Paper Group NAWR 13
Neural network based spectral mask estimation for acoustic beamforming. Finding significant combinations of features in the presence of categorical covariates. Probabilistic Graph-based Dependency Parsing with Convolutional Neural Network. Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter. Discrete-State Va …
Neural network based spectral mask estimation for acoustic beamforming
| Title | Neural network based spectral mask estimation for acoustic beamforming |
| Authors | Jahn Heymann, Lukas Drude, Reinhold Haeb-Umbach |
| Abstract | We present a neural network based approach to acoustic beamforming. The network is used to estimate spectral masks from which the Cross-Power Spectral Density matrices of speech and noise are estimated, which in turn are used to compute the beamformer coefficients. The network training is independent of the number and the geometric configuration of the microphones. We further show that it is possible to train the network on clean speech only, avoiding the need for stereo data with separated speech and noise. Two types of networks are evaluated. One small feed-forward network with only one hidden layer and one more elaborated bi-directional Long Short-Term Memory network. We compare our system with different parametric approaches to mask estimation and using different beamforming algorithms. We show that our system yields superior results, both in terms of perceptual speech quality and with respect to speech recognition error rate. The results for the simple feed-forward network are especially encouraging considering its low computational requirements. |
| Tasks | Speech Recognition |
| Published | 2016-03-20 |
| URL | https://ieeexplore.ieee.org/document/7471664 |
| https://groups.uni-paderborn.de/nt/pubs/2016/icassp_2016_heymann_paper.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-based-spectral-mask-estimation |
| Repo | https://github.com/fgnt/nn-gev |
| Framework | none |
Finding significant combinations of features in the presence of categorical covariates
| Title | Finding significant combinations of features in the presence of categorical covariates |
| Authors | Laetitia Papaxanthos, Felipe Llinares-Lopez, Dean Bodenham, Karsten Borgwardt |
| Abstract | In high-dimensional settings, where the number of features p is typically much larger than the number of samples n, methods which can systematically examine arbitrary combinations of features, a huge 2^p-dimensional space, have recently begun to be explored. However, none of the current methods is able to assess the association between feature combinations and a target variable while conditioning on a categorical covariate, in order to correct for potential confounding effects. We propose the Fast Automatic Conditional Search (FACS) algorithm, a significant discriminative itemset mining method which conditions on categorical covariates and only scales as O(k log k), where k is the number of states of the categorical covariate. Based on the Cochran-Mantel-Haenszel Test, FACS demonstrates superior speed and statistical power on simulated and real-world datasets compared to the state of the art, opening the door to numerous applications in biomedicine. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6345-finding-significant-combinations-of-features-in-the-presence-of-categorical-covariates |
| http://papers.nips.cc/paper/6345-finding-significant-combinations-of-features-in-the-presence-of-categorical-covariates.pdf | |
| PWC | https://paperswithcode.com/paper/finding-significant-combinations-of-features |
| Repo | https://github.com/BorgwardtLab/FACS |
| Framework | none |
Probabilistic Graph-based Dependency Parsing with Convolutional Neural Network
| Title | Probabilistic Graph-based Dependency Parsing with Convolutional Neural Network |
| Authors | Zhisong Zhang, Hai Zhao, Lianhui Qin |
| Abstract | |
| Tasks | Constituency Parsing, Dependency Parsing, Transition-Based Dependency Parsing |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1131/ |
| https://www.aclweb.org/anthology/P16-1131 | |
| PWC | https://paperswithcode.com/paper/probabilistic-graph-based-dependency-parsing |
| Repo | https://github.com/zzsfornlp/nnpgdparser |
| Framework | none |
Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter
| Title | Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter |
| Authors | Zeerak Waseem, Dirk Hovy |
| Abstract | |
| Tasks | Hate Speech Detection |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-2013/ |
| https://www.aclweb.org/anthology/N16-2013 | |
| PWC | https://paperswithcode.com/paper/hateful-symbols-or-hateful-people-predictive |
| Repo | https://github.com/zeerakw/hatespeech |
| Framework | none |
Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations
| Title | Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations |
| Authors | Diego Marcheggiani, Ivan Titov |
| Abstract | We present a method for unsupervised open-domain relation discovery. In contrast to previous (mostly generative and agglomerative clustering) approaches, our model relies on rich contextual features and makes minimal independence assumptions. The model is composed of two parts: a feature-rich relation extractor, which predicts a semantic relation between two entities, and a factorization model, which reconstructs arguments (i.e., the entities) relying on the predicted relation. The two components are estimated jointly so as to minimize errors in recovering arguments. We study factorization models inspired by previous work in relation factorization and selectional preference modeling. Our models substantially outperform the generative and agglomerative-clustering counterparts and achieve state-of-the-art performance. |
| Tasks | Information Retrieval, Natural Language Inference, Question Answering, Relation Extraction |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/Q16-1017/ |
| https://www.aclweb.org/anthology/Q16-1017 | |
| PWC | https://paperswithcode.com/paper/discrete-state-variational-autoencoders-for |
| Repo | https://github.com/diegma/relation-autoencoder |
| Framework | none |
Do We Really Need All Those Rich Linguistic Features? A Neural Network-Based Approach to Implicit Sense Labeling
| Title | Do We Really Need All Those Rich Linguistic Features? A Neural Network-Based Approach to Implicit Sense Labeling |
| Authors | Niko Schenk, Christian Chiarcos, Don, Kathrin t, Samuel R{"o}nnqvist, Evgeny Stepanov, Giuseppe Riccardi |
| Abstract | |
| Tasks | Reading Comprehension, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-2005/ |
| https://www.aclweb.org/anthology/K16-2005 | |
| PWC | https://paperswithcode.com/paper/do-we-really-need-all-those-rich-linguistic |
| Repo | https://github.com/atreyasha/shallow-discourse-parser |
| Framework | none |
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
| Title | Single-Image Crowd Counting via Multi-Column Convolutional Neural Network |
| Authors | Yingying Zhang, Desen Zhou, Siqin Chen, Shenghua Gao, Yi Ma |
| Abstract | This paper aims to develop a method than can accurately estimate the crowd count from an individual image with arbitrary crowd density and arbitrary perspective. To this end, we have proposed a simple but effective Multi-column Convolutional Neural Network (MCNN) architecture to map the image to its crowd density map. The proposed MCNN allows the input image to be of arbitrary size or resolution. By utilizing filters with receptive fields of different sizes, the features learned by each column CNN are adaptive to variations in people/head size due to perspective effect or image resolution. Furthermore, the true density map is computed accurately based on geometry-adaptive kernels which do not need knowing the perspective map of the input image. Since exiting crowd counting datasets do not adequately cover all the challenging situations considered in our work, we have collected and labelled a large new dataset that includes 1198 images with about 330,000 heads annotated. On this challenging new dataset, as well as all existing datasets, we conduct extensive experiments to verify the effectiveness of the proposed model and method. In particular, with the proposed simple MCNN model, our method outperforms all existing methods. In addition, experiments show that our model, once trained on one dataset, can be readily transferred to a new dataset. |
| Tasks | Crowd Counting |
| Published | 2016-01-01 |
| URL | https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhang_Single-Image_Crowd_Counting_CVPR_2016_paper.pdf |
| https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Zhang_Single-Image_Crowd_Counting_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/single-image-crowd-counting-via-multi-column-1 |
| Repo | https://github.com/CommissarMa/MCNN-pytorch |
| Framework | pytorch |
An Unsupervised Model of Orthographic Variation for Historical Document Transcription
| Title | An Unsupervised Model of Orthographic Variation for Historical Document Transcription |
| Authors | Dan Garrette, Hannah Alpert-Abrams |
| Abstract | |
| Tasks | Optical Character Recognition |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1055/ |
| https://www.aclweb.org/anthology/N16-1055 | |
| PWC | https://paperswithcode.com/paper/an-unsupervised-model-of-orthographic |
| Repo | https://github.com/tberg12/ocular |
| Framework | none |
Are You a Racist or Am I Seeing Things? Annotator Influence on Hate Speech Detection on Twitter
| Title | Are You a Racist or Am I Seeing Things? Annotator Influence on Hate Speech Detection on Twitter |
| Authors | Zeerak Waseem |
| Abstract | |
| Tasks | Hate Speech Detection |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-5618/ |
| https://www.aclweb.org/anthology/W16-5618 | |
| PWC | https://paperswithcode.com/paper/are-you-a-racist-or-am-i-seeing-things |
| Repo | https://github.com/zeerakw/hatespeech |
| Framework | none |
