Paper Group NAWR 12
PRUNE: Preserving Proximity and Global Ranking for Network Embedding. Evaluating the morphological compositionality of polarity. Detection and Localization of Drosophila Egg Chambers in Microscopy Images.. RoBO: A Flexible and Robust Bayesian Optimization Framework in Python. Deanonymization in the Bitcoin P2P Network. Tilde’s Machine Translation S …
PRUNE: Preserving Proximity and Global Ranking for Network Embedding
| Title | PRUNE: Preserving Proximity and Global Ranking for Network Embedding |
| Authors | Yi-An Lai, Chin-Chi Hsu, Wen Hao Chen, Mi-Yen Yeh, Shou-De Lin |
| Abstract | We investigate an unsupervised generative approach for network embedding. A multi-task Siamese neural network structure is formulated to connect embedding vectors and our objective to preserve the global node ranking and local proximity of nodes. We provide deeper analysis to connect the proposed proximity objective to link prediction and community detection in the network. We show our model can satisfy the following design properties: scalability, asymmetry, unity and simplicity. Experiment results not only verify the above design properties but also demonstrate the superior performance in learning-to-rank, classification, regression, and link prediction tasks. |
| Tasks | Community Detection, Learning-To-Rank, Link Prediction, Network Embedding |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7110-prune-preserving-proximity-and-global-ranking-for-network-embedding |
| http://papers.nips.cc/paper/7110-prune-preserving-proximity-and-global-ranking-for-network-embedding.pdf | |
| PWC | https://paperswithcode.com/paper/prune-preserving-proximity-and-global-ranking |
| Repo | https://github.com/ntumslab/PRUNE |
| Framework | tf |
Evaluating the morphological compositionality of polarity
| Title | Evaluating the morphological compositionality of polarity |
| Authors | Josef Ruppenhofer, Petra Steiner, Michael Wiegand |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://aclanthology.coli.uni-saarland.de/papers/R17-1081/r17-1081 |
| https://doi.org/10.26615/978-954-452-049-6_081 | |
| PWC | https://paperswithcode.com/paper/evaluating-the-morphological-compositionality |
| Repo | https://github.com/josefkr/morphcomp |
| Framework | none |
Detection and Localization of Drosophila Egg Chambers in Microscopy Images.
| Title | Detection and Localization of Drosophila Egg Chambers in Microscopy Images. |
| Authors | Jiří Borovec, Jan Kybic, Rodrigo Nava |
| Abstract | Drosophila melanogaster is a well-known model organism that can be used for studying oogenesis (egg chamber development) including gene expression patterns. Standard analysis methods require manual segmentation of individual egg chambers, which is a difficult and time-consuming task. We present an image processing pipeline to detect and localize Drosophila egg chambers that consists of the following steps: (i) superpixel-based image segmentation into relevant tissue classes; (ii) detection of egg center candidates using label histograms and ray features; (iii) clustering of center candidates and; (iv) area-based maximum likelihood ellipse model fitting. Our proposal is able to detect 96% of human-expert annotated egg chambers at relevant developmental stages with less than 1% false-positive rate, which is adequate for the further analysis. |
| Tasks | Semantic Segmentation |
| Published | 2017-09-07 |
| URL | https://link.springer.com/chapter/10.1007%2F978-3-319-67389-9_3 |
| https://link.springer.com/chapter/10.1007%2F978-3-319-67389-9_3 | |
| PWC | https://paperswithcode.com/paper/detection-and-localization-of-drosophila-egg |
| Repo | https://github.com/Borda/pyImSegm |
| Framework | none |
RoBO: A Flexible and Robust Bayesian Optimization Framework in Python
| Title | RoBO: A Flexible and Robust Bayesian Optimization Framework in Python |
| Authors | Aaron Klein, Stefan Falkner, Numair Mansur, Frank Hutter |
| Abstract | Bayesian optimization is a powerful approach for the global derivative-free optimization of non-convex expensive functions. Even though there is a rich literature on Bayesian optimization, the source code of advanced methods is rarely available, making it difficult for practitioners to use them and for researchers to compare to and extend them. The BSD-licensed python package ROBO, released with this paper, tackles these problems by facilitating both ease of use and extensibility. Beyond the standard methods in Bayesian optimization, RoBO offers (to the best of our knowledge) the only available implementations of Bayesian optimization with Bayesian neural networks, multi-task optimization, and fast Bayesian hyperparameter optimization on large datasets (Fabolas). |
| Tasks | Hyperparameter Optimization |
| Published | 2017-01-01 |
| URL | https://bayesopt.github.io/papers/2017/22.pdf |
| https://bayesopt.github.io/papers/2017/22.pdf | |
| PWC | https://paperswithcode.com/paper/robo-a-flexible-and-robust-bayesian |
| Repo | https://github.com/automl/RoBO |
| Framework | none |
Deanonymization in the Bitcoin P2P Network
| Title | Deanonymization in the Bitcoin P2P Network |
| Authors | Giulia Fanti, Pramod Viswanath |
| Abstract | Recent attacks on Bitcoin’s peer-to-peer (P2P) network demonstrated that its transaction-flooding protocols, which are used to ensure network consistency, may enable user deanonymization—the linkage of a user’s IP address with her pseudonym in the Bitcoin network. In 2015, the Bitcoin community responded to these attacks by changing the network’s flooding mechanism to a different protocol, known as diffusion. However, it is unclear if diffusion actually improves the system’s anonymity. In this paper, we model the Bitcoin networking stack and analyze its anonymity properties, both pre- and post-2015. The core problem is one of epidemic source inference over graphs, where the observational model and spreading mechanisms are informed by Bitcoin’s implementation; notably, these models have not been studied in the epidemic source detection literature before. We identify and analyze near-optimal source estimators. This analysis suggests that Bitcoin’s networking protocols (both pre- and post-2015) offer poor anonymity properties on networks with a regular-tree topology. We confirm this claim in simulation on a 2015 snapshot of the real Bitcoin P2P network topology. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6735-deanonymization-in-the-bitcoin-p2p-network |
| http://papers.nips.cc/paper/6735-deanonymization-in-the-bitcoin-p2p-network.pdf | |
| PWC | https://paperswithcode.com/paper/deanonymization-in-the-bitcoin-p2p-network |
| Repo | https://github.com/gfanti/bitcoin-trickle-diffusion |
| Framework | none |
Tilde’s Machine Translation Systems for WMT 2017
| Title | Tilde’s Machine Translation Systems for WMT 2017 |
| Authors | M{=a}rcis Pinnis, Rihards Kri{\v{s}}lauks, Toms Miks, Daiga Deksne, Valters {\v{S}}ics |
| Abstract | |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4737/ |
| https://www.aclweb.org/anthology/W17-4737 | |
| PWC | https://paperswithcode.com/paper/tildes-machine-translation-systems-for-wmt-1 |
| Repo | https://github.com/tilde-nlp/nematus |
| Framework | none |
Systematically Adapting Machine Translation for Grammatical Error Correction
| Title | Systematically Adapting Machine Translation for Grammatical Error Correction |
| Authors | Courtney Napoles, Chris Callison-Burch |
| Abstract | n this work we adapt machine translation (MT) to grammatical error correction, identifying how components of the statistical MT pipeline can be modified for this task and analyzing how each modification impacts system performance. We evaluate the contribution of each of these components with standard evaluation metrics and automatically characterize the morphological and lexical transformations made in system output. Our model rivals the current state of the art using a fraction of the training data. |
| Tasks | Grammatical Error Correction, Machine Translation, Spelling Correction |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5039/ |
| https://www.aclweb.org/anthology/W17-5039 | |
| PWC | https://paperswithcode.com/paper/systematically-adapting-machine-translation |
| Repo | https://github.com/cnap/smt-for-gec |
| Framework | none |
GPU Kernels for Block-Sparse Weights
| Title | GPU Kernels for Block-Sparse Weights |
| Authors | Scott Gray, Alec Radford and Diederik P. Kingma |
| Abstract | We’re releasing highly optimized GPU kernels for an underexplored class of neural network architectures: networks with block-sparse weights. The kernels allow for efficient evaluation and differentiation of linear layers, including convolutional layers, with flexibly configurable block-sparsity patterns in the weight matrix. We find that depending on the sparsity, these kernels can run orders of magnitude faster than the best available alternatives such as cuBLAS. Using the kernels we improve upon the state-of-the-art in text sentiment analysis and generative modeling of text and images. By releasing our kernels in the open we aim to spur further advancement in model and algorithm design. |
| Tasks | Sentiment Analysis |
| Published | 2017-12-01 |
| URL | https://blog.openai.com/block-sparse-gpu-kernels/ |
| https://s3-us-west-2.amazonaws.com/openai-assets/blocksparse/blocksparsepaper.pdf | |
| PWC | https://paperswithcode.com/paper/gpu-kernels-for-block-sparse-weights |
| Repo | https://github.com/openai/blocksparse |
| Framework | tf |
Centered Weight Normalization in Accelerating Training of Deep Neural Networks
| Title | Centered Weight Normalization in Accelerating Training of Deep Neural Networks |
| Authors | Lei Huang, Xianglong Liu, Yang Liu, Bo Lang, Dacheng Tao |
| Abstract | Training deep neural networks is difficult for the pathological curvature problem. Re-parameterization is an effective way to relieve the problem by learning the curvature approximately or constraining the solutions of weights with good properties for optimization. This paper proposes to re-parameterize the input weight of each neuron in deep neural networks by normalizing it with zero-mean and unit-norm, followed by a learnable scalar parameter to adjust the norm of the weight. This technique effectively stabilizes the distribution implicitly. Besides, it improves the conditioning of the optimization problem and thus accelerates the training of deep neural networks. It can be wrapped as a linear module in practice and plugged in any architecture to replace the standard linear module. We highlight the benefits of our method on both multi-layer perceptrons and convolutional neural networks, and demonstrate its scalability and efficiency on SVHN, CIFAR-10, CIFAR-100 and ImageNet datasets. |
| Tasks | |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Huang_Centered_Weight_Normalization_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Huang_Centered_Weight_Normalization_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/centered-weight-normalization-in-accelerating |
| Repo | https://github.com/huangleiBuaa/CenteredWN |
| Framework | torch |
When does a compliment become sexist? Analysis and classification of ambivalent sexism using twitter data
| Title | When does a compliment become sexist? Analysis and classification of ambivalent sexism using twitter data |
| Authors | Akshita Jha, Radhika Mamidi |
| Abstract | Sexism is prevalent in today{'}s society, both offline and online, and poses a credible threat to social equality with respect to gender. According to ambivalent sexism theory (Glick and Fiske, 1996), it comes in two forms: Hostile and Benevolent. While hostile sexism is characterized by an explicitly negative attitude, benevolent sexism is more subtle. Previous works on computationally detecting sexism present online are restricted to identifying the hostile form. Our objective is to investigate the less pronounced form of sexism demonstrated online. We achieve this by creating and analyzing a dataset of tweets that exhibit benevolent sexism. By using Support Vector Machines (SVM), sequence-to-sequence models and FastText classifier, we classify tweets into {}Hostile{'}, {}Benevolent{'} or {`}Others{'} class depending on the kind of sexism they exhibit. We have been able to achieve an F1-score of 87.22{%} using FastText classifier. Our work helps analyze and understand the much prevalent ambivalent sexism in social media. | |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2902/ |
| https://www.aclweb.org/anthology/W17-2902 | |
| PWC | https://paperswithcode.com/paper/when-does-a-compliment-become-sexist-analysis |
| Repo | https://github.com/AkshitaJha/NLP_CSS_2017 |
| Framework | none |
Adapting Neural Machine Translation with Parallel Synthetic Data
| Title | Adapting Neural Machine Translation with Parallel Synthetic Data |
| Authors | Mara Chinea-R{'\i}os, {'A}lvaro Peris, Francisco Casacuberta |
| Abstract | |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4714/ |
| https://www.aclweb.org/anthology/W17-4714 | |
| PWC | https://paperswithcode.com/paper/adapting-neural-machine-translation-with |
| Repo | https://github.com/lvapeab/nmt-keras |
| Framework | tf |
Using Coreference Links to Improve Spanish-to-English Machine Translation
| Title | Using Coreference Links to Improve Spanish-to-English Machine Translation |
| Authors | Lesly Miculicich Werlen, Andrei Popescu-Belis |
| Abstract | In this paper, we present a proof-of-concept implementation of a coreference-aware decoder for document-level machine translation. We consider that better translations should have coreference links that are closer to those in the source text, and implement this criterion in two ways. First, we define a similarity measure between source and target coreference structures, by projecting the target ones onto the source and reusing existing coreference metrics. Based on this similarity measure, we re-rank the translation hypotheses of a baseline system for each sentence. Alternatively, to address the lack of diversity of mentions in the MT hypotheses, we focus on mention pairs and integrate their coreference scores with MT ones, resulting in post-editing decisions for mentions. The experimental results for Spanish to English MT on the AnCora-ES corpus show that the second approach yields a substantial increase in the accuracy of pronoun translation, with BLEU scores remaining constant. |
| Tasks | Coreference Resolution, Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1505/ |
| https://www.aclweb.org/anthology/W17-1505 | |
| PWC | https://paperswithcode.com/paper/using-coreference-links-to-improve-spanish-to |
| Repo | https://github.com/idiap/APT |
| Framework | none |
Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities
| Title | Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities |
| Authors | Ngoc Quang Luong, Andrei Popescu-Belis, Annette Rios Gonzales, Don Tuggener |
| Abstract | We implement a fully probabilistic model to combine the hypotheses of a Spanish anaphora resolution system with those of a Spanish-English machine translation system. The probabilities over antecedents are converted into probabilities for the features of translated pronouns, and are integrated with phrase-based MT using an additional translation model for pronouns. The system improves the translation of several Spanish personal and possessive pronouns into English, by solving translation divergencies such as {}ella{'} vs. {}she{'}/{}it{'} or {}su{'} vs. {}his{'}/{}her{'}/{}its{'}/{}their{'}. On a test set with 2,286 pronouns, a baseline system correctly translates 1,055 of them, while ours improves this by 41. Moreover, with oracle antecedents, possessives are translated with an accuracy of 83{%}. |
| Tasks | Coreference Resolution, Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2100/ |
| https://www.aclweb.org/anthology/E17-2100 | |
| PWC | https://paperswithcode.com/paper/machine-translation-of-spanish-personal-and |
| Repo | https://github.com/a-rios/CorefMT |
| Framework | none |
Automatic analysis and 3D-modelling of Hi-C data using TADbit reveals structural features of the fly chromatin colors
| Title | Automatic analysis and 3D-modelling of Hi-C data using TADbit reveals structural features of the fly chromatin colors |
| Authors | François Serra, Davide Baù, Mike Goodstadt, David Castillo, Guillaume J. Filion, Marc A. Marti-Renom |
| Abstract | The sequence of a genome is insufficient to understand all genomic processes carried out in the cell nucleus. To achieve this, the knowledge of its three-dimensional architecture is necessary. Advances in genomic technologies and the development of new analytical methods, such as Chromosome Conformation Capture (3C) and its derivatives, provide unprecedented insights in the spatial organization of genomes. Here we present TADbit, a computational framework to analyze and model the chromatin fiber in three dimensions. Our package takes as input the sequencing reads of 3C-based experiments and performs the following main tasks: (i) pre-process the reads, (ii) map the reads to a reference genome, (iii) filter and normalize the interaction data, (iv) analyze the resulting interaction matrices, (v) build 3D models of selected genomic domains, and (vi) analyze the resulting models to characterize their structural properties. To illustrate the use of TADbit, we automatically modeled 50 genomic domains from the fly genome revealing differential structural features of the previously defined chromatin colors, establishing a link between the conformation of the genome and the local chromatin composition. TADbit provides three-dimensional models built from 3C-based experiments, which are ready for visualization and for characterizing their relation to gene expression and epigenetic states. TADbit is an open-source Python library available for download from https://github.com/3DGenomes/tadbit. |
| Tasks | |
| Published | 2017-07-19 |
| URL | https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1005665 |
| https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1005665&type=printable | |
| PWC | https://paperswithcode.com/paper/automatic-analysis-and-3d-modelling-of-hi-c |
| Repo | https://github.com/3DGenomes/tadbit |
| Framework | none |
Improving Coarsening Schemes for Hypergraph Partitioning by Exploiting Community Structure
| Title | Improving Coarsening Schemes for Hypergraph Partitioning by Exploiting Community Structure |
| Authors | Tobias Heuer, Sebastian Schlag |
| Abstract | We present an improved coarsening process for multilevel hypergraph partitioning that incorporates global information about the community structure. Community detection is performed via modularity maximization on a bipartite graph representation. The approach is made suitable for different classes of hypergraphs by defining weights for the graph edges that express structural properties of the hypergraph. We integrate our approach into a leading multilevel hypergraph partitioner with strong local search algorithms and perform extensive experiments on a large benchmark set of hypergraphs stemming from application areas such as VLSI design, SAT solving, and scientific computing. Our results indicate that respecting community structure during coarsening not only significantly improves the solutions found by the initial partitioning algorithm, but also consistently improves overall solution quality. |
| Tasks | Community Detection, graph partitioning, hypergraph partitioning |
| Published | 2017-01-01 |
| URL | http://drops.dagstuhl.de/opus/volltexte/2017/7622/ |
| http://drops.dagstuhl.de/opus/volltexte/2017/7622/pdf/LIPIcs-SEA-2017-21.pdf | |
| PWC | https://paperswithcode.com/paper/improving-coarsening-schemes-for-hypergraph |
| Repo | https://github.com/SebastianSchlag/kahypar |
| Framework | none |
