Paper Group NANR 16
Building timelines of soccer matches from Twitter. Bayesian Dyadic Trees and Histograms for Regression. Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications. Zero-Inflated Exponential Family Embeddings. Clustering High Dimensional Dynamic Data Streams. Multiple Clustering Views from Multiple Uncertain Experts. Machine Learni …
Building timelines of soccer matches from Twitter
| Title | Building timelines of soccer matches from Twitter |
| Authors | Amosse Edouard, Elena Cabrio, Sara Tonelli, Nhan Le-Thanh |
| Abstract | This demo paper presents a system that builds a timeline with salient actions of a soccer game, based on the tweets posted by users. It combines information provided by external knowledge bases to enrich the content of tweets and applies graph theory to model relations between actions (e.g. goals, penalties) and participants of a game (e.g. players, teams). In the demo, a web application displays in nearly real-time the actions detected from tweets posted by users for a given match of Euro 2016. Our tools are freely available at \url{https://bitbucket.org/eamosse/event_tracking}. |
| Tasks | Named Entity Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1029/ |
| https://doi.org/10.26615/978-954-452-049-6_029 | |
| PWC | https://paperswithcode.com/paper/building-timelines-of-soccer-matches-from |
| Repo | |
| Framework | |
Bayesian Dyadic Trees and Histograms for Regression
| Title | Bayesian Dyadic Trees and Histograms for Regression |
| Authors | Stéphanie Van Der Pas, Veronika Rockova |
| Abstract | Many machine learning tools for regression are based on recursive partitioning of the covariate space into smaller regions, where the regression function can be estimated locally. Among these, regression trees and their ensembles have demonstrated impressive empirical performance. In this work, we shed light on the machinery behind Bayesian variants of these methods. In particular, we study Bayesian regression histograms, such as Bayesian dyadic trees, in the simple regression case with just one predictor. We focus on the reconstruction of regression surfaces that are piecewise constant, where the number of jumps is unknown. We show that with suitably designed priors, posterior distributions concentrate around the true step regression function at a near-minimax rate. These results {\sl do not} require the knowledge of the true number of steps, nor the width of the true partitioning cells. Thus, Bayesian dyadic regression trees are fully adaptive and can recover the true piecewise regression function nearly as well as if we knew the exact number and location of jumps. Our results constitute the first step towards understanding why Bayesian trees and their ensembles have worked so well in practice. As an aside, we discuss prior distributions on balanced interval partitions and how they relate to an old problem in geometric probability. Namely, we relate the probability of covering the circumference of a circle with random arcs whose endpoints are confined to a grid, a new variant of the original problem. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6804-bayesian-dyadic-trees-and-histograms-for-regression |
| http://papers.nips.cc/paper/6804-bayesian-dyadic-trees-and-histograms-for-regression.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-dyadic-trees-and-histograms-for |
| Repo | |
| Framework | |
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications
| Title | Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications |
| Authors | Evgeny Levinkov, Jonas Uhrig, Siyu Tang, Mohamed Omran, Eldar Insafutdinov, Alexander Kirillov, Carsten Rother, Thomas Brox, Bernt Schiele, Bjoern Andres |
| Abstract | We state a combinatorial optimization problem whose feasible solutions define both a decomposition and a node labeling of a given graph. This problem offers a common mathematical abstraction of seemingly unrelated computer vision tasks, including instance-separating semantic segmentation, articulated human body pose estimation and multiple object tracking. Conceptually, it generalizes the unconstrained integer quadratic program and the minimum cost lifted multicut problem, both of which are NP-hard. In order to find feasible solutions efficiently, we define two local search algorithms that converge monotonously to a local optimum, offering a feasible solution at any time. To demonstrate the effectiveness of these algorithms in tackling computer vision tasks, we apply them to instances of the problem that we construct from published data, using published algorithms. We report state-of-the-art application-specific accuracy in the three above-mentioned applications. |
| Tasks | Combinatorial Optimization, Multiple Object Tracking, Object Tracking, Pose Estimation, Semantic Segmentation |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Levinkov_Joint_Graph_Decomposition_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Levinkov_Joint_Graph_Decomposition_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/joint-graph-decomposition-node-labeling |
| Repo | |
| Framework | |
Zero-Inflated Exponential Family Embeddings
| Title | Zero-Inflated Exponential Family Embeddings |
| Authors | Li-Ping Liu, David M. Blei |
| Abstract | Word embeddings are a widely-used tool to analyze language, and exponential family embeddings (Rudolph et al., 2016) generalize the technique to other types of data. One challenge to fitting embedding methods is sparse data, such as a document/term matrix that contains many zeros. To address this issue, practitioners typically downweight or subsample the zeros, thus focusing learning on the non-zero entries. In this paper, we develop zero-inflated embeddings, a new embedding method that is designed to learn from sparse observations. In a zero-inflated embedding (ZIE), a zero in the data can come from an interaction to other data (i.e., an embedding) or from a separate process by which many observations are equal to zero (i.e. a probability mass at zero). Fitting a ZIE naturally downweights the zeros and dampens their influence on the model. Across many types of data—language, movie ratings, shopping histories, and bird watching logs—we found that zero-inflated embeddings provide improved predictive performance over standard approaches and find better vector representation of items. |
| Tasks | Word Embeddings |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=625 |
| http://proceedings.mlr.press/v70/liu17a/liu17a.pdf | |
| PWC | https://paperswithcode.com/paper/zero-inflated-exponential-family-embeddings |
| Repo | |
| Framework | |
Clustering High Dimensional Dynamic Data Streams
| Title | Clustering High Dimensional Dynamic Data Streams |
| Authors | Vladimir Braverman, Gereon Frahling, Harry Lang, Christian Sohler, Lin F. Yang |
| Abstract | We present data streaming algorithms for the $k$-median problem in high-dimensional dynamic geometric data streams, i.e. streams allowing both insertions and deletions of points from a discrete Euclidean space ${1, 2, \ldots \Delta}^d$. Our algorithms use $k \epsilon^{-2} \mathrm{poly}(d \log \Delta)$ space/time and maintain with high probability a small weighted set of points (a coreset) such that for every set of $k$ centers the cost of the coreset $(1+\epsilon)$-approximates the cost of the streamed point set. We also provide algorithms that guarantee only positive weights in the coreset with additional logarithmic factors in the space and time complexities. We can use this positively-weighted coreset to compute a $(1+\epsilon)$-approximation for the $k$-median problem by any efficient offline $k$-median algorithm. All previous algorithms for computing a $(1+\epsilon)$-approximation for the $k$-median problem over dynamic data streams required space and time exponential in $d$. Our algorithms can be generalized to metric spaces of bounded doubling dimension. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=626 |
| http://proceedings.mlr.press/v70/braverman17a/braverman17a.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-high-dimensional-dynamic-data |
| Repo | |
| Framework | |
Multiple Clustering Views from Multiple Uncertain Experts
| Title | Multiple Clustering Views from Multiple Uncertain Experts |
| Authors | Yale Chang, Junxiang Chen, Michael H. Cho, Peter J. Castaldi, Edwin K. Silverman, Jennifer G. Dy |
| Abstract | Expert input can improve clustering performance. In today’s collaborative environment, the availability of crowdsourced multiple expert input is becoming common. Given multiple experts’ inputs, most existing approaches can only discover one clustering structure. However, data is multi-faced by nature and can be clustered in different ways (also known as views). In an exploratory analysis problem where ground truth is not known, different experts may have diverse views on how to cluster data. In this paper, we address the problem on how to automatically discover multiple ways to cluster data given potentially diverse inputs from multiple uncertain experts. We propose a novel Bayesian probabilistic model that automatically learns the multiple expert views and the clustering structure associated with each view. The benefits of learning the experts’ views include 1) enabling the discovery of multiple diverse clustering structures, and 2) improving the quality of clustering solution in each view by assigning higher weights to experts with higher confidence. In our approach, the expert views, multiple clustering structures and expert confidences are jointly learned via variational inference. Experimental results on synthetic datasets, benchmark datasets and a real-world disease subtyping problem show that our proposed approach outperforms competing baselines, including meta clustering, semi-supervised clustering, semi-crowdsourced clustering and consensus clustering. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=484 |
| http://proceedings.mlr.press/v70/chang17a/chang17a.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-clustering-views-from-multiple |
| Repo | |
| Framework | |
Machine Learning for Rhetorical Figure Detection: More Chiasmus with Less Annotation
| Title | Machine Learning for Rhetorical Figure Detection: More Chiasmus with Less Annotation |
| Authors | Marie Dubremetz, Joakim Nivre |
| Abstract | |
| Tasks | Language Identification |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0205/ |
| https://www.aclweb.org/anthology/W17-0205 | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-rhetorical-figure |
| Repo | |
| Framework | |
Extracting semantic relations via the combination of inferences, schemas and cooccurrences
| Title | Extracting semantic relations via the combination of inferences, schemas and cooccurrences |
| Authors | Mathieu Lafourcade, Nathalie Le Brun |
| Abstract | Extracting semantic relations from texts is a good way to build and supply a knowledge base, an indispensable resource for text analysis. We propose and evaluate the combination of three ways of producing lexical-semantic relations. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1055/ |
| https://doi.org/10.26615/978-954-452-049-6_055 | |
| PWC | https://paperswithcode.com/paper/extracting-semantic-relations-via-the |
| Repo | |
| Framework | |
World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions
| Title | World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions |
| Authors | Teng Long, Emmanuel Bengio, Ryan Lowe, Jackie Chi Kit Cheung, Doina Precup |
| Abstract | Humans interpret texts with respect to some background information, or world knowledge, and we would like to develop automatic reading comprehension systems that can do the same. In this paper, we introduce a task and several models to drive progress towards this goal. In particular, we propose the task of rare entity prediction: given a web document with several entities removed, models are tasked with predicting the correct missing entities conditioned on the document context and the lexical resources. This task is challenging due to the diversity of language styles and the extremely large number of rare entities. We propose two recurrent neural network architectures which make use of external knowledge in the form of entity descriptions. Our experiments show that our hierarchical LSTM model performs significantly better at the rare entity prediction task than those that do not make use of external resources. |
| Tasks | Language Modelling, Reading Comprehension |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1086/ |
| https://www.aclweb.org/anthology/D17-1086 | |
| PWC | https://paperswithcode.com/paper/world-knowledge-for-reading-comprehension |
| Repo | |
| Framework | |
Recurrent Color Constancy
| Title | Recurrent Color Constancy |
| Authors | Yanlin Qian, Ke Chen, Jarno Nikkanen, Joni-Kristian Kamarainen, Jiri Matas |
| Abstract | We introduce a novel formulation of temporal color constancy which considers multiple frames preceding the frame for which illumination is estimated. We propose an end-to-end trainable recurrent color constancy network – the RCC-Net – which exploits convolutional LSTMs and a simulated sequence to learn compositional representations in space and time. We use a standard single frame color constancy benchmark, the SFU Gray Ball Dataset, which can be adapted to a temporal setting. Extensive experiments show that the proposed method consistently outperforms single-frame state-of-the-art methods and their temporal variants. |
| Tasks | Color Constancy |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Qian_Recurrent_Color_Constancy_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Qian_Recurrent_Color_Constancy_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-color-constancy |
| Repo | |
| Framework | |
Sentiment Analysis: An Empirical Comparative Study of Various Machine Learning Approaches
| Title | Sentiment Analysis: An Empirical Comparative Study of Various Machine Learning Approaches |
| Authors | Swapnil Jain, Shrikant Malviya, Rohit Mishra, Uma Shanker Tiwary |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7515/ |
| https://www.aclweb.org/anthology/W17-7515 | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-an-empirical-comparative |
| Repo | |
| Framework | |
Bilingual Word Embeddings for Bilingual Terminology Extraction from Specialized Comparable Corpora
| Title | Bilingual Word Embeddings for Bilingual Terminology Extraction from Specialized Comparable Corpora |
| Authors | Amir Hazem, Emmanuel Morin |
| Abstract | Bilingual lexicon extraction from comparable corpora is constrained by the small amount of available data when dealing with specialized domains. This aspect penalizes the performance of distributional-based approaches, which is closely related to the reliability of word{'}s cooccurrence counts extracted from comparable corpora. A solution to avoid this limitation is to associate external resources with the comparable corpus. Since bilingual word embeddings have recently shown efficient models for learning bilingual distributed representation of words, we explore different word embedding models and show how a general-domain comparable corpus can enrich a specialized comparable corpus via neural networks |
| Tasks | Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1069/ |
| https://www.aclweb.org/anthology/I17-1069 | |
| PWC | https://paperswithcode.com/paper/bilingual-word-embeddings-for-bilingual |
| Repo | |
| Framework | |
Derivation of Document Vectors from Adaptation of LSTM Language Model
| Title | Derivation of Document Vectors from Adaptation of LSTM Language Model |
| Authors | Wei Li, Brian Mak |
| Abstract | In many natural language processing (NLP) tasks, a document is commonly modeled as a bag of words using the term frequency-inverse document frequency (TF-IDF) vector. One major shortcoming of the frequency-based TF-IDF feature vector is that it ignores word orders that carry syntactic and semantic relationships among the words in a document. This paper proposes a novel distributed vector representation of a document, which will be labeled as DV-LSTM, and is derived from the result of adapting a long short-term memory recurrent neural network language model by the document. DV-LSTM is expected to capture some high-level sequential information in the document, which other current document representations fail to do. It was evaluated in document genre classification in the Brown Corpus and the BNC Baby Corpus. The results show that DV-LSTM significantly outperforms TF-IDF vector and paragraph vector (PV-DM) in most cases, and their combinations may further improve the classification performance. |
| Tasks | Language Modelling |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2073/ |
| https://www.aclweb.org/anthology/E17-2073 | |
| PWC | https://paperswithcode.com/paper/derivation-of-document-vectors-from |
| Repo | |
| Framework | |
Using Word Embedding for Cross-Language Plagiarism Detection
| Title | Using Word Embedding for Cross-Language Plagiarism Detection |
| Authors | J{'e}r{'e}my Ferrero, Laurent Besacier, Didier Schwab, Fr{'e}d{'e}ric Agn{`e}s |
| Abstract | This paper proposes to use distributed representation of words (word embeddings) in cross-language textual similarity detection. The main contributions of this paper are the following: (a) we introduce new cross-language similarity detection methods based on distributed representation of words; (b) we combine the different methods proposed to verify their complementarity and finally obtain an overall F1 score of 89.15{%} for English-French similarity detection at chunk level (88.5{%} at sentence level) on a very challenging corpus. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2066/ |
| https://www.aclweb.org/anthology/E17-2066 | |
| PWC | https://paperswithcode.com/paper/using-word-embedding-for-cross-language |
| Repo | |
| Framework | |
An Empirical Study of Language Relatedness for Transfer Learning in Neural Machine Translation
| Title | An Empirical Study of Language Relatedness for Transfer Learning in Neural Machine Translation |
| Authors | Raj Dabre, Tetsuji Nakagawa, Hideto Kazawa |
| Abstract | |
| Tasks | Machine Translation, Transfer Learning |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1038/ |
| https://www.aclweb.org/anthology/Y17-1038 | |
| PWC | https://paperswithcode.com/paper/an-empirical-study-of-language-relatedness |
| Repo | |
| Framework | |
