11
11

Jun 28, 2018
06/18

by
Lukas Zilka; Filip Jurcicek

texts

#
eye 11

#
favorite 0

#
comment 0

A dialog state tracker is an important component in modern spoken dialog systems. We present an incremental dialog state tracker, based on LSTM networks. It directly uses automatic speech recognition hypotheses to track the state. We also present the key non-standard aspects of the model that bring its performance close to the state-of-the-art and experimentally analyze their contribution: including the ASR confidence scores, abstracting scarcely represented values, including transcriptions in...

Topics: Computation and Language, Computing Research Repository

Source: http://arxiv.org/abs/1507.03471

5
5.0

Jun 30, 2018
06/18

by
Chenhao Tan; Lillian Lee; Bo Pang

texts

#
eye 5

#
favorite 0

#
comment 0

Consider a person trying to spread an important message on a social network. He/she can spend hours trying to craft the message. Does it actually matter? While there has been extensive prior work looking into predicting popularity of social-media content, the effect of wording per se has rarely been studied since it is often confounded with the popularity of the author and the topic. To control for these confounding factors, we take advantage of the surprising fact that there are many pairs of...

Topics: Physics, Computing Research Repository, Computation and Language, Social and Information Networks,...

Source: http://arxiv.org/abs/1405.1438

11
11

Jun 27, 2018
06/18

by
Luke Vilnis; David Belanger; Daniel Sheldon; Andrew McCallum

texts

#
eye 11

#
favorite 0

#
comment 0

Many inference problems in structured prediction are naturally solved by augmenting a tractable dependency structure with complex, non-local auxiliary objectives. This includes the mean field family of variational inference algorithms, soft- or hard-constrained inference using Lagrangian relaxation or linear programming, collective graphical models, and forms of semi-supervised learning such as posterior regularization. We present a method to discriminatively learn broad families of inference...

Topics: Machine Learning, Learning, Computing Research Repository, Statistics, Computation and Language

Source: http://arxiv.org/abs/1503.01397

4
4.0

audio

#
eye 4

#
favorite 0

#
comment 0

Topics: Radio Program, Citizen science, Crowdsourcing, Nuclear physics, Republics, Epidemiology, Member...

4
4.0

Jun 30, 2018
06/18

by
Robert Speer; Joanna Lowry-Duda

texts

#
eye 4

#
favorite 0

#
comment 0

This paper describes Luminoso's participation in SemEval 2017 Task 2, "Multilingual and Cross-lingual Semantic Word Similarity", with a system based on ConceptNet. ConceptNet is an open, multilingual knowledge graph that focuses on general knowledge that relates the meanings of words and phrases. Our submission to SemEval was an update of previous work that builds high-quality, multilingual word embeddings from a combination of ConceptNet and distributional semantics. Our system took...

Topics: Computing Research Repository, Computation and Language

Source: http://arxiv.org/abs/1704.03560

Topics: Radio Program, Citizen science, Crowdsourcing, Nuclear physics, Measuring instruments, Statistical...

9
9.0

Jun 28, 2018
06/18

by
Kyunghyun Cho; Aaron Courville; Yoshua Bengio

texts

#
eye 9

#
favorite 0

#
comment 0

Whereas deep neural networks were first mostly used for classification tasks, they are rapidly expanding in the realm of structured output problems, where the observed target is composed of multiple random variables that have a rich joint distribution, given the input. We focus in this paper on the case where the input also has a rich structure and the input and output structures are somehow related. We describe systems that learn to attend to different places in the input, for each element of...

Topics: Computation and Language, Computer Vision and Pattern Recognition, Computing Research Repository,...

Source: http://arxiv.org/abs/1507.01053

3
3.0

Jun 29, 2018
06/18

by
Madhav Nimishakavi; Uday Singh Saini; Partha Talukdar

texts

#
eye 3

#
favorite 0

#
comment 0

Given a set of documents from a specific domain (e.g., medical research journals), how do we automatically build a Knowledge Graph (KG) for that domain? Automatic identification of relations and their schemas, i.e., type signature of arguments of relations (e.g., undergo(Patient, Surgery)), is an important first step towards this goal. We refer to this problem as Relation Schema Induction (RSI). In this paper, we propose Schema Induction using Coupled Tensor Factorization (SICTF), a novel...

Topics: Databases, Information Retrieval, Computing Research Repository, Computation and Language

Source: http://arxiv.org/abs/1605.04227

7
7.0

Jun 29, 2018
06/18

by
Robert Piche

texts

#
eye 7

#
favorite 0

#
comment 0

A linear Gaussian state-space smoothing algorithm is presented for estimation of derivatives from a sequence of noisy measurements. The algorithm uses numerically stable square-root formulas, can handle simultaneous independent measurements and non-equally spaced abscissas, and can compute state estimates at points between the data abscissas. The state space model's parameters, including driving noise intensity, measurement variance, and initial state, are determined from the given data...

Topics: Methodology, Computation, Statistics

Source: http://arxiv.org/abs/1610.04397

9
9.0

Jun 29, 2018
06/18

by
Song Han; Junlong Kang; Huizi Mao; Yiming Hu; Xin Li; Yubin Li; Dongliang Xie; Hong Luo; Song Yao; Yu Wang; Huazhong Yang; William J. Dally

texts

#
eye 9

#
favorite 0

#
comment 0

Long Short-Term Memory (LSTM) is widely used in speech recognition. In order to achieve higher prediction accuracy, machine learning scientists have built larger and larger models. Such large model is both computation intensive and memory intensive. Deploying such bulky model results in high power consumption and leads to high total cost of ownership (TCO) of a data center. In order to speedup the prediction and make it energy efficient, we first propose a load-balance-aware pruning method that...

Topics: Computation and Language, Computing Research Repository

Source: http://arxiv.org/abs/1612.00694

6
6.0

Jun 30, 2018
06/18

by
Samuel Rönnqvist; Xiaolu Wang; Peter Sarlin

texts

#
eye 6

#
favorite 0

#
comment 0

Probabilistic topic modeling is a popular and powerful family of tools for uncovering thematic structure in large sets of unstructured text documents. While much attention has been directed towards the modeling algorithms and their various extensions, comparatively few studies have concerned how to present or visualize topic models in meaningful ways. In this paper, we present a novel design that uses graphs to visually communicate topic structure and meaning. By connecting topic nodes via...

Topics: Computing Research Repository, Computation and Language, Information Retrieval

Source: http://arxiv.org/abs/1409.5623

Topics: Radio Program, Concepts in physics, Decision theory, Models of computation, Cooking techniques,...

3
3.0

Jun 30, 2018
06/18

by
Joël Legrand; Ronan Collobert

texts

#
eye 3

#
favorite 0

#
comment 0

This paper introduces a greedy parser based on neural networks, which leverages a new compositional sub-tree representation. The greedy parser and the compositional procedure are jointly trained, and tightly depends on each-other. The composition procedure outputs a vector representation which summarizes syntactically (parsing tags) and semantically (words) sub-trees. Composition and tagging is achieved over continuous (word or tag) representations, and recurrent neural networks. We reach F1...

Topics: Neural and Evolutionary Computing, Computing Research Repository, Computation and Language, Learning

Source: http://arxiv.org/abs/1412.7028

3
3.0

Jun 30, 2018
06/18

by
Alireza S. Mahani; Mansour T. A. Sharabiani

texts

#
eye 3

#
favorite 0

#
comment 0

The R package MfUSampler provides Monte Carlo Markov Chain machinery for generating samples from multivariate probability distributions using univariate sampling algorithms such as Slice Sampler and Adaptive Rejection Sampler. The sampler function performs a full cycle of univariate sampling steps, one coordinate at a time. In each step, the latest sample values obtained for other coordinates are used to form the conditional distributions. The concept is an extension of Gibbs sampling where...

Topics: Computation, Statistics

Source: http://arxiv.org/abs/1412.7784

3
3.0

Jun 30, 2018
06/18

by
Fred Morstatter; Nichola Lubold; Heather Pon-Barry; Jürgen Pfeffer; Huan Liu

texts

#
eye 3

#
favorite 0

#
comment 0

Disaster response agencies have started to incorporate social media as a source of fast-breaking information to understand the needs of people affected by the many crises that occur around the world. These agencies look for tweets from within the region affected by the crisis to get the latest updates of the status of the affected region. However only 1% of all tweets are geotagged with explicit location information. First responders lose valuable information because they cannot assess the...

Topics: Computers and Society, Computing Research Repository, Computation and Language

Source: http://arxiv.org/abs/1403.1773

2
2.0

Jun 30, 2018
06/18

by
Michael U. Gutmann; Ritabrata Dutta; Samuel Kaski; Jukka Corander

texts

#
eye 2

#
favorite 0

#
comment 0

Increasingly complex generative models are being used across disciplines as they allow for realistic characterization of data, but a common difficulty with them is the prohibitively large computational cost to evaluate the likelihood function and thus to perform likelihood-based statistical inference. A likelihood-free inference framework has emerged where the parameters are identified by finding values that yield simulated data resembling the observed data. While widely applicable, a major...

Topics: Computation, Machine Learning, Statistics, Methodology

Source: http://arxiv.org/abs/1407.4981

2
2.0

Jun 30, 2018
06/18

by
Jakob Ablinger

texts

#
eye 2

#
favorite 0

#
comment 0

This paper summarizes the essential functionality of the computer algebra package HarmonicSums. On the one hand HarmonicSums can work with nested sums such as harmonic sums and their generalizations and on the other hand it can treat iterated integrals of the Poincare and Chen-type, such as harmonic polylogarithms and their generalizations. The interplay of these representations and the analytic aspects are illustrated by concrete examples.

Topics: Symbolic Computation, High Energy Physics - Phenomenology, Computing Research Repository

Source: http://arxiv.org/abs/1407.6180

3
3.0

Jun 30, 2018
06/18

by
Houying Zhu; Josef Dick

texts

#
eye 3

#
favorite 0

#
comment 0

In this paper we propose an acceptance-rejection sampler using stratified inputs as diver sequence. We estimate the discrepancy of the points generated by this algorithm. First we show an upper bound on the star discrepancy of order $N^{-1/2-1/(2s)}$. Further we prove an upper bound on the $q$-th moment of the $L_q$-discrepancy $(\mathbb{E}[N^{q}L^{q}_{q,N}])^{1/q}$ for $2\le q\le \infty$, which is of order $N^{(1-1/s)(1-1/q)}$. We also present an improved convergence rate for a deterministic...

Topics: Computation, Numerical Analysis, Mathematics, Statistics

Source: http://arxiv.org/abs/1408.1742

3
3.0

Jun 30, 2018
06/18

by
Balasubramanian Narasimhan; Daniel L. Rubin; Samuel M. Gross; Marina Bendersky; Philip W. Lavori

texts

#
eye 3

#
favorite 0

#
comment 0

Bringing together the information latent in distributed medical databases promises to personalize medical care by enabling reliable, stable modeling of outcomes with rich feature sets (including patient characteristics and treatments received). However, there are barriers to aggregation of medical data, due to lack of standardization of ontologies, privacy concerns, proprietary attitudes toward data, and a reluctance to give up control over end use. Aggregation of data is not always necessary...

Topics: Mathematical Software, Computation, Computing Research Repository, Statistics, Software Engineering

Source: http://arxiv.org/abs/1412.6890

4
4.0

Jun 30, 2018
06/18

by
Tomáš Kočiský; Karl Moritz Hermann; Phil Blunsom

texts

#
eye 4

#
favorite 0

#
comment 0

We present a probabilistic model that simultaneously learns alignments and distributed representations for bilingual data. By marginalizing over word alignments the model captures a larger semantic context than prior work relying on hard alignments. The advantage of this approach is demonstrated in a cross-lingual classification task, where we outperform the prior published state of the art.

Topics: Computing Research Repository, Computation and Language

Source: http://arxiv.org/abs/1405.0947

2
2.0

Jun 30, 2018
06/18

by
Juan Luis Valerdi

texts

#
eye 2

#
favorite 0

#
comment 0

En este trabajo se presenta una propuesta para realizar Diferenciaci\'on Autom\'atica Anidada utilizando cualquier biblioteca de Diferenciaci\'on Autom\'atica que permita sobrecarga de operadores. Para calcular las derivadas anidadas en una misma evaluaci\'on de la funci\'on, la cual se asume que sea anal'itica, se trabaja con el modo forward utilizando una nueva estructura llamada SuperAdouble, que garantiza que se aplique correctamente la diferenciaci\'on autom\'atica y se calculen el valor y...

Topics: Symbolic Computation, Computing Research Repository

Source: http://arxiv.org/abs/1405.5854

3
3.0

Jun 30, 2018
06/18

by
Matthew England; David Wilson; Russell Bradford; James H. Davenport

texts

#
eye 3

#
favorite 0

#
comment 0

Cylindrical algebraic decomposition (CAD) is an important tool, both for quantifier elimination over the reals and a range of other applications. Traditionally, a CAD is built through a process of projection and lifting to move the problem within Euclidean spaces of changing dimension. Recently, an alternative approach which first decomposes complex space using triangular decomposition before refining to real space has been introduced and implemented within the RegularChains Library of Maple....

Topics: Symbolic Computation, Computing Research Repository

Source: http://arxiv.org/abs/1405.6090

2
2.0

Jun 30, 2018
06/18

by
Pete Bunch; Simon Godsill

texts

#
eye 2

#
favorite 0

#
comment 0

Recently developed particle flow algorithms provide an alternative to importance sampling for drawing particles from a posterior distribution, and a number of particle filters based on this principle have been proposed. Samples are drawn from the prior and then moved according to some dynamics over an interval of pseudo-time such that their final values are distributed according to the desired posterior. In practice, implementing a particle flow sampler requires multiple layers of...

Topics: Computation, Statistics

Source: http://arxiv.org/abs/1406.3183

3
3.0

Jun 30, 2018
06/18

by
Elizabeth Gross; Sonja Petrović; Despina Stasi

texts

#
eye 3

#
favorite 0

#
comment 0

Social networks and other large sparse data sets pose significant challenges for statistical inference, as many standard statistical methods for testing model fit are not applicable in such settings. Algebraic statistics offers a theoretically justified approach to goodness-of-fit testing that relies on the theory of Markov bases and is intimately connected with the geometry of the model as described by its fibers. Most current practices require the computation of the entire basis, which is...

Topics: Mathematics, Computation, Combinatorics, Statistics, Methodology

Source: http://arxiv.org/abs/1401.4896

Described are methods and apparatus, including computer program products, for reconfigurable environmentally adaptive computing technology. An environmental signal representative of an external environmental condition is received. A processing configuration is automatically selected, based on the environmental signal, from a plurality of processing configurations. A reconfigurable processing element is reconfigured to operate according to the selected processing configuration. In some examples,...

Topics: NASA Technical Reports Server (NTRS), COMPUTATION, COMPUTER PROGRAMS, COMPUTERS, COMPUTER SYSTEMS...

8
8.0

Jun 26, 2018
06/18

by
Tianran Chen; Dhagash Mehta

texts

#
eye 8

#
favorite 0

#
comment 0

The problem of solving a system of polynomial equations is one of the most fundamental problems in applied mathematics. Among them, the problem of solving a system of binomial equations form a important subclass for which specialized techniques exist. For both theoretic and applied purposes, the degree of the solution set of a system of binomial equations often plays an important role in understanding the geometric structure of the solution set. Its computation, however, is computationally...

Topics: Symbolic Computation, High Energy Physics - Theory, Computing Research Repository, Mathematical...

Source: http://arxiv.org/abs/1501.02237

8
8.0

Jun 25, 2018
06/18

by
C. Fantacci; B. -T. Vo; F. Papi; B. -N. Vo

texts

#
eye 8

#
favorite 0

#
comment 0

The multi-target Bayes filter proposed by Mahler is a principled solution to recursive Bayesian tracking based on RFS or FISST. The $\delta$-GLMB filter is an exact closed form solution to the multi-target Bayes recursion which yields joint state and label or trajectory estimates in the presence of clutter, missed detections and association uncertainty. Due to presence of explicit data associations in the $\delta$-GLMB filter, the number of components in the posterior grows without bound in...

Topics: Computation, Statistics

Source: http://arxiv.org/abs/1501.00926

4
4.0

Jun 29, 2018
06/18

by
Bhuwan Dhingra; Zhong Zhou; Dylan Fitzpatrick; Michael Muehl; William W. Cohen

texts

#
eye 4

#
favorite 0

#
comment 0

Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively large vocabulary size for word-level approaches. We propose a character composition model, tweet2vec, which finds vector-space representations of whole tweets by learning complex, non-local dependencies in character sequences. The proposed model outperforms a...

Topics: Computation and Language, Computing Research Repository, Learning

Source: http://arxiv.org/abs/1605.03481

5
5.0

Jun 29, 2018
06/18

by
Aleš Tamchyna; Alexander Fraser; Ondřej Bojar; Marcin Junczys-Dowmunt

texts

#
eye 5

#
favorite 0

#
comment 0

Discriminative translation models utilizing source context have been shown to help statistical machine translation performance. We propose a novel extension of this work using target context information. Surprisingly, we show that this model can be efficiently integrated directly in the decoding process. Our approach scales to large training data sizes and results in consistent improvements in translation quality on four language pairs. We also provide an analysis comparing the strengths of the...

Topics: Computation and Language, Computing Research Repository

Source: http://arxiv.org/abs/1607.01149

Data compression will pay an increasingly important role in the storage and transmission of image data within NASA science programs as the Earth Observing System comes into operation. It is important that the science data be preserved at the fidelity the instrument and the satellite communication systems were designed to produce. Lossless compression must therefore be applied, at least, to archive the processed instrument data. In this paper, we present an analysis of the performance of...

Topics: NASA Technical Reports Server (NTRS), DATA COMPRESSION, DIFFERENTIAL PULSE CODE MODULATION,...

2
2.0

Jun 30, 2018
06/18

by
D. S. Poskitt; Gael M. Martin; Simone D. Grose

texts

#
eye 2

#
favorite 0

#
comment 0

This paper investigates the use of bootstrap-based bias correction of semi-parametric estimators of the long memory parameter in fractionally integrated processes. The re-sampling method involves the application of the sieve bootstrap to data pre-filtered by a preliminary semi-parametric estimate of the long memory parameter. Theoretical justification for using the bootstrap techniques to bias adjust log-periodogram and semi-parametric local Whittle estimators of the memory parameter is...

Topics: Computation, Statistics, Methodology

Source: http://arxiv.org/abs/1402.6781

3
3.0

Jun 30, 2018
06/18

by
Adelchi Azzalini; Ryan P. Browne; Marc G. Genton; Paul D. McNicholas

texts

#
eye 3

#
favorite 0

#
comment 0

We examine some distributions used extensively within the model-based clustering literature in recent years, paying special attention to} claims that have been made about their relative efficacy. Theoretical arguments are provided as well as real data examples.

Topics: Mathematics, Computation, Statistics Theory, Statistics

Source: http://arxiv.org/abs/1402.5431

15
15

Jun 28, 2018
06/18

by
Shaoshi Chen; Christoph Koutschan

texts

#
eye 15

#
favorite 0

#
comment 0

In 1992, Wilf and Zeilberger conjectured that a hypergeometric term in several discrete and continuous variables is holonomic if and only if it is proper. Strictly speaking the conjecture does not hold, but it is true when reformulated properly: Payne proved a piecewise interpretation in 1997, and independently, Abramov and Petkovsek in 2002 proved a conjugate interpretation. Both results address the pure discrete case of the conjecture. In this paper we extend their work to hypergeometric...

Topics: Combinatorics, Computing Research Repository, Mathematics, Symbolic Computation

Source: http://arxiv.org/abs/1507.04840

4
4.0

Jun 29, 2018
06/18

by
Lidong Bing; Mingyang Ling; Richard C. Wang; William W. Cohen

texts

#
eye 4

#
favorite 0

#
comment 0

Distant labeling for information extraction (IE) suffers from noisy training data. We describe a way of reducing the noise associated with distant IE by identifying coupling constraints between potential instance labels. As one example of coupling, items in a list are likely to have the same label. A second example of coupling comes from analysis of document structure: in some corpora, sections can be identified such that items in the same section are likely to have the same label. Such...

Topics: Computation and Language, Computing Research Repository

Source: http://arxiv.org/abs/1601.00620

3
3.0

Jun 28, 2018
06/18

by
P. S. Koutsourelakis

texts

#
eye 3

#
favorite 0

#
comment 0

The present paper proposes a novel Bayesian, computational strategy in the context of model-based inverse problems in elastostatics. On one hand we attempt to provide probabilistic estimates of the material properties and their spatial variability that account for the various sources of uncertainty. On the other hand we attempt to address the question of model fidelity in relation to the experimental reality and particularly in the context of the material constitutive law adopted. This is...

Topics: Statistics, Computation

Source: http://arxiv.org/abs/1512.05913

5
5.0

Jun 29, 2018
06/18

by
Giovanni Da San Martino; Alberto Barrón-Cedeño; Salvatore Romeo; Alessandro Moschitti; Shafiq Joty; Fahad A. Al Obaidli; Kateryna Tymoshenko; Antonio Uva

texts

#
eye 5

#
favorite 0

#
comment 0

This paper studies the impact of different types of features applied to learning to re-rank questions in community Question Answering. We tested our models on two datasets released in SemEval-2016 Task 3 on "Community Question Answering". Task 3 targeted real-life Web fora both in English and Arabic. Our models include bag-of-words features (BoW), syntactic tree kernels (TKs), rank features, embeddings, and machine translation evaluation features. To the best of our knowledge,...

Topics: Computation and Language, Computing Research Repository

Source: http://arxiv.org/abs/1610.05522

4
4.0

Jun 29, 2018
06/18

by
Liang Sun; Jason Mielens; Jason Baldridge

texts

#
eye 4

#
favorite 0

#
comment 0

Unsupervised models of dependency parsing typically require large amounts of clean, unlabeled data plus gold-standard part-of-speech tags. Adding indirect supervision (e.g. language universals and rules) can help, but we show that obtaining small amounts of direct supervision - here, partial dependency annotations - provides a strong balance between zero and full supervision. We adapt the unsupervised ConvexMST dependency parser to learn from partial dependencies expressed in the Graph Fragment...

Topics: Computation and Language, Computing Research Repository

Source: http://arxiv.org/abs/1611.08765

3
3.0

Jun 30, 2018
06/18

by
Arthur White; Jason Wyse; Thomas Brendan Murphy

texts

#
eye 3

#
favorite 0

#
comment 0

Latent class analysis is used to perform model based clustering for multivariate categorical responses. Selection of the variables most relevant for clustering is an important task which can affect the quality of clustering considerably. This work considers a Bayesian approach for selecting the number of clusters and the best clustering variables. The main idea is to reformulate the problem of group and variable selection as a probabilistically driven search over a large discrete space using...

Topics: Computation, Statistics

Source: http://arxiv.org/abs/1402.6928

7
7.0

Jun 30, 2018
06/18

by
Jing Xi; Seth Sullivant

texts

#
eye 7

#
favorite 0

#
comment 0

In recent years, sequential importance sampling (SIS) has been well developed for sampling contingency tables with linear constraints. In this paper, we apply SIS procedure to 2-dimensional Ising models, which give observations of 0-1 tables and include both linear and quadratic constraints. We show how to compute bounds for specific cells by solving linear programming (LP) problems over cut polytopes to reduce rejections. The computational results, which includes both simulations and real data...

Topics: Optimization and Control, Computation, Combinatorics, Statistics, Statistical Mechanics,...

Source: http://arxiv.org/abs/1410.4217

4
4.0

Jun 29, 2018
06/18

by
Florian Maire; Nial Friel; Antonietta Mira; Adrian Raftery

texts

#
eye 4

#
favorite 0

#
comment 0

We propose Adaptive Incremental Mixture Markov chain Monte Carlo (AIMM), a novel approach to sample from challenging probability distributions defined on a general state-space. Typically, adaptive MCMC methods recursively update a parametric proposal kernel with a global rule; by contrast AIMM locally adapts a non-parametric kernel. AIMM is based on an independent Metropolis-Hastings proposal distribution which takes the form of a finite mixture of Gaussian distributions. Central to this...

Topics: Methodology, Computation, Statistics

Source: http://arxiv.org/abs/1604.08016

5
5.0

Jun 28, 2018
06/18

by
Sahil Garg; Aram Galstyan; Ulf Hermjakob; Daniel Marcu

texts

#
eye 5

#
favorite 0

#
comment 0

We advance the state of the art in biomolecular interaction extraction with three contributions: (i) We show that deep, Abstract Meaning Representations (AMR) significantly improve the accuracy of a biomolecular interaction extraction system when compared to a baseline that relies solely on surface- and syntax-based features; (ii) In contrast with previous approaches that infer relations on a sentence-by-sentence basis, we expand our framework to enable consistent predictions over sets of...

Topics: Information Theory, Mathematics, Learning, Information Retrieval, Computation and Language,...

Source: http://arxiv.org/abs/1512.01587

6
6.0

Jun 29, 2018
06/18

by
Hoon Hong; Zachary Hough; Irina A. Kogan

texts

#
eye 6

#
favorite 0

#
comment 0

We present a new algorithm for computing a $\mu$-basis of the syzygy module of $n$ polynomials in one variable over an arbitrary field $\mathbb{K}$. The algorithm is conceptually different from the previously-developed algorithms by Cox, Sederberg, Chen, Zheng, and Wang for $n=3$, and by Song and Goldman for an arbitrary $n$. It involves computing a "partial" reduced row-echelon form of a $ (2d+1)\times n(d+1)$ matrix over $\mathbb{K}$, where $d$ is the maximum degree of the input...

Topics: Symbolic Computation, Algebraic Geometry, Commutative Algebra, Computing Research Repository,...

Source: http://arxiv.org/abs/1603.04813

3
3.0

Jun 29, 2018
06/18

by
Shoaib Jameel; Steven Schockaert

texts

#
eye 3

#
favorite 0

#
comment 0

Conceptual spaces are geometric representations of conceptual knowledge, in which entities correspond to points, natural properties correspond to convex regions, and the dimensions of the space correspond to salient features. While conceptual spaces enable elegant models of various cognitive phenomena, the lack of automated methods for constructing such representations have so far limited their application in artificial intelligence. To address this issue, we propose a method which learns a...

Topics: Artificial Intelligence, Computation and Language, Computing Research Repository

Source: http://arxiv.org/abs/1602.05765

3
3.0

Jun 29, 2018
06/18

by
Axel Finke; Arnaud Doucet; Adam M. Johansen

texts

#
eye 3

#
favorite 0

#
comment 0

The embedded hidden Markov model (EHMM) sampling method is a Markov chain Monte Carlo (MCMC) technique for state inference in non-linear non-Gaussian state-space models which was proposed in Neal (2003); Neal et al. (2004) and extended in Shestopaloff and Neal (2016). An extension to Bayesian parameter inference was presented in Shestopaloff and Neal (2013). An alternative class of MCMC schemes addressing similar inference problems is provided by particle MCMC (PMCMC) methods (Andrieu et al....

Topics: Computation, Statistics

Source: http://arxiv.org/abs/1610.08962

15
15

Jun 27, 2018
06/18

by
Nicolas Chopin; Mathieu Gerber

texts

#
eye 15

#
favorite 0

#
comment 0

Sequential Monte Carlo algorithms (also known as particle filters) are popular methods to approximate filtering (and related) distributions of state-space models. However, they converge at the slow $1/\sqrt{N}$ rate, which may be an issue in real-time data-intensive scenarios. We give a brief outline of SQMC (Sequential Quasi-Monte Carlo), a variant of SMC based on low-discrepancy point sets proposed by Gerber and Chopin (2015), which converges at a faster rate, and we illustrate the greater...

Topics: Computation, Statistics

Source: http://arxiv.org/abs/1503.01631

3
3.0

Jun 30, 2018
06/18

by
Anthony Lee; Arnaud Doucet; Krzysztof Łatuszyński

texts

#
eye 3

#
favorite 0

#
comment 0

Consider an irreducible, Harris recurrent Markov chain of transition kernel {\Pi} and invariant probability measure {\pi}. If {\Pi} satisfies a minorization condition, then the split chain allows the identification of regeneration times which may be exploited to obtain perfect samples from {\pi}. Unfortunately, many transition kernels associated with complex Markov chain Monte Carlo algorithms are analytically intractable, so establishing a minorization condition and simulating the split chain...

Topics: Computation, Statistics

Source: http://arxiv.org/abs/1407.5770

11
11

Jun 28, 2018
06/18

by
Sridhar Mahadevan; Sarath Chandar

texts

#
eye 11

#
favorite 0

#
comment 0

Recent work has explored methods for learning continuous vector space word representations reflecting the underlying semantics of words. Simple vector space arithmetic using cosine distances has been shown to capture certain types of analogies, such as reasoning about plurals from singulars, past tense from present tense, etc. In this paper, we introduce a new approach to capture analogies in continuous word representations, based on modeling not just individual word vectors, but rather the...

Topics: Computation and Language, Computing Research Repository

Source: http://arxiv.org/abs/1507.07636

4
4.0

Jun 29, 2018
06/18

by
Prajit Ramachandran; Peter J. Liu; Quoc V. Le

texts

#
eye 4

#
favorite 0

#
comment 0

Sequence to sequence models are successful tools for supervised sequence learning tasks, such as machine translation. Despite their success, these models still require much labeled data and it is unclear how to improve them using unlabeled data, which is much less expensive to obtain. In this paper, we present simple changes that lead to a significant improvement in the accuracy of seq2seq models when the labeled set is small. Our method intializes the encoder and decoder of the seq2seq model...

Topics: Neural and Evolutionary Computing, Computation and Language, Computing Research Repository, Learning

Source: http://arxiv.org/abs/1611.02683

4
4.0

Jun 29, 2018
06/18

by
Joji Toyama; Masanori Misono; Masahiro Suzuki; Kotaro Nakayama; Yutaka Matsuo

texts

#
eye 4

#
favorite 0

#
comment 0

Although attention-based Neural Machine Translation have achieved great success, attention-mechanism cannot capture the entire meaning of the source sentence because the attention mechanism generates a target word depending heavily on the relevant parts of the source sentence. The report of earlier studies has introduced a latent variable to capture the entire meaning of sentence and achieved improvement on attention-based Neural Machine Translation. We follow this approach and we believe that...

Topics: Computation and Language, Computing Research Repository

Source: http://arxiv.org/abs/1611.08459

7
7.0

Jun 30, 2018
06/18

by
Panagiotis Tzirakis; George Trigeorgis; Mihalis A. Nicolaou; Björn Schuller; Stefanos Zafeiriou

texts

#
eye 7

#
favorite 0

#
comment 0

Automatic affect recognition is a challenging task due to the various modalities emotions can be expressed with. Applications can be found in many domains including multimedia retrieval and human computer interaction. In recent years, deep neural networks have been used with great success in determining emotional states. Inspired by this success, we propose an emotion recognition system using auditory and visual modalities. To capture the emotional content for various styles of speaking, robust...

Topics: Computing Research Repository, Computer Vision and Pattern Recognition, Computation and Language

Source: http://arxiv.org/abs/1704.08619