the Abstract Dialectical Framework (Preliminary Report) |
| Authors | Sylwia Polberg |
| Abstract | Among the most general structures extending the framework by Dung are the abstract dialectical frameworks (ADFs). They come equipped with various types of semantics, with the most prominent - the labeling-based one - analyzed in the context of computational complexity, signatures, instantiations and software support. This makes the abstract dialectical frameworks valuable tools for argumentation. However, there are fewer results available concerning the relation between the ADFs and other argumentation frameworks. In this paper we would like to address this issue by introducing a number of translations from various formalisms into ADFs. The results of our study show the similarities and differences between them, thus promoting the use and understanding of ADFs. Moreover, our analysis also proves their capability to model many of the existing frameworks, including those that go beyond the attack relation. Finally, translations allow other structures to benefit from the research on ADFs in general and from the existing software in particular. |
| Tasks | |
| Published | 2016-07-04 |
| URL | http://arxiv.org/abs/1607.00819v1 |
| http://arxiv.org/pdf/1607.00819v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-the-abstract-dialectical |
| Repo | |
| Framework | |
Towards Better Response Times and Higher-Quality Queries in Interactive Knowledge Base Debugging
| Title | Towards Better Response Times and Higher-Quality Queries in Interactive Knowledge Base Debugging |
| Authors | Patrick Rodler |
| Abstract | Many AI applications rely on knowledge encoded in a locigal knowledge base (KB). The most essential benefit of such logical KBs is the opportunity to perform automatic reasoning which however requires a KB to meet some minimal quality criteria such as consistency. Without adequate tool assistance, the task of resolving such violated quality criteria in a KB can be extremely hard, especially when the problematic KB is large and complex. To this end, interactive KB debuggers have been introduced which ask a user queries whether certain statements must or must not hold in the intended domain. The given answers help to gradually restrict the search space for KB repairs. Existing interactive debuggers often rely on a pool-based strategy for query computation. A pool of query candidates is precomputed, from which the best candidate according to some query quality criterion is selected to be shown to the user. This often leads to the generation of many unnecessary query candidates and thus to a high number of expensive calls to logical reasoning services. We tackle this issue by an in-depth mathematical analysis of diverse real-valued active learning query selection measures in order to determine qualitative criteria that make a query favorable. These criteria are the key to devising efficient heuristic query search methods. The proposed methods enable for the first time a completely reasoner-free query generation for interactive KB debugging while at the same time guaranteeing optimality conditions, e.g. minimal cardinality or best understandability for the user, of the generated query that existing methods cannot realize. Further, we study different relations between active learning measures. The obtained picture gives a hint about which measures are more favorable in which situation or which measures always lead to the same outcomes, based on given types of queries. |
| Tasks | Active Learning |
| Published | 2016-09-08 |
| URL | http://arxiv.org/abs/1609.02584v2 |
| http://arxiv.org/pdf/1609.02584v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-better-response-times-and-higher |
| Repo | |
| Framework | |
