Paper Group ANR 385
![Paper Group ANR 385](/2016/images/pwc/paper-arxiv_hu144ec288a26b3e360d673e256787de3e_28623_900x500_fit_q75_box.jpg)
Automatic Identification of Sarcasm Target: An Introductory Approach. Are Word Embedding-based Features Useful for Sarcasm Detection?. Deep Identity-aware Transfer of Facial Attributes. Applying Interval Type-2 Fuzzy Rule Based Classifiers Through a Cluster-Based Class Representation. Measuring the reliability of MCMC inference with bidirectional M …
Automatic Identification of Sarcasm Target: An Introductory Approach
Title | Automatic Identification of Sarcasm Target: An Introductory Approach |
Authors | Aditya Joshi, Pranav Goel, Pushpak Bhattacharyya, Mark Carman |
Abstract | Past work in computational sarcasm deals primarily with sarcasm detection. In this paper, we introduce a novel, related problem: sarcasm target identification i.e., extracting the target of ridicule in a sarcastic sentence). We present an introductory approach for sarcasm target identification. Our approach employs two types of extractors: one based on rules, and another consisting of a statistical classifier. To compare our approach, we use two baselines: a na"ive baseline and another baseline based on work in sentiment target identification. We perform our experiments on book snippets and tweets, and show that our hybrid approach performs better than the two baselines and also, in comparison with using the two extractors individually. Our introductory approach establishes the viability of sarcasm target identification, and will serve as a baseline for future work. |
Tasks | Sarcasm Detection |
Published | 2016-10-22 |
URL | http://arxiv.org/abs/1610.07091v2 |
http://arxiv.org/pdf/1610.07091v2.pdf | |
PWC | https://paperswithcode.com/paper/automatic-identification-of-sarcasm-target-an |
Repo | |
Framework | |
Are Word Embedding-based Features Useful for Sarcasm Detection?
Title | Are Word Embedding-based Features Useful for Sarcasm Detection? |
Authors | Aditya Joshi, Vaibhav Tripathi, Kevin Patel, Pushpak Bhattacharyya, Mark Carman |
Abstract | This paper makes a simple increment to state-of-the-art in sarcasm detection research. Existing approaches are unable to capture subtle forms of context incongruity which lies at the heart of sarcasm. We explore if prior work can be enhanced using semantic similarity/discordance between word embeddings. We augment word embedding-based features to four feature sets reported in the past. We also experiment with four types of word embeddings. We observe an improvement in sarcasm detection, irrespective of the word embedding used or the original feature set to which our features are augmented. For example, this augmentation results in an improvement in F-score of around 4% for three out of these four feature sets, and a minor degradation in case of the fourth, when Word2Vec embeddings are used. Finally, a comparison of the four embeddings shows that Word2Vec and dependency weight-based features outperform LSA and GloVe, in terms of their benefit to sarcasm detection. |
Tasks | Sarcasm Detection, Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
Published | 2016-10-04 |
URL | http://arxiv.org/abs/1610.00883v1 |
http://arxiv.org/pdf/1610.00883v1.pdf | |
PWC | https://paperswithcode.com/paper/are-word-embedding-based-features-useful-for |
Repo | |
Framework | |
Deep Identity-aware Transfer of Facial Attributes
Title | Deep Identity-aware Transfer of Facial Attributes |
Authors | Mu Li, Wangmeng Zuo, David Zhang |
Abstract | This paper presents a Deep convolutional network model for Identity-Aware Transfer (DIAT) of facial attributes. Given the source input image and the reference attribute, DIAT aims to generate a facial image that owns the reference attribute as well as keeps the same or similar identity to the input image. In general, our model consists of a mask network and an attribute transform network which work in synergy to generate a photo-realistic facial image with the reference attribute. Considering that the reference attribute may be only related to some parts of the image, the mask network is introduced to avoid the incorrect editing on attribute irrelevant region. Then the estimated mask is adopted to combine the input and transformed image for producing the transfer result. For joint training of transform network and mask network, we incorporate the adversarial attribute loss, identity-aware adaptive perceptual loss, and VGG-FACE based identity loss. Furthermore, a denoising network is presented to serve for perceptual regularization to suppress the artifacts in transfer result, while an attribute ratio regularization is introduced to constrain the size of attribute relevant region. Our DIAT can provide a unified solution for several representative facial attribute transfer tasks, e.g., expression transfer, accessory removal, age progression, and gender transfer, and can be extended for other face enhancement tasks such as face hallucination. The experimental results validate the effectiveness of the proposed method. Even for the identity-related attribute (e.g., gender), our DIAT can obtain visually impressive results by changing the attribute while retaining most identity-aware features. |
Tasks | Denoising, Face Hallucination, Image-to-Image Translation |
Published | 2016-10-18 |
URL | http://arxiv.org/abs/1610.05586v2 |
http://arxiv.org/pdf/1610.05586v2.pdf | |
PWC | https://paperswithcode.com/paper/deep-identity-aware-transfer-of-facial |
Repo | |
Framework | |
Applying Interval Type-2 Fuzzy Rule Based Classifiers Through a Cluster-Based Class Representation
Title | Applying Interval Type-2 Fuzzy Rule Based Classifiers Through a Cluster-Based Class Representation |
Authors | Javier Navarro, Christian Wagner, Uwe Aickelin |
Abstract | Fuzzy Rule-Based Classification Systems (FRBCSs) have the potential to provide so-called interpretable classifiers, i.e. classifiers which can be introspective, understood, validated and augmented by human experts by relying on fuzzy-set based rules. This paper builds on prior work for interval type-2 fuzzy set based FRBCs where the fuzzy sets and rules of the classifier are generated using an initial clustering stage. By introducing Subtractive Clustering in order to identify multiple cluster prototypes, the proposed approach has the potential to deliver improved classification performance while maintaining good interpretability, i.e. without resulting in an excessive number of rules. The paper provides a detailed overview of the proposed FRBC framework, followed by a series of exploratory experiments on both linearly and non-linearly separable datasets, comparing results to existing rule-based and SVM approaches. Overall, initial results indicate that the approach enables comparable classification performance to non rule-based classifiers such as SVM, while often achieving this with a very small number of rules. |
Tasks | |
Published | 2016-07-21 |
URL | http://arxiv.org/abs/1607.06186v1 |
http://arxiv.org/pdf/1607.06186v1.pdf | |
PWC | https://paperswithcode.com/paper/applying-interval-type-2-fuzzy-rule-based |
Repo | |
Framework | |
Measuring the reliability of MCMC inference with bidirectional Monte Carlo
Title | Measuring the reliability of MCMC inference with bidirectional Monte Carlo |
Authors | Roger B. Grosse, Siddharth Ancha, Daniel M. Roy |
Abstract | Markov chain Monte Carlo (MCMC) is one of the main workhorses of probabilistic inference, but it is notoriously hard to measure the quality of approximate posterior samples. This challenge is particularly salient in black box inference methods, which can hide details and obscure inference failures. In this work, we extend the recently introduced bidirectional Monte Carlo technique to evaluate MCMC-based posterior inference algorithms. By running annealed importance sampling (AIS) chains both from prior to posterior and vice versa on simulated data, we upper bound in expectation the symmetrized KL divergence between the true posterior distribution and the distribution of approximate samples. We present Bounding Divergences with REverse Annealing (BREAD), a protocol for validating the relevance of simulated data experiments to real datasets, and integrate it into two probabilistic programming languages: WebPPL and Stan. As an example of how BREAD can be used to guide the design of inference algorithms, we apply it to study the effectiveness of different model representations in both WebPPL and Stan. |
Tasks | Probabilistic Programming |
Published | 2016-06-07 |
URL | http://arxiv.org/abs/1606.02275v1 |
http://arxiv.org/pdf/1606.02275v1.pdf | |
PWC | https://paperswithcode.com/paper/measuring-the-reliability-of-mcmc-inference |
Repo | |
Framework | |
Bachelor’s thesis on generative probabilistic programming (in Russian language, June 2014)
Title | Bachelor’s thesis on generative probabilistic programming (in Russian language, June 2014) |
Authors | Yura N Perov |
Abstract | This Bachelor’s thesis, written in Russian, is devoted to a relatively new direction in the field of machine learning and artificial intelligence, namely probabilistic programming. The thesis gives a brief overview to the already existing probabilistic programming languages: Church, Venture, and Anglican. It also describes the results of the first experiments on the automatic induction of probabilistic programs. The thesis was submitted, in June 2014, in partial fulfilment of the requirements for the degree of Bachelor of Science in Mathematics in the Department of Mathematics and Computer Science, Siberian Federal University, Krasnoyarsk, Russia. The work, which is described in this thesis, has been performing in 2012-2014 in the Massachusetts Institute of Technology and in the University of Oxford by the colleagues of the author and by himself. |
Tasks | Probabilistic Programming |
Published | 2016-01-26 |
URL | http://arxiv.org/abs/1601.07224v1 |
http://arxiv.org/pdf/1601.07224v1.pdf | |
PWC | https://paperswithcode.com/paper/bachelors-thesis-on-generative-probabilistic |
Repo | |
Framework | |
Relational Models
Title | Relational Models |
Authors | Volker Tresp, Maximilian Nickel |
Abstract | We provide a survey on relational models. Relational models describe complete networked {domains by taking into account global dependencies in the data}. Relational models can lead to more accurate predictions if compared to non-relational machine learning approaches. Relational models typically are based on probabilistic graphical models, e.g., Bayesian networks, Markov networks, or latent variable models. Relational models have applications in social networks analysis, the modeling of knowledge graphs, bioinformatics, recommendation systems, natural language processing, medical decision support, and linked data. |
Tasks | Knowledge Graphs, Latent Variable Models, Recommendation Systems |
Published | 2016-09-11 |
URL | http://arxiv.org/abs/1609.03145v1 |
http://arxiv.org/pdf/1609.03145v1.pdf | |
PWC | https://paperswithcode.com/paper/relational-models |
Repo | |
Framework | |
Max-plus statistical leverage scores
Title | Max-plus statistical leverage scores |
Authors | James Hook |
Abstract | The statistical leverage scores of a complex matrix $A\in\mathbb{C}^{n\times d}$ record the degree of alignment between col$(A)$ and the coordinate axes in $\mathbb{C}^n$. These score are used in random sampling algorithms for solving certain numerical linear algebra problems. In this paper we present a max-plus algebraic analogue for statistical leverage scores. We show that max-plus statistical leverage scores can be used to calculate the exact asymptotic behavior of the conventional statistical leverage scores of a generic matrices of Puiseux series and also provide a novel way to approximate the conventional statistical leverage scores of a fixed or complex matrix. The advantage of approximating a complex matrices scores with max-plus scores is that the max-plus scores can be computed very quickly. This approximation is typically accurate to within an order or magnitude and should be useful in practical problems where the true scores are known to vary widely. |
Tasks | |
Published | 2016-09-29 |
URL | http://arxiv.org/abs/1609.09519v1 |
http://arxiv.org/pdf/1609.09519v1.pdf | |
PWC | https://paperswithcode.com/paper/max-plus-statistical-leverage-scores |
Repo | |
Framework | |
Proportional Rankings
Title | Proportional Rankings |
Authors | Piotr Skowron, Martin Lackner, Markus Brill, Dominik Peters, Edith Elkind |
Abstract | In this paper we extend the principle of proportional representation to rankings. We consider the setting where alternatives need to be ranked based on approval preferences. In this setting, proportional representation requires that cohesive groups of voters are represented proportionally in each initial segment of the ranking. Proportional rankings are desirable in situations where initial segments of different lengths may be relevant, e.g., hiring decisions (if it is unclear how many positions are to be filled), the presentation of competing proposals on a liquid democracy platform (if it is unclear how many proposals participants are taking into consideration), or recommender systems (if a ranking has to accommodate different user types). We study the proportional representation provided by several ranking methods and prove theoretical guarantees. Furthermore, we experimentally evaluate these methods and present preliminary evidence as to which methods are most suitable for producing proportional rankings. |
Tasks | Recommendation Systems |
Published | 2016-12-05 |
URL | http://arxiv.org/abs/1612.01434v1 |
http://arxiv.org/pdf/1612.01434v1.pdf | |
PWC | https://paperswithcode.com/paper/proportional-rankings |
Repo | |
Framework | |
A Novel Framework based on SVDD to Classify Water Saturation from Seismic Attributes
Title | A Novel Framework based on SVDD to Classify Water Saturation from Seismic Attributes |
Authors | Soumi Chaki, Akhilesh Kumar Verma, Aurobinda Routray, William K. Mohanty, Mamata Jenamani |
Abstract | Water saturation is an important property in reservoir engineering domain. Thus, satisfactory classification of water saturation from seismic attributes is beneficial for reservoir characterization. However, diverse and non-linear nature of subsurface attributes makes the classification task difficult. In this context, this paper proposes a generalized Support Vector Data Description (SVDD) based novel classification framework to classify water saturation into two classes (Class high and Class low) from three seismic attributes seismic impedance, amplitude envelop, and seismic sweetness. G-metric means and program execution time are used to quantify the performance of the proposed framework along with established supervised classifiers. The documented results imply that the proposed framework is superior to existing classifiers. The present study is envisioned to contribute in further reservoir modeling. |
Tasks | |
Published | 2016-12-02 |
URL | http://arxiv.org/abs/1612.00841v1 |
http://arxiv.org/pdf/1612.00841v1.pdf | |
PWC | https://paperswithcode.com/paper/a-novel-framework-based-on-svdd-to-classify |
Repo | |
Framework | |
Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction
Title | Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction |
Authors | Weizhong Zhang, Bin Hong, Wei Liu, Jieping Ye, Deng Cai, Xiaofei He, Jie Wang |
Abstract | Sparse support vector machine (SVM) is a popular classification technique that can simultaneously learn a small set of the most interpretable features and identify the support vectors. It has achieved great successes in many real-world applications. However, for large-scale problems involving a huge number of samples and ultra-high dimensional features, solving sparse SVMs remains challenging. By noting that sparse SVMs induce sparsities in both feature and sample spaces, we propose a novel approach, which is based on accurate estimations of the primal and dual optima of sparse SVMs, to simultaneously identify the inactive features and samples that are guaranteed to be irrelevant to the outputs. Thus, we can remove the identified inactive samples and features from the training phase, leading to substantial savings in the computational cost without sacrificing the accuracy. Moreover, we show that our method can be extended to multi-class sparse support vector machines. To the best of our knowledge, the proposed method is the \emph{first} \emph{static} feature and sample reduction method for sparse SVMs and multi-class sparse SVMs. Experiments on both synthetic and real data sets demonstrate that our approach significantly outperforms state-of-the-art methods and the speedup gained by our approach can be orders of magnitude. |
Tasks | |
Published | 2016-07-24 |
URL | https://arxiv.org/abs/1607.06996v6 |
https://arxiv.org/pdf/1607.06996v6.pdf | |
PWC | https://paperswithcode.com/paper/scaling-up-sparse-support-vector-machines-by |
Repo | |
Framework | |
Low-complexity feedback-channel-free distributed video coding using Local Rank Transform
Title | Low-complexity feedback-channel-free distributed video coding using Local Rank Transform |
Authors | P Raj Bhagath, Kallol Mallick, Jayanta Mukherjee, Sudipta Mukopadhayay |
Abstract | In this paper, we propose a new feedback-channel-free Distributed Video Coding (DVC) algorithm using Local Rank Transform (LRT). The encoder computes LRT by considering selected neighborhood pixels of Wyner-Ziv frame. The ranks from the modified LRT are merged, and their positions are entropy coded and sent to the decoder. In addition, means of each block of Wyner-Ziv frame are also transmitted to assist motion estimation. Using these measurements, the decoder generates side information (SI) by implementing motion estimation and compensation in LRT domain. An iterative algorithm is executed on SI using LRT to reconstruct the Wyner-Ziv frame. Experimental results show that the coding efficiency of our codec is close to the efficiency of pixel domain distributed video coders based on Low-Density Parity Check and Accumulate (LDPCA) or turbo codes, with less encoder complexity. |
Tasks | Motion Estimation |
Published | 2016-07-15 |
URL | http://arxiv.org/abs/1607.07697v1 |
http://arxiv.org/pdf/1607.07697v1.pdf | |
PWC | https://paperswithcode.com/paper/low-complexity-feedback-channel-free |
Repo | |
Framework | |
Empirical Gaussian priors for cross-lingual transfer learning
Title | Empirical Gaussian priors for cross-lingual transfer learning |
Authors | Anders Søgaard |
Abstract | Sequence model learning algorithms typically maximize log-likelihood minus the norm of the model (or minimize Hamming loss + norm). In cross-lingual part-of-speech (POS) tagging, our target language training data consists of sequences of sentences with word-by-word labels projected from translations in $k$ languages for which we have labeled data, via word alignments. Our training data is therefore very noisy, and if Rademacher complexity is high, learning algorithms are prone to overfit. Norm-based regularization assumes a constant width and zero mean prior. We instead propose to use the $k$ source language models to estimate the parameters of a Gaussian prior for learning new POS taggers. This leads to significantly better performance in multi-source transfer set-ups. We also present a drop-out version that injects (empirical) Gaussian noise during online learning. Finally, we note that using empirical Gaussian priors leads to much lower Rademacher complexity, and is superior to optimally weighted model interpolation. |
Tasks | Cross-Lingual Transfer, Part-Of-Speech Tagging, Transfer Learning |
Published | 2016-01-09 |
URL | http://arxiv.org/abs/1601.02166v1 |
http://arxiv.org/pdf/1601.02166v1.pdf | |
PWC | https://paperswithcode.com/paper/empirical-gaussian-priors-for-cross-lingual |
Repo | |
Framework | |
A Logic of Knowing Why
Title | A Logic of Knowing Why |
Authors | Chao Xu, Yanjing Wang, Thomas Studer |
Abstract | When we say “I know why he was late”, we know not only the fact that he was late, but also an explanation of this fact. We propose a logical framework of “knowing why” inspired by the existing formal studies on why-questions, scientific explanation, and justification logic. We introduce the Ky_i operator into the language of epistemic logic to express “agent i knows why phi” and propose a Kripke-style semantics of such expressions in terms of knowing an explanation of phi. We obtain two sound and complete axiomatizations w.r.t. two different model classes depending on different assumptions about introspection. |
Tasks | |
Published | 2016-09-21 |
URL | http://arxiv.org/abs/1609.06405v2 |
http://arxiv.org/pdf/1609.06405v2.pdf | |
PWC | https://paperswithcode.com/paper/a-logic-of-knowing-why |
Repo | |
Framework | |
Incremental Factorization Machines for Persistently Cold-starting Online Item Recommendation
Title | Incremental Factorization Machines for Persistently Cold-starting Online Item Recommendation |
Authors | Takuya Kitazawa |
Abstract | Real-world item recommenders commonly suffer from a persistent cold-start problem which is caused by dynamically changing users and items. In order to overcome the problem, several context-aware recommendation techniques have been recently proposed. In terms of both feasibility and performance, factorization machine (FM) is one of the most promising methods as generalization of the conventional matrix factorization techniques. However, since online algorithms are suitable for dynamic data, the static FMs are still inadequate. Thus, this paper proposes incremental FMs (iFMs), a general online factorization framework, and specially extends iFMs into an online item recommender. The proposed framework can be a promising baseline for further development of the production recommender systems. Evaluation is done empirically both on synthetic and real-world unstable datasets. |
Tasks | Recommendation Systems |
Published | 2016-07-11 |
URL | http://arxiv.org/abs/1607.02858v1 |
http://arxiv.org/pdf/1607.02858v1.pdf | |
PWC | https://paperswithcode.com/paper/incremental-factorization-machines-for |
Repo | |
Framework | |