Paper Group NANR 147
Fast Forward Through Opportunistic Incremental Meaning Representation Construction. Improving Coverage of an Inuktitut Morphological Analyzer Using a Segmental Recurrent Neural Network. Multi-Class Optimal Margin Distribution Machine. Evaluating the Variance of Likelihood-Ratio Gradient Estimators. The Code2Text Challenge: Text Generation in Source …
Fast Forward Through Opportunistic Incremental Meaning Representation Construction
| Title | Fast Forward Through Opportunistic Incremental Meaning Representation Construction |
| Authors | Petr Babkin, Sergei Nirenburg |
| Abstract | |
| Tasks | Decision Making, Dialogue Understanding, Semantic Parsing |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3019/ |
| https://www.aclweb.org/anthology/P17-3019 | |
| PWC | https://paperswithcode.com/paper/fast-forward-through-opportunistic |
| Repo | |
| Framework | |
Improving Coverage of an Inuktitut Morphological Analyzer Using a Segmental Recurrent Neural Network
| Title | Improving Coverage of an Inuktitut Morphological Analyzer Using a Segmental Recurrent Neural Network |
| Authors | Jeffrey Micher |
| Abstract | |
| Tasks | Morphological Analysis |
| Published | 2017-03-01 |
| URL | https://www.aclweb.org/anthology/W17-0114/ |
| https://www.aclweb.org/anthology/W17-0114 | |
| PWC | https://paperswithcode.com/paper/improving-coverage-of-an-inuktitut |
| Repo | |
| Framework | |
Multi-Class Optimal Margin Distribution Machine
| Title | Multi-Class Optimal Margin Distribution Machine |
| Authors | Teng Zhang, Zhi-Hua Zhou |
| Abstract | Recent studies disclose that maximizing the minimum margin like support vector machines does not necessarily lead to better generalization performances, and instead, it is crucial to optimize the margin distribution. Although it has been shown that for binary classification, characterizing the margin distribution by the first- and second-order statistics can achieve superior performance. It still remains open for multi-class classification, and due to the complexity of margin for multi-class classification, optimizing its distribution by mean and variance can also be difficult. In this paper, we propose mcODM (multi-class Optimal margin Distribution Machine), which can solve this problem efficiently. We also give a theoretical analysis for our method, which verifies the significance of margin distribution for multi-class classification. Empirical study further shows that mcODM always outperforms all four versions of multi-class SVMs on all experimental data sets. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=823 |
| http://proceedings.mlr.press/v70/zhang17h/zhang17h.pdf | |
| PWC | https://paperswithcode.com/paper/multi-class-optimal-margin-distribution |
| Repo | |
| Framework | |
Evaluating the Variance of Likelihood-Ratio Gradient Estimators
| Title | Evaluating the Variance of Likelihood-Ratio Gradient Estimators |
| Authors | Seiya Tokui, Issei Sato |
| Abstract | The likelihood-ratio method is often used to estimate gradients of stochastic computations, for which baselines are required to reduce the estimation variance. Many types of baselines have been proposed, although their degree of optimality is not well understood. In this study, we establish a novel framework of gradient estimation that includes most of the common gradient estimators as special cases. The framework gives a natural derivation of the optimal estimator that can be interpreted as a special case of the likelihood-ratio method so that we can evaluate the optimal degree of practical techniques with it. It bridges the likelihood-ratio method and the reparameterization trick while still supporting discrete variables. It is derived from the exchange property of the differentiation and integration. To be more specific, it is derived by the reparameterization trick and local marginalization analogous to the local expectation gradient. We evaluate various baselines and the optimal estimator for variational learning and show that the performance of the modern estimators is close to the optimal estimator. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=608 |
| http://proceedings.mlr.press/v70/tokui17a/tokui17a.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-the-variance-of-likelihood-ratio |
| Repo | |
| Framework | |
The Code2Text Challenge: Text Generation in Source Libraries
| Title | The Code2Text Challenge: Text Generation in Source Libraries |
| Authors | Kyle Richardson, Sina Zarrie{\ss}, Jonas Kuhn |
| Abstract | We propose a new shared task for tactical data-to-text generation in the domain of source code libraries. Specifically, we focus on text generation of function descriptions from example software projects. Data is drawn from existing resources used for studying the related problem of semantic parser induction, and spans a wide variety of both natural languages and programming languages. In this paper, we describe these existing resources, which will serve as training and development data for the task, and discuss plans for building new independent test sets. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3516/ |
| https://www.aclweb.org/anthology/W17-3516 | |
| PWC | https://paperswithcode.com/paper/the-code2text-challenge-text-generation-in-1 |
| Repo | |
| Framework | |
Invariance and Stability of Deep Convolutional Representations
| Title | Invariance and Stability of Deep Convolutional Representations |
| Authors | Alberto Bietti, Julien Mairal |
| Abstract | In this paper, we study deep signal representations that are near-invariant to groups of transformations and stable to the action of diffeomorphisms without losing signal information. This is achieved by generalizing the multilayer kernel introduced in the context of convolutional kernel networks and by studying the geometry of the corresponding reproducing kernel Hilbert space. We show that the signal representation is stable, and that models from this functional space, such as a large class of convolutional neural networks, may enjoy the same stability. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7201-invariance-and-stability-of-deep-convolutional-representations |
| http://papers.nips.cc/paper/7201-invariance-and-stability-of-deep-convolutional-representations.pdf | |
| PWC | https://paperswithcode.com/paper/invariance-and-stability-of-deep |
| Repo | |
| Framework | |
Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence
| Title | Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence |
| Authors | Yi Xu, Qihang Lin, Tianbao Yang |
| Abstract | In this paper, a new theory is developed for first-order stochastic convex optimization, showing that the global convergence rate is sufficiently quantified by a local growth rate of the objective function in a neighborhood of the optimal solutions. In particular, if the objective function $F(\mathbf{w})$ in the $\epsilon$-sublevel set grows as fast as $\mathbf{w} - \mathbf{w}*_2^{1/\theta}$, where $\mathbf{w}*$ represents the closest optimal solution to $\mathbf{w}$ and $\theta\in(0,1]$ quantifies the local growth rate, the iteration complexity of first-order stochastic optimization for achieving an $\epsilon$-optimal solution can be $\widetilde O(1/\epsilon^{2(1-\theta)})$, which is optimal at most up to a logarithmic factor. This result is fundamentally better in contrast with the previous works that either assume a global growth condition in the entire domain or achieve a local faster convergence under the local faster growth condition. To achieve the faster global convergence, we develop two different accelerated stochastic subgradient methods by iteratively solving the original problem approximately in a local region around a historical solution with the size of the local region gradually decreasing as the solution approaches the optimal set. Besides the theoretical improvements, this work also include new contributions towards making the proposed algorithms practical: (i) we present practical variants of accelerated stochastic subgradient methods that can run without the knowledge of multiplicative growth constant and even the growth rate $\theta$; (ii) we consider a broad family of problems in machine learning to demonstrate that the proposed algorithms enjoy faster convergence than traditional stochastic subgradient method. For example, when applied to the $\ell_1$ regularized empirical polyhedral loss minimization (e.g., hinge loss, absolute loss), the proposed stochastic methods have a logarithmic iteration complexity. |
| Tasks | Stochastic Optimization |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=505 |
| http://proceedings.mlr.press/v70/xu17a/xu17a.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-convex-optimization-faster-local |
| Repo | |
| Framework | |
Multi-modular domain-tailored OCR post-correction
| Title | Multi-modular domain-tailored OCR post-correction |
| Authors | Sarah Schulz, Jonas Kuhn |
| Abstract | One of the main obstacles for many Digital Humanities projects is the low data availability. Texts have to be digitized in an expensive and time consuming process whereas Optical Character Recognition (OCR) post-correction is one of the time-critical factors. At the example of OCR post-correction, we show the adaptation of a generic system to solve a specific problem with little data. The system accounts for a diversity of errors encountered in OCRed texts coming from different time periods in the domain of literature. We show that the combination of different approaches, such as e.g. Statistical Machine Translation and spell checking, with the help of a ranking mechanism tremendously improves over single-handed approaches. Since we consider the accessibility of the resulting tool as a crucial part of Digital Humanities collaborations, we describe the workflow we suggest for efficient text recognition and subsequent automatic and manual post-correction |
| Tasks | Machine Translation, Optical Character Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1288/ |
| https://www.aclweb.org/anthology/D17-1288 | |
| PWC | https://paperswithcode.com/paper/multi-modular-domain-tailored-ocr-post |
| Repo | |
| Framework | |
Blend: a Novel Combined MT Metric Based on Direct Assessment — CASICT-DCU submission to WMT17 Metrics Task
| Title | Blend: a Novel Combined MT Metric Based on Direct Assessment — CASICT-DCU submission to WMT17 Metrics Task |
| Authors | Qingsong Ma, Yvette Graham, Shugen Wang, Qun Liu |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4768/ |
| https://www.aclweb.org/anthology/W17-4768 | |
| PWC | https://paperswithcode.com/paper/blend-a-novel-combined-mt-metric-based-on |
| Repo | |
| Framework | |
The ContrastMedium Algorithm: Taxonomy Induction From Noisy Knowledge Graphs With Just A Few Links
| Title | The ContrastMedium Algorithm: Taxonomy Induction From Noisy Knowledge Graphs With Just A Few Links |
| Authors | Stefano Faralli, Alex Panchenko, er, Chris Biemann, Simone Paolo Ponzetto |
| Abstract | In this paper, we present ContrastMedium, an algorithm that transforms noisy semantic networks into full-fledged, clean taxonomies. ContrastMedium is able to identify the embedded taxonomy structure from a noisy knowledge graph without explicit human supervision such as, for instance, a set of manually selected input root and leaf concepts. This is achieved by leveraging structural information from a companion reference taxonomy, to which the input knowledge graph is linked (either automatically or manually). When used in conjunction with methods for hypernym acquisition and knowledge base linking, our methodology provides a complete solution for end-to-end taxonomy induction. We conduct experiments using automatically acquired knowledge graphs, as well as a SemEval benchmark, and show that our method is able to achieve high performance on the task of taxonomy induction. |
| Tasks | Knowledge Graphs, Open Information Extraction |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1056/ |
| https://www.aclweb.org/anthology/E17-1056 | |
| PWC | https://paperswithcode.com/paper/the-contrastmedium-algorithm-taxonomy |
| Repo | |
| Framework | |
Integrated sentence generation using charts
| Title | Integrated sentence generation using charts |
| Authors | Alex Koller, er, Nikos Engonopoulos |
| Abstract | Integrating surface realization and the generation of referring expressions into a single algorithm can improve the quality of the generated sentences. Existing algorithms for doing this, such as SPUD and CRISP, are search-based and can be slow or incomplete. We offer a chart-based algorithm for integrated sentence generation and demonstrate its runtime efficiency. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3520/ |
| https://www.aclweb.org/anthology/W17-3520 | |
| PWC | https://paperswithcode.com/paper/integrated-sentence-generation-using-charts |
| Repo | |
| Framework | |
Kernelized Support Tensor Machines
| Title | Kernelized Support Tensor Machines |
| Authors | Lifang He, Chun-Ta Lu, Guixiang Ma, Shen Wang, Linlin Shen, Philip S. Yu, Ann B. Ragin |
| Abstract | In the context of supervised tensor learning, preserving the structural information and exploiting the discriminative nonlinear relationships of tensor data are crucial for improving the performance of learning tasks. Based on tensor factorization theory and kernel methods, we propose a novel Kernelized Support Tensor Machine (KSTM) which integrates kernelized tensor factorization with maximum-margin criterion. Specifically, the kernelized factorization technique is introduced to approximate the tensor data in kernel space such that the complex nonlinear relationships within tensor data can be explored. Further, dual structural preserving kernels are devised to learn the nonlinear boundary between tensor data. As a result of joint optimization, the kernels obtained in KSTM exhibit better generalization power to discriminative analysis. The experimental results on real-world neuroimaging datasets show the superiority of KSTM over the state-of-the-art techniques. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=516 |
| http://proceedings.mlr.press/v70/he17a/he17a.pdf | |
| PWC | https://paperswithcode.com/paper/kernelized-support-tensor-machines |
| Repo | |
| Framework | |
Evaluating Dialogs based on Grice’s Maxims
| Title | Evaluating Dialogs based on Grice’s Maxims |
| Authors | Prathyusha Jwalapuram |
| Abstract | There is no agreed upon standard for the evaluation of conversational dialog systems, which are well-known to be hard to evaluate due to the difficulty in pinning down metrics that will correspond to human judgements and the subjective nature of human judgment itself. We explored the possibility of using Grice{'}s Maxims to evaluate effective communication in conversation. We collected some system generated dialogs from popular conversational chatbots across the spectrum and conducted a survey to see how the human judgements based on Gricean maxims correlate, and if such human judgments can be used as an effective evaluation metric for conversational dialog. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-2003/ |
| https://doi.org/10.26615/issn.1314-9156.2017_003 | |
| PWC | https://paperswithcode.com/paper/evaluating-dialogs-based-on-grices-maxims |
| Repo | |
| Framework | |
GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization
| Title | GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization |
| Authors | Li Shen, Wei Liu, Ganzhao Yuan, Shiqian Ma |
| Abstract | In this paper, we propose a fast Gauss-Seidel Operator Splitting (GSOS) algorithm for addressing multi-term nonsmooth convex composite optimization, which has wide applications in machine learning, signal processing and statistics. The proposed GSOS algorithm inherits the advantage of the Gauss-Seidel technique to accelerate the optimization procedure, and leverages the operator splitting technique to reduce the computational complexity. In addition, we develop a new technique to establish the global convergence of the GSOS algorithm. To be specific, we first reformulate the iterations of GSOS as a two-step iterations algorithm by employing the tool of operator optimization theory. Subsequently, we establish the convergence of GSOS based on the two-step iterations algorithm reformulation. At last, we apply the proposed GSOS algorithm to solve overlapping group Lasso and graph-guided fused Lasso problems. Numerical experiments show that our proposed GSOS algorithm is superior to the state-of-the-art algorithms in terms of both efficiency and effectiveness. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=477 |
| http://proceedings.mlr.press/v70/shen17b/shen17b.pdf | |
| PWC | https://paperswithcode.com/paper/gsos-gauss-seidel-operator-splitting |
| Repo | |
| Framework | |
Ordinal Graphical Models: A Tale of Two Approaches
| Title | Ordinal Graphical Models: A Tale of Two Approaches |
| Authors | Arun Sai Suggala, Eunho Yang, Pradeep Ravikumar |
| Abstract | Undirected graphical models or Markov random fields (MRFs) are widely used for modeling multivariate probability distributions. Much of the work on MRFs has focused on continuous variables, and nominal variables (that is, unordered categorical variables). However, data from many real world applications involve ordered categorical variables also known as ordinal variables, e.g., movie ratings on Netflix which can be ordered from 1 to 5 stars. With respect to univariate ordinal distributions, as we detail in the paper, there are two main categories of distributions; while there have been efforts to extend these to multivariate ordinal distributions, the resulting distributions are typically very complex, with either a large number of parameters, or with non-convex likelihoods. While there have been some work on tractable approximations, these do not come with strong statistical guarantees, and moreover are relatively computationally expensive. In this paper, we theoretically investigate two classes of graphical models for ordinal data, corresponding to the two main categories of univariate ordinal distributions. In contrast to previous work, our theoretical developments allow us to provide correspondingly two classes of estimators that are not only computationally efficient but also have strong statistical guarantees. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=644 |
| http://proceedings.mlr.press/v70/suggala17a/suggala17a.pdf | |
| PWC | https://paperswithcode.com/paper/ordinal-graphical-models-a-tale-of-two |
| Repo | |
| Framework | |
