Paper Group ANR 442
Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder. Creating Causal Embeddings for Question Answering with Minimal Supervision. Regression-based Hypergraph Learning for Image Clustering and Classification. The Generalized Smallest Grammar Problem. Relating Knowledge and Coordinated Action: The Knowledge of Precondit …
Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
| Title | Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder |
| Authors | Soroush Vosoughi, Prashanth Vijayaraghavan, Deb Roy |
| Abstract | We present Tweet2Vec, a novel method for generating general-purpose vector representation of tweets. The model learns tweet embeddings using character-level CNN-LSTM encoder-decoder. We trained our model on 3 million, randomly selected English-language tweets. The model was evaluated using two methods: tweet semantic similarity and tweet sentiment categorization, outperforming the previous state-of-the-art in both tasks. The evaluations demonstrate the power of the tweet embeddings generated by our model for various tweet categorization tasks. The vector representations generated by our model are generic, and hence can be applied to a variety of tasks. Though the model presented in this paper is trained on English-language tweets, the method presented can be used to learn tweet embeddings for different languages. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2016-07-26 |
| URL | http://arxiv.org/abs/1607.07514v1 |
| http://arxiv.org/pdf/1607.07514v1.pdf | |
| PWC | https://paperswithcode.com/paper/tweet2vec-learning-tweet-embeddings-using |
| Repo | |
| Framework | |
Creating Causal Embeddings for Question Answering with Minimal Supervision
| Title | Creating Causal Embeddings for Question Answering with Minimal Supervision |
| Authors | Rebecca Sharp, Mihai Surdeanu, Peter Jansen, Peter Clark, Michael Hammond |
| Abstract | A common model for question answering (QA) is that a good answer is one that is closely related to the question, where relatedness is often determined using general-purpose lexical models such as word embeddings. We argue that a better approach is to look for answers that are related to the question in a relevant way, according to the information need of the question, which may be determined through task-specific embeddings. With causality as a use case, we implement this insight in three steps. First, we generate causal embeddings cost-effectively by bootstrapping cause-effect pairs extracted from free text using a small set of seed patterns. Second, we train dedicated embeddings over this data, by using task-specific contexts, i.e., the context of a cause is its effect. Finally, we extend a state-of-the-art reranking approach for QA to incorporate these causal embeddings. We evaluate the causal embedding models both directly with a casual implication task, and indirectly, in a downstream causal QA task using data from Yahoo! Answers. We show that explicitly modeling causality improves performance in both tasks. In the QA task our best model achieves 37.3% P@1, significantly outperforming a strong baseline by 7.7% (relative). |
| Tasks | Question Answering, Word Embeddings |
| Published | 2016-09-26 |
| URL | http://arxiv.org/abs/1609.08097v1 |
| http://arxiv.org/pdf/1609.08097v1.pdf | |
| PWC | https://paperswithcode.com/paper/creating-causal-embeddings-for-question |
| Repo | |
| Framework | |
Regression-based Hypergraph Learning for Image Clustering and Classification
| Title | Regression-based Hypergraph Learning for Image Clustering and Classification |
| Authors | Sheng Huang, Dan Yang, Bo Liu, Xiaohong Zhang |
| Abstract | Inspired by the recently remarkable successes of Sparse Representation (SR), Collaborative Representation (CR) and sparse graph, we present a novel hypergraph model named Regression-based Hypergraph (RH) which utilizes the regression models to construct the high quality hypergraphs. Moreover, we plug RH into two conventional hypergraph learning frameworks, namely hypergraph spectral clustering and hypergraph transduction, to present Regression-based Hypergraph Spectral Clustering (RHSC) and Regression-based Hypergraph Transduction (RHT) models for addressing the image clustering and classification issues. Sparse Representation and Collaborative Representation are employed to instantiate two RH instances and their RHSC and RHT algorithms. The experimental results on six popular image databases demonstrate that the proposed RH learning algorithms achieve promising image clustering and classification performances, and also validate that RH can inherit the desirable properties from both hypergraph models and regression models. |
| Tasks | Image Clustering |
| Published | 2016-03-14 |
| URL | http://arxiv.org/abs/1603.04150v1 |
| http://arxiv.org/pdf/1603.04150v1.pdf | |
| PWC | https://paperswithcode.com/paper/regression-based-hypergraph-learning-for |
| Repo | |
| Framework | |
The Generalized Smallest Grammar Problem
| Title | The Generalized Smallest Grammar Problem |
| Authors | Payam Siyari, Matthias Gallé |
| Abstract | The Smallest Grammar Problem – the problem of finding the smallest context-free grammar that generates exactly one given sequence – has never been successfully applied to grammatical inference. We investigate the reasons and propose an extended formulation that seeks to minimize non-recursive grammars, instead of straight-line programs. In addition, we provide very efficient algorithms that approximate the minimization problem of this class of grammars. Our empirical evaluation shows that we are able to find smaller models than the current best approximations to the Smallest Grammar Problem on standard benchmarks, and that the inferred rules capture much better the syntactic structure of natural language. |
| Tasks | |
| Published | 2016-08-31 |
| URL | http://arxiv.org/abs/1608.08927v1 |
| http://arxiv.org/pdf/1608.08927v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-generalized-smallest-grammar-problem |
| Repo | |
| Framework | |
Relating Knowledge and Coordinated Action: The Knowledge of Preconditions Principle
| Title | Relating Knowledge and Coordinated Action: The Knowledge of Preconditions Principle |
| Authors | Yoram Moses |
| Abstract | The Knowledge of Preconditions principle (KoP) is proposed as a widely applicable connection between knowledge and action in multi-agent systems. Roughly speaking, it asserts that if some condition is a necessary condition for performing a given action A, then knowing that this condition holds is also a necessary condition for performing A. Since the specifications of tasks often involve necessary conditions for actions, the KoP principle shows that such specifications induce knowledge preconditions for the actions. Distributed protocols or multi-agent plans that satisfy the specifications must ensure that this knowledge be attained, and that it is detected by the agents as a condition for action. The knowledge of preconditions principle is formalised in the runs and systems framework, and is proven to hold in a wide class of settings. Well-known connections between knowledge and coordinated action are extended and shown to derive directly from the KoP principle: a “common knowledge of preconditions” principle is established showing that common knowledge is a necessary condition for performing simultaneous actions, and a “nested knowledge of preconditions” principle is proven, showing that coordinating actions to be performed in linear temporal order requires a corresponding form of nested knowledge. |
| Tasks | |
| Published | 2016-06-24 |
| URL | http://arxiv.org/abs/1606.07525v1 |
| http://arxiv.org/pdf/1606.07525v1.pdf | |
| PWC | https://paperswithcode.com/paper/relating-knowledge-and-coordinated-action-the |
| Repo | |
| Framework | |
A Semi-automatic Method for Efficient Detection of Stories on Social Media
| Title | A Semi-automatic Method for Efficient Detection of Stories on Social Media |
| Authors | Soroush Vosoughi, Deb Roy |
| Abstract | Twitter has become one of the main sources of news for many people. As real-world events and emergencies unfold, Twitter is abuzz with hundreds of thousands of stories about the events. Some of these stories are harmless, while others could potentially be life-saving or sources of malicious rumors. Thus, it is critically important to be able to efficiently track stories that spread on Twitter during these events. In this paper, we present a novel semi-automatic tool that enables users to efficiently identify and track stories about real-world events on Twitter. We ran a user study with 25 participants, demonstrating that compared to more conventional methods, our tool can increase the speed and the accuracy with which users can track stories about real-world events. |
| Tasks | |
| Published | 2016-05-17 |
| URL | http://arxiv.org/abs/1605.05134v1 |
| http://arxiv.org/pdf/1605.05134v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-semi-automatic-method-for-efficient |
| Repo | |
| Framework | |
Scalable Metric Learning via Weighted Approximate Rank Component Analysis
| Title | Scalable Metric Learning via Weighted Approximate Rank Component Analysis |
| Authors | Cijo Jose, Francois Fleuret |
| Abstract | We are interested in the large-scale learning of Mahalanobis distances, with a particular focus on person re-identification. We propose a metric learning formulation called Weighted Approximate Rank Component Analysis (WARCA). WARCA optimizes the precision at top ranks by combining the WARP loss with a regularizer that favors orthonormal linear mappings, and avoids rank-deficient embeddings. Using this new regularizer allows us to adapt the large-scale WSABIE procedure and to leverage the Adam stochastic optimization algorithm, which results in an algorithm that scales gracefully to very large data-sets. Also, we derive a kernelized version which allows to take advantage of state-of-the-art features for re-identification when data-set size permits kernel computation. Benchmarks on recent and standard re-identification data-sets show that our method beats existing state-of-the-art techniques both in term of accuracy and speed. We also provide experimental analysis to shade lights on the properties of the regularizer we use, and how it improves performance. |
| Tasks | Metric Learning, Person Re-Identification, Stochastic Optimization |
| Published | 2016-03-01 |
| URL | http://arxiv.org/abs/1603.00370v2 |
| http://arxiv.org/pdf/1603.00370v2.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-metric-learning-via-weighted |
| Repo | |
| Framework | |
How Far are We from Solving Pedestrian Detection?
| Title | How Far are We from Solving Pedestrian Detection? |
| Authors | Shanshan Zhang, Rodrigo Benenson, Mohamed Omran, Jan Hosang, Bernt Schiele |
| Abstract | Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods and the “perfect single frame detector”. We enable our analysis by creating a human baseline for pedestrian detection (over the Caltech dataset), and by manually clustering the recurrent errors of a top detector. Our results characterize both localization and background-versus-foreground errors. To address localization errors we study the impact of training annotation noise on the detector performance, and show that we can improve even with a small portion of sanitized training data. To address background/foreground discrimination, we study convnets for pedestrian detection, and discuss which factors affect their performance. Other than our in-depth analysis, we report top performance on the Caltech dataset, and provide a new sanitized set of training and test annotations. |
| Tasks | Pedestrian Detection |
| Published | 2016-02-03 |
| URL | http://arxiv.org/abs/1602.01237v2 |
| http://arxiv.org/pdf/1602.01237v2.pdf | |
| PWC | https://paperswithcode.com/paper/how-far-are-we-from-solving-pedestrian |
| Repo | |
| Framework | |
Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks
| Title | Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks |
| Authors | Pichao Wang, Wanqing Li, Chuankun Li, Yonghong Hou |
| Abstract | Convolutional Neural Networks (ConvNets) have recently shown promising performance in many computer vision tasks, especially image-based recognition. How to effectively apply ConvNets to sequence-based data is still an open problem. This paper proposes an effective yet simple method to represent spatio-temporal information carried in $3D$ skeleton sequences into three $2D$ images by encoding the joint trajectories and their dynamics into color distribution in the images, referred to as Joint Trajectory Maps (JTM), and adopts ConvNets to learn the discriminative features for human action recognition. Such an image-based representation enables us to fine-tune existing ConvNets models for the classification of skeleton sequences without training the networks afresh. The three JTMs are generated in three orthogonal planes and provide complimentary information to each other. The final recognition is further improved through multiply score fusion of the three JTMs. The proposed method was evaluated on four public benchmark datasets, the large NTU RGB+D Dataset, MSRC-12 Kinect Gesture Dataset (MSRC-12), G3D Dataset and UTD Multimodal Human Action Dataset (UTD-MHAD) and achieved the state-of-the-art results. |
| Tasks | Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2016-12-30 |
| URL | http://arxiv.org/abs/1612.09401v1 |
| http://arxiv.org/pdf/1612.09401v1.pdf | |
| PWC | https://paperswithcode.com/paper/action-recognition-based-on-joint-trajectory |
| Repo | |
| Framework | |
Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent
| Title | Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent |
| Authors | Qinqing Zheng, John Lafferty |
| Abstract | We address the rectangular matrix completion problem by lifting the unknown matrix to a positive semidefinite matrix in higher dimension, and optimizing a nonconvex objective over the semidefinite factor using a simple gradient descent scheme. With $O( \mu r^2 \kappa^2 n \max(\mu, \log n))$ random observations of a $n_1 \times n_2$ $\mu$-incoherent matrix of rank $r$ and condition number $\kappa$, where $n = \max(n_1, n_2)$, the algorithm linearly converges to the global optimum with high probability. |
| Tasks | Matrix Completion |
| Published | 2016-05-23 |
| URL | http://arxiv.org/abs/1605.07051v2 |
| http://arxiv.org/pdf/1605.07051v2.pdf | |
| PWC | https://paperswithcode.com/paper/convergence-analysis-for-rectangular-matrix |
| Repo | |
| Framework | |
Real-Time Web Scale Event Summarization Using Sequential Decision Making
| Title | Real-Time Web Scale Event Summarization Using Sequential Decision Making |
| Authors | Chris Kedzie, Fernando Diaz, Kathleen McKeown |
| Abstract | We present a system based on sequential decision making for the online summarization of massive document streams, such as those found on the web. Given an event of interest (e.g. “Boston marathon bombing”), our system is able to filter the stream for relevance and produce a series of short text updates describing the event as it unfolds over time. Unlike previous work, our approach is able to jointly model the relevance, comprehensiveness, novelty, and timeliness required by time-sensitive queries. We demonstrate a 28.3% improvement in summary F1 and a 43.8% improvement in time-sensitive F1 metrics. |
| Tasks | Decision Making |
| Published | 2016-05-12 |
| URL | http://arxiv.org/abs/1605.03664v1 |
| http://arxiv.org/pdf/1605.03664v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-web-scale-event-summarization-using |
| Repo | |
| Framework | |
PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition
| Title | PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition |
| Authors | Brandon RichardWebster, Samuel E. Anthony, Walter J. Scheirer |
| Abstract | By providing substantial amounts of data and standardized evaluation protocols, datasets in computer vision have helped fuel advances across all areas of visual recognition. But even in light of breakthrough results on recent benchmarks, it is still fair to ask if our recognition algorithms are doing as well as we think they are. The vision sciences at large make use of a very different evaluation regime known as Visual Psychophysics to study visual perception. Psychophysics is the quantitative examination of the relationships between controlled stimuli and the behavioral responses they elicit in experimental test subjects. Instead of using summary statistics to gauge performance, psychophysics directs us to construct item-response curves made up of individual stimulus responses to find perceptual thresholds, thus allowing one to identify the exact point at which a subject can no longer reliably recognize the stimulus class. In this article, we introduce a comprehensive evaluation framework for visual recognition models that is underpinned by this methodology. Over millions of procedurally rendered 3D scenes and 2D images, we compare the performance of well-known convolutional neural networks. Our results bring into question recent claims of human-like performance, and provide a path forward for correcting newly surfaced algorithmic deficiencies. |
| Tasks | |
| Published | 2016-11-19 |
| URL | http://arxiv.org/abs/1611.06448v6 |
| http://arxiv.org/pdf/1611.06448v6.pdf | |
| PWC | https://paperswithcode.com/paper/psyphy-a-psychophysics-driven-evaluation |
| Repo | |
| Framework | |
Strong Backdoors for Default Logic
| Title | Strong Backdoors for Default Logic |
| Authors | Johannes K. Fichte, Arne Meier, Irina Schindler |
| Abstract | In this paper, we introduce a notion of backdoors to Reiter’s propositional default logic and study structural properties of it. Also we consider the problems of backdoor detection (parameterised by the solution size) as well as backdoor evaluation (parameterised by the size of the given backdoor), for various kinds of target classes (cnf, horn, krom, monotone, identity). We show that backdoor detection is fixed-parameter tractable for the considered target classes, and backdoor evaluation is either fixed-parameter tractable, in para-DP2 , or in para-NP, depending on the target class. |
| Tasks | |
| Published | 2016-02-19 |
| URL | http://arxiv.org/abs/1602.06052v1 |
| http://arxiv.org/pdf/1602.06052v1.pdf | |
| PWC | https://paperswithcode.com/paper/strong-backdoors-for-default-logic |
| Repo | |
| Framework | |
Inference via Message Passing on Partially Labeled Stochastic Block Models
| Title | Inference via Message Passing on Partially Labeled Stochastic Block Models |
| Authors | T. Tony Cai, Tengyuan Liang, Alexander Rakhlin |
| Abstract | We study the community detection and recovery problem in partially-labeled stochastic block models (SBM). We develop a fast linearized message-passing algorithm to reconstruct labels for SBM (with $n$ nodes, $k$ blocks, $p,q$ intra and inter block connectivity) when $\delta$ proportion of node labels are revealed. The signal-to-noise ratio ${\sf SNR}(n,k,p,q,\delta)$ is shown to characterize the fundamental limitations of inference via local algorithms. On the one hand, when ${\sf SNR}>1$, the linearized message-passing algorithm provides the statistical inference guarantee with mis-classification rate at most $\exp(-({\sf SNR}-1)/2)$, thus interpolating smoothly between strong and weak consistency. This exponential dependence improves upon the known error rate $({\sf SNR}-1)^{-1}$ in the literature on weak recovery. On the other hand, when ${\sf SNR}<1$ (for $k=2$) and ${\sf SNR}<1/4$ (for general growing $k$), we prove that local algorithms suffer an error rate at least $\frac{1}{2} - \sqrt{\delta \cdot {\sf SNR}}$, which is only slightly better than random guess for small $\delta$. |
| Tasks | Community Detection |
| Published | 2016-03-22 |
| URL | http://arxiv.org/abs/1603.06923v1 |
| http://arxiv.org/pdf/1603.06923v1.pdf | |
| PWC | https://paperswithcode.com/paper/inference-via-message-passing-on-partially |
| Repo | |
| Framework | |
Deep Model Compression: Distilling Knowledge from Noisy Teachers
| Title | Deep Model Compression: Distilling Knowledge from Noisy Teachers |
| Authors | Bharat Bhusan Sau, Vineeth N. Balasubramanian |
| Abstract | The remarkable successes of deep learning models across various applications have resulted in the design of deeper networks that can solve complex problems. However, the increasing depth of such models also results in a higher storage and runtime complexity, which restricts the deployability of such very deep models on mobile and portable devices, which have limited storage and battery capacity. While many methods have been proposed for deep model compression in recent years, almost all of them have focused on reducing storage complexity. In this work, we extend the teacher-student framework for deep model compression, since it has the potential to address runtime and train time complexity too. We propose a simple methodology to include a noise-based regularizer while training the student from the teacher, which provides a healthy improvement in the performance of the student network. Our experiments on the CIFAR-10, SVHN and MNIST datasets show promising improvement, with the best performance on the CIFAR-10 dataset. We also conduct a comprehensive empirical evaluation of the proposed method under related settings on the CIFAR-10 dataset to show the promise of the proposed approach. |
| Tasks | Model Compression |
| Published | 2016-10-30 |
| URL | http://arxiv.org/abs/1610.09650v2 |
| http://arxiv.org/pdf/1610.09650v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-model-compression-distilling-knowledge |
| Repo | |
| Framework | |
