Paper Group NAWR 1
Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations. Learning Deep Parsimonious Representations. UNIMELB at SemEval-2016 Tasks 4A and 4B: An Ensemble of Neural Networks and a Word2Vec Based Model for Sentiment Classification. Table Filling Multi-Task Recurrent Neural Network for Joint Entity and Relation Extraction. LLSF - Learning …
Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations
| Title | Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations |
| Authors | Kirthevasan Kandasamy, Gautam Dasarathy, Junier B. Oliva, Jeff Schneider, Barnabas Poczos |
| Abstract | In many scientific and engineering applications, we are tasked with the optimisation of an expensive to evaluate black box function $\func$. Traditional methods for this problem assume just the availability of this single function. However, in many cases, cheap approximations to $\func$ may be obtainable. For example, the expensive real world behaviour of a robot can be approximated by a cheap computer simulation. We can use these approximations to eliminate low function value regions cheaply and use the expensive evaluations of $\func$ in a small but promising region and speedily identify the optimum. We formalise this task as a \emph{multi-fidelity} bandit problem where the target function and its approximations are sampled from a Gaussian process. We develop \mfgpucb, a novel method based on upper confidence bound techniques. In our theoretical analysis we demonstrate that it exhibits precisely the above behaviour, and achieves better regret than strategies which ignore multi-fidelity information. \mfgpucbs outperforms such naive strategies and other multi-fidelity methods on several synthetic and real experiments. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6118-gaussian-process-bandit-optimisation-with-multi-fidelity-evaluations |
| http://papers.nips.cc/paper/6118-gaussian-process-bandit-optimisation-with-multi-fidelity-evaluations.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-process-bandit-optimisation-with |
| Repo | https://github.com/kirthevasank/mf-gp-ucb |
| Framework | none |
Learning Deep Parsimonious Representations
| Title | Learning Deep Parsimonious Representations |
| Authors | Renjie Liao, Alex Schwing, Richard Zemel, Raquel Urtasun |
| Abstract | In this paper we aim at facilitating generalization for deep networks while supporting interpretability of the learned representations. Towards this goal, we propose a clustering based regularization that encourages parsimonious representations. Our k-means style objective is easy to optimize and flexible supporting various forms of clustering, including sample and spatial clustering as well as co-clustering. We demonstrate the effectiveness of our approach on the tasks of unsupervised learning, classification, fine grained categorization and zero-shot learning. |
| Tasks | Few-Shot Image Classification, Zero-Shot Learning |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6263-learning-deep-parsimonious-representations |
| http://papers.nips.cc/paper/6263-learning-deep-parsimonious-representations.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deep-parsimonious-representations |
| Repo | https://github.com/lrjconan/deep_parsimonious |
| Framework | tf |
UNIMELB at SemEval-2016 Tasks 4A and 4B: An Ensemble of Neural Networks and a Word2Vec Based Model for Sentiment Classification
| Title | UNIMELB at SemEval-2016 Tasks 4A and 4B: An Ensemble of Neural Networks and a Word2Vec Based Model for Sentiment Classification |
| Authors | Steven Xu, HuiZhi Liang, Timothy Baldwin |
| Abstract | |
| Tasks | Document Classification, Language Modelling, Reading Comprehension, Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1027/ |
| https://www.aclweb.org/anthology/S16-1027 | |
| PWC | https://paperswithcode.com/paper/unimelb-at-semeval-2016-tasks-4a-and-4b-an |
| Repo | https://github.com/liufly/narrative-modeling |
| Framework | tf |
Table Filling Multi-Task Recurrent Neural Network for Joint Entity and Relation Extraction
| Title | Table Filling Multi-Task Recurrent Neural Network for Joint Entity and Relation Extraction |
| Authors | Pankaj Gupta, Hinrich Sch{"u}tze, Bernt Andrassy |
| Abstract | This paper proposes a novel context-aware joint entity and word-level relation extraction approach through semantic composition of words, introducing a Table Filling Multi-Task Recurrent Neural Network (TF-MTRNN) model that reduces the entity recognition and relation classification tasks to a table-filling problem and models their interdependencies. The proposed neural network architecture is capable of modeling multiple relation instances without knowing the corresponding relation arguments in a sentence. The experimental results show that a simple approach of piggybacking candidate entities to model the label dependencies from relations to entities improves performance. We present state-of-the-art results with improvements of 2.0{%} and 2.7{%} for entity recognition and relation classification, respectively on CoNLL04 dataset. |
| Tasks | Entity Extraction, Joint Entity and Relation Extraction, Relation Classification, Relation Extraction, Semantic Composition, Structured Prediction |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1239/ |
| https://www.aclweb.org/anthology/C16-1239 | |
| PWC | https://paperswithcode.com/paper/table-filling-multi-task-recurrent-neural |
| Repo | https://github.com/pgcool/TF-MTRNN |
| Framework | tf |
LLSF - Learning Label Specific Features for Multi-Label Classifcation
| Title | LLSF - Learning Label Specific Features for Multi-Label Classifcation |
| Authors | Jun Huang ; Guorong Li ; Qingming Huang ; Xindong Wu |
| Abstract | Binary Relevance is a well-known framework for multi-label classification, which considers each class label as a binary classification problem. Many existing multi-label algorithms are constructed within this framework, and utilize identical data representation in the discrimination of all the class labels. In multi-label classification, however, each class label might be determined by some specific characteristics of its own. In this paper, we seek to learn label-specific data representation for each class label, which is composed of label-specific features. Our proposed method LLSF can not only be utilized for multi-label classification directly, but also be applied as a feature selection method for multi-label learning and a general strategy to improve multi-label classification algorithms comprising a number of binary classifiers. Inspired by the research works on modeling high-order label correlations, we further extend LLSF to learn class-Dependent Labels in a sparse stackingway, denoted as LLSF-DL. It incorporates both second-order- and high-order label correlations. A comparative study with the state-of-the-art approaches manifests the effectiveness and efficiency of our proposed methods. |
| Tasks | Feature Selection, Multi-Label Classification, Multi-Label Learning |
| Published | 2016-01-07 |
| URL | https://ieeexplore.ieee.org/document/7373322 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7373322 | |
| PWC | https://paperswithcode.com/paper/llsf-learning-label-specific-features-for |
| Repo | https://github.com/Prady029/LLSF-Learning-Label-Specific-Features-for-Multi-Label-Classifcation |
| Framework | none |
SeeDev Binary Event Extraction using SVMs and a Rich Feature Set
| Title | SeeDev Binary Event Extraction using SVMs and a Rich Feature Set |
| Authors | Nagesh C. Panyam, Gitansh Khirbat, Karin Verspoor, Trevor Cohn, Kotagiri Ramamohanarao |
| Abstract | |
| Tasks | Relation Extraction |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-3010/ |
| https://www.aclweb.org/anthology/W16-3010 | |
| PWC | https://paperswithcode.com/paper/seedev-binary-event-extraction-using-svms-and |
| Repo | https://github.com/unimelbbionlp/BioNLPST2016 |
| Framework | none |
Standard Test Collection for English-Persian Cross-Lingual Word Sense Disambiguation
| Title | Standard Test Collection for English-Persian Cross-Lingual Word Sense Disambiguation |
| Authors | Navid Rekabsaz, Serwah Sabetghadam, Mihai Lupu, Linda Andersson, Allan Hanbury |
| Abstract | In this paper, we address the shortage of evaluation benchmarks on Persian (Farsi) language by creating and making available a new benchmark for English to Persian Cross Lingual Word Sense Disambiguation (CL-WSD). In creating the benchmark, we follow the format of the SemEval 2013 CL-WSD task, such that the introduced tools of the task can also be applied on the benchmark. In fact, the new benchmark extends the SemEval-2013 CL-WSD task to Persian language. |
| Tasks | Word Sense Disambiguation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1659/ |
| https://www.aclweb.org/anthology/L16-1659 | |
| PWC | https://paperswithcode.com/paper/standard-test-collection-for-english-persian |
| Repo | https://github.com/neds/wsd_persian |
| Framework | none |
More is not always better: balancing sense distributions for all-words Word Sense Disambiguation
| Title | More is not always better: balancing sense distributions for all-words Word Sense Disambiguation |
| Authors | Marten Postma, Ruben Izquierdo Bevia, Piek Vossen |
| Abstract | Current Word Sense Disambiguation systems show an extremely poor performance on low frequent senses, which is mainly caused by the difference in sense distributions between training and test data. The main focus in tackling this problem has been on acquiring more data or selecting a single predominant sense and not necessarily on the meta properties of the data itself. We demonstrate that these properties, such as the volume, provenance, and balancing, play an important role with respect to system performance. In this paper, we describe a set of experiments to analyze these meta properties in the framework of a state-of-the-art WSD system when evaluated on the SemEval-2013 English all-words dataset. We show that volume and provenance are indeed important, but that approximating the perfect balancing of the selected training data leads to an improvement of 21 points and exceeds state-of-the-art systems by 14 points while using only simple features. We therefore conclude that unsupervised acquisition of training data should be guided by strategies aimed at matching meta properties. |
| Tasks | Word Sense Disambiguation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1330/ |
| https://www.aclweb.org/anthology/C16-1330 | |
| PWC | https://paperswithcode.com/paper/more-is-not-always-better-balancing-sense |
| Repo | https://github.com/cltl/MoreIsNotAlwaysBetter |
| Framework | none |
GAKE: Graph Aware Knowledge Embedding
| Title | GAKE: Graph Aware Knowledge Embedding |
| Authors | Jun Feng, Minlie Huang, Yang Yang, Xiaoyan Zhu |
| Abstract | Knowledge embedding, which projects triples in a given knowledge base to d-dimensional vectors, has attracted considerable research efforts recently. Most existing approaches treat the given knowledge base as a set of triplets, each of whose representation is then learned separately. However, as a fact, triples are connected and depend on each other. In this paper, we propose a graph aware knowledge embedding method (GAKE), which formulates knowledge base as a directed graph, and learns representations for any vertices or edges by leveraging the graph{'}s structural information. We introduce three types of graph context for embedding: neighbor context, path context, and edge context, each reflects properties of knowledge from different perspectives. We also design an attention mechanism to learn representative power of different vertices or edges. To validate our method, we conduct several experiments on two tasks. Experimental results suggest that our method outperforms several state-of-art knowledge embedding models. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1062/ |
| https://www.aclweb.org/anthology/C16-1062 | |
| PWC | https://paperswithcode.com/paper/gake-graph-aware-knowledge-embedding |
| Repo | https://github.com/JuneFeng/GAKE |
| Framework | none |
GenSVM: A Generalized Multiclass Support Vector Machine
| Title | GenSVM: A Generalized Multiclass Support Vector Machine |
| Authors | Gerrit J. J. van den Burg, Patrick J. F. Groenen |
| Abstract | Traditional extensions of the binary support vector machine (SVM) to multiclass problems are either heuristics or require solving a large dual optimization problem. Here, a generalized multiclass SVM is proposed called GenSVM. In this method classification boundaries for a K-class problem are constructed in a (K−1)-dimensional space using a simplex encoding. Additionally, several different weightings of the misclassification errors are incorporated in the loss function, such that it generalizes three existing multiclass SVMs through a single optimization problem. An iterative majorization algorithm is derived that solves the optimization problem without the need of a dual formulation. This algorithm has the advantage that it can use warm starts during cross validation and during a grid search, which significantly speeds up the training phase. Rigorous numerical experiments compare linear GenSVM with seven existing multiclass SVMs on both small and large data sets. These comparisons show that the proposed method is competitive with existing methods in both predictive accuracy and training time, and that it significantly outperforms several existing methods on these criteria. |
| Tasks | |
| Published | 2016-12-30 |
| URL | http://jmlr.org/papers/v17/14-526.html |
| http://jmlr.org/papers/volume17/14-526/14-526.pdf | |
| PWC | https://paperswithcode.com/paper/gensvm-a-generalized-multiclass-support |
| Repo | https://github.com/GjjvdBurg/GenSVM |
| Framework | none |
Recognizing Emotions From Abstract Paintings Using Non-Linear Matrix Completion
| Title | Recognizing Emotions From Abstract Paintings Using Non-Linear Matrix Completion |
| Authors | Xavier Alameda-Pineda, Elisa Ricci, Yan Yan, Nicu Sebe |
| Abstract | Advanced computer vision and machine learning techniques tried to automatically categorize the emotions elicited by abstract paintings with limited success. Since the annotation of the emotional content is highly resource-consuming, datasets of abstract paintings are either constrained in size or partially annotated. Consequently, it is natural to address the targeted task within a transductive framework. Intuitively, the use of multi-label classification techniques is desirable so to synergically exploit the relations between multiple latent variables, such as emotional content, technique, author, etc. A very popular approach for transductive multi-label recognition under linear classification settings is matrix completion. In this study we introduce non-linear matrix completion (NLMC), thus extending classical linear matrix completion techniques to the non-linear case. Together with the theory grounding the model, we propose an efficient optimization solver. As shown by our extensive experimental validation on two publicly available datasets, NLMC outperforms state-of-the-art methods when recognizing emotions from abstract paintings. |
| Tasks | Matrix Completion, Multi-Label Classification |
| Published | 2016-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2016/html/Alameda-Pineda_Recognizing_Emotions_From_CVPR_2016_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2016/papers/Alameda-Pineda_Recognizing_Emotions_From_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/recognizing-emotions-from-abstract-paintings |
| Repo | https://github.com/xavirema/nlmc |
| Framework | none |
Natural Image Stitching with the Global Similarity Prior
| Title | Natural Image Stitching with the Global Similarity Prior |
| Authors | Yu-Sheng Chen; Yung-Yu Chuang |
| Abstract | This paper proposes a method for stitching multiple images together so that the stitched image looks as natural as possible. Our method adopts the local warp model and guides the warping of each image with a grid mesh. An objective function is designed for specifying the desired characteristics of the warps. In addition to good alignment and minimal local distortion, we add a global similarity prior in the objective function. This prior constrains the warp of each image so that it resembles a similarity transformation as a whole. The selection of the similarity transformation is crucial to the naturalness of the results. We propose methods for selecting the proper scale and rotation for each image. The warps of all images are solved together for minimizing the distortion globally. A comprehensive evaluation shows that the proposed method consistently outperforms several state-of-the-art methods, including AutoStitch, APAP, SPHP and ANNAP. |
| Tasks | Image Stitching |
| Published | 2016-10-01 |
| URL | https://www.cmlab.csie.ntu.edu.tw/project/stitching-wGSP/ |
| https://www.cmlab.csie.ntu.edu.tw/project/stitching-wGSP/ECCV-2016-NISwGSP.pdf | |
| PWC | https://paperswithcode.com/paper/natural-image-stitching-with-the-global |
| Repo | https://github.com/nothinglo/NISwGSP |
| Framework | none |
Bridging the gap between extractive and abstractive summaries: Creation and evaluation of coherent extracts from heterogeneous sources
| Title | Bridging the gap between extractive and abstractive summaries: Creation and evaluation of coherent extracts from heterogeneous sources |
| Authors | Darina Benikova, Margot Mieskes, Christian M. Meyer, Iryna Gurevych |
| Abstract | Coherent extracts are a novel type of summary combining the advantages of manually created abstractive summaries, which are fluent but difficult to evaluate, and low-quality automatically created extractive summaries, which lack coherence and structure. We use a corpus of heterogeneous documents to address the issue that information seekers usually face {–} a variety of different types of information sources. We directly extract information from these, but minimally redact and meaningfully order it to form a coherent text. Our qualitative and quantitative evaluations show that quantitative results are not sufficient to judge the quality of a summary and that other quality criteria, such as coherence, should also be taken into account. We find that our manually created corpus is of high quality and that it has the potential to bridge the gap between reference corpora of abstracts and automatic methods producing extracts. Our corpus is available to the research community for further development. |
| Tasks | Document Summarization, Multi-Document Summarization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1099/ |
| https://www.aclweb.org/anthology/C16-1099 | |
| PWC | https://paperswithcode.com/paper/bridging-the-gap-between-extractive-and |
| Repo | https://github.com/AIPHES/DBS |
| Framework | none |
General Tensor Spectral Co-clustering for Higher-Order Data
| Title | General Tensor Spectral Co-clustering for Higher-Order Data |
| Authors | Tao Wu, Austin R. Benson, David F. Gleich |
| Abstract | Spectral clustering and co-clustering are well-known techniques in data analysis, and recent work has extended spectral clustering to square, symmetric tensors and hypermatrices derived from a network. We develop a new tensor spectral co-clustering method that simultaneously clusters the rows, columns, and slices of a nonnegative three-mode tensor and generalizes to tensors with any number of modes. The algorithm is based on a new random walk model which we call the super-spacey random surfer. We show that our method out-performs state-of-the-art co-clustering methods on several synthetic datasets with ground truth clusters and then use the algorithm to analyze several real-world datasets. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6376-general-tensor-spectral-co-clustering-for-higher-order-data |
| http://papers.nips.cc/paper/6376-general-tensor-spectral-co-clustering-for-higher-order-data.pdf | |
| PWC | https://paperswithcode.com/paper/general-tensor-spectral-co-clustering-for |
| Repo | https://github.com/wutao27/GtensorSC |
| Framework | none |
An urn model for majority voting in classification ensembles
| Title | An urn model for majority voting in classification ensembles |
| Authors | Victor Soto, Alberto Suárez, Gonzalo Martinez-Muñoz |
| Abstract | In this work we analyze the class prediction of parallel randomized ensembles by majority voting as an urn model. For a given test instance, the ensemble can be viewed as an urn of marbles of different colors. A marble represents an individual classifier. Its color represents the class label prediction of the corresponding classifier. The sequential querying of classifiers in the ensemble can be seen as draws without replacement from the urn. An analysis of this classical urn model based on the hypergeometric distribution makes it possible to estimate the confidence on the outcome of majority voting when only a fraction of the individual predictions is known. These estimates can be used to speed up the prediction by the ensemble. Specifically, the aggregation of votes can be halted when the confidence in the final prediction is sufficiently high. If one assumes a uniform prior for the distribution of possible votes the analysis is shown to be equivalent to a previous one based on Dirichlet distributions. The advantage of the current approach is that prior knowledge on the possible vote outcomes can be readily incorporated in a Bayesian framework. We show how incorporating this type of problem-specific knowledge into the statistical analysis of majority voting leads to faster classification by the ensemble and allows us to estimate the expected average speed-up beforehand. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6120-an-urn-model-for-majority-voting-in-classification-ensembles |
| http://papers.nips.cc/paper/6120-an-urn-model-for-majority-voting-in-classification-ensembles.pdf | |
| PWC | https://paperswithcode.com/paper/an-urn-model-for-majority-voting-in |
| Repo | https://github.com/vsoto/majority-ibp-prior |
| Framework | none |
