October 15, 2019

1946 words 10 mins read

Paper Group NANR 203

Paper Group NANR 203

Improving Large-Scale Fact-Checking using Decomposable Attention Models and Lexical Tagging. Ranking Distributions based on Noisy Sorting. Generative diffeomorphic modelling of large MRI data sets for probabilistic template construction. An Italian Twitter Corpus of Hate Speech against Immigrants. From dictations to clinical reports using machine t …

Improving Large-Scale Fact-Checking using Decomposable Attention Models and Lexical Tagging

Title Improving Large-Scale Fact-Checking using Decomposable Attention Models and Lexical Tagging
Authors Nayeon Lee, Chien-Sheng Wu, Pascale Fung
Abstract Fact-checking of textual sources needs to effectively extract relevant information from large knowledge bases. In this paper, we extend an existing pipeline approach to better tackle this problem. We propose a neural ranker using a decomposable attention model that dynamically selects sentences to achieve promising improvement in evidence retrieval F1 by 38.80{%}, with (x65) speedup compared to a TF-IDF method. Moreover, we incorporate lexical tagging methods into our pipeline framework to simplify the tasks and render the model more generalizable. As a result, our framework achieves promising performance on a large-scale fact extraction and verification dataset with speedup.
Tasks Question Answering, Stance Detection
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1143/
PDF https://www.aclweb.org/anthology/D18-1143
PWC https://paperswithcode.com/paper/improving-large-scale-fact-checking-using
Repo
Framework

Ranking Distributions based on Noisy Sorting

Title Ranking Distributions based on Noisy Sorting
Authors Adil El Mesaoudi-Paul, Eyke Hüllermeier, Robert Busa-Fekete
Abstract We propose a new statistical model for ranking data, i.e., a new family of probability distributions on permutations. Our model is inspired by the idea of a data-generating process in the form of a noisy sorting procedure, in which deterministic comparisons between pairs of items are replaced by Bernoulli trials. The probability of producing a certain ranking as a result then essentially depends on the Bernoulli parameters, which can be interpreted as pairwise preferences. We show that our model can be written in closed form if insertion or quick sort are used as sorting algorithms, and propose a maximum likelihood approach for parameter estimation. We also introduce a generalization of the model, in which the constraints on pairwise preferences are relaxed, and for which maximum likelihood estimation can be carried out based on a variation of the generalized iterative scaling algorithm. Experimentally, we show that the models perform very well in terms of goodness of fit, compared to existing models for ranking data.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2051
PDF http://proceedings.mlr.press/v80/mesaoudi-paul18a/mesaoudi-paul18a.pdf
PWC https://paperswithcode.com/paper/ranking-distributions-based-on-noisy-sorting
Repo
Framework

Generative diffeomorphic modelling of large MRI data sets for probabilistic template construction

Title Generative diffeomorphic modelling of large MRI data sets for probabilistic template construction
Authors Claudia Blaiotta, Patrick Freund, M. Jorge Cardoso, John Ashburner
Abstract In this paper we present a hierarchical generative model of medical image data, which can capture simultaneously the variability of both signal intensity and anatomical shapes across large populations. Such a model has a direct application for learning average-shaped probabilistic tissue templates in a fully automated manner. While in principle the generality of the proposed Bayesian approach makes it suitable to address a wide range of medical image computing problems, our work focuses primarily on neuroimaging applications. In particular we validate the proposed method on both real and synthetic brain MR scans including the cervical cord and demonstrate that it yields accurate alignment of brain and spinal cord structures, as compared to state-of-the-art tools for medical image registration. At the same time we illustrate how the resulting tissue probability maps can readily be used to segment, bias correct and spatially normalise unseen data, which are all crucial pre-processing steps for MR imaging studies.
Tasks Diffeomorphic Medical Image Registration, Image Registration, Medical Image Registration
Published 2018-02-01
URL https://doi.org/10.1016/j.neuroimage.2017.10.060
PDF http://discovery.ucl.ac.uk/10036377/1/Ashburner_1-s2.0-S1053811917308947-main.pdf
PWC https://paperswithcode.com/paper/generative-diffeomorphic-modelling-of-large
Repo
Framework

An Italian Twitter Corpus of Hate Speech against Immigrants

Title An Italian Twitter Corpus of Hate Speech against Immigrants
Authors Manuela Sanguinetti, Fabio Poletto, Cristina Bosco, Viviana Patti, Marco Stranisci
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1443/
PDF https://www.aclweb.org/anthology/L18-1443
PWC https://paperswithcode.com/paper/an-italian-twitter-corpus-of-hate-speech
Repo
Framework

From dictations to clinical reports using machine translation

Title From dictations to clinical reports using machine translation
Authors Gregory Finley, Wael Salloum, Najmeh Sadoughi, Erik Edwards, Am Robinson, a, Nico Axtmann, Michael Brenndoerfer, Mark Miller, David Suendermann-Oeft
Abstract A typical workflow to document clinical encounters entails dictating a summary, running speech recognition, and post-processing the resulting text into a formatted letter. Post-processing entails a host of transformations including punctuation restoration, truecasing, marking sections and headers, converting dates and numerical expressions, parsing lists, etc. In conventional implementations, most of these tasks are accomplished by individual modules. We introduce a novel holistic approach to post-processing that relies on machine callytranslation. We show how this technique outperforms an alternative conventional system{—}even learning to correct speech recognition errors during post-processing{—}while being much simpler to maintain.
Tasks Machine Translation, Speech Recognition
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-3015/
PDF https://www.aclweb.org/anthology/N18-3015
PWC https://paperswithcode.com/paper/from-dictations-to-clinical-reports-using
Repo
Framework

GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints

Title GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints
Authors Fuhai Chen, Rongrong Ji, Xiaoshuai Sun, Yongjian Wu, Jinsong Su
Abstract Most image captioning models focus on one-line (single image) captioning, where the correlations like relevance and diversity among group images (e.g., within the same album or event) are simply neglected, resulting in less accurate and diverse captions. Recent works mainly consider imposing the diversity during the online inference only, which neglect the correlation among visual structures in offline training. In this paper, we propose a novel group-based image captioning scheme (termed GroupCap), which jointly models the structured relevance and diversity among visual contents of group images towards an optimal collaborative captioning. In particular, we first propose a visual tree parser (VP-Tree) to construct the structured semantic correlations within individual images. Then, the relevance and diversity among images are well modeled by exploiting the correlations among their tree structures. Finally, such correlations are modeled as constraints and sent into the LSTM-based captioning generator. In offline optimization, we adopt an end-to-end formulation, which jointly trains the visual tree parser, the structured relevance and diversity constraints, as well as the LSTM based captioning model. To facilitate quantitative evaluation, we further release two group captioning datasets derived from the MS-COCO benchmark, serving as the first of their kind. Quantitative results show that the proposed GroupCap model outperforms the state-of-the-art and alternative approaches, which can generate much more accurate and discriminative captions under various evaluation metrics.
Tasks Image Captioning
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Chen_GroupCap_Group-Based_Image_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_GroupCap_Group-Based_Image_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/groupcap-group-based-image-captioning-with
Repo
Framework

Utilizing Large Twitter Corpora to Create Sentiment Lexica

Title Utilizing Large Twitter Corpora to Create Sentiment Lexica
Authors Valerij Fredriksen, Brage Jahren, Bj{"o}rn Gamb{"a}ck
Abstract
Tasks Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1447/
PDF https://www.aclweb.org/anthology/L18-1447
PWC https://paperswithcode.com/paper/utilizing-large-twitter-corpora-to-create
Repo
Framework

Dialog Intent Structure: A Hierarchical Schema of Linked Dialog Acts

Title Dialog Intent Structure: A Hierarchical Schema of Linked Dialog Acts
Authors Silvia Pareti, L, Tatiana o
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1460/
PDF https://www.aclweb.org/anthology/L18-1460
PWC https://paperswithcode.com/paper/dialog-intent-structure-a-hierarchical-schema
Repo
Framework

Boundary Seeking GANs

Title Boundary Seeking GANs
Authors R Devon Hjelm, Athul Paul Jacob, Adam Trischler, Gerry Che, Kyunghyun Cho, Yoshua Bengio
Abstract Generative adversarial networks are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated samples being completely differentiable w.r.t. the generative parameters, and thus do not work for discrete data. We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator. The importance weights have a strong connection to the decision boundary of the discriminator, and we call our method boundary-seeking GANs (BGANs). We demonstrate the effectiveness of the proposed algorithm with discrete image and character-based natural language generation. In addition, the boundary-seeking objective extends to continuous data, which can be used to improve stability of training, and we demonstrate this on Celeba, Large-scale Scene Understanding (LSUN) bedrooms, and Imagenet without conditioning.
Tasks Scene Understanding, Text Generation
Published 2018-01-01
URL https://openreview.net/forum?id=rkTS8lZAb
PDF https://openreview.net/pdf?id=rkTS8lZAb
PWC https://paperswithcode.com/paper/boundary-seeking-gans
Repo
Framework

Book Review: Bayesian Analysis in Natural Language Processing by Shay Cohen

Title Book Review: Bayesian Analysis in Natural Language Processing by Shay Cohen
Authors Kevin Duh
Abstract
Tasks Coreference Resolution, Machine Translation
Published 2018-03-01
URL https://www.aclweb.org/anthology/J18-1006/
PDF https://www.aclweb.org/anthology/J18-1006
PWC https://paperswithcode.com/paper/book-review-bayesian-analysis-in-natural
Repo
Framework

PoSTWITA-UD: an Italian Twitter Treebank in Universal Dependencies

Title PoSTWITA-UD: an Italian Twitter Treebank in Universal Dependencies
Authors Manuela Sanguinetti, Cristina Bosco, Alberto Lavelli, Aless Mazzei, ro, Oronzo Antonelli, Fabio Tamburini
Abstract
Tasks Opinion Mining, Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1279/
PDF https://www.aclweb.org/anthology/L18-1279
PWC https://paperswithcode.com/paper/postwita-ud-an-italian-twitter-treebank-in
Repo
Framework

Modeling Collaborative Multimodal Behavior in Group Dialogues: The MULTISIMO Corpus

Title Modeling Collaborative Multimodal Behavior in Group Dialogues: The MULTISIMO Corpus
Authors Maria Koutsombogera, Carl Vogel
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1466/
PDF https://www.aclweb.org/anthology/L18-1466
PWC https://paperswithcode.com/paper/modeling-collaborative-multimodal-behavior-in
Repo
Framework

Scalable Construction and Reasoning of Massive Knowledge Bases

Title Scalable Construction and Reasoning of Massive Knowledge Bases
Authors Xiang Ren, Nanyun Peng, William Yang Wang
Abstract In today{'}s information-based society, there is abundant knowledge out there carried in the form of natural language texts (e.g., news articles, social media posts, scientific publications), which spans across various domains (e.g., corporate documents, advertisements, legal acts, medical reports), which grows at an astonishing rate. Yet this knowledge is mostly inaccessible to computers and overwhelming for human experts to absorb. How to turn such massive and unstructured text data into structured, actionable knowledge, and furthermore, how to teach machines learn to reason and complete the extracted knowledge is a grand challenge to the research community. Traditional IE systems assume abundant human annotations for training high quality machine learning models, which is impractical when trying to deploy IE systems to a broad range of domains, settings and languages. In the first part of the tutorial, we introduce how to extract structured facts (i.e., entities and their relations for types of interest) from text corpora to construct knowledge bases, with a focus on methods that are weakly-supervised and domain-independent for timely knowledge base construction across various application domains. In the second part, we introduce how to leverage other knowledge, such as the distributional statistics of characters and words, the annotations for other tasks and other domains, and the linguistics and problem structures, to combat the problem of inadequate supervision, and conduct low-resource information extraction. In the third part, we describe recent advances in knowledge base reasoning. We start with the gentle introduction to the literature, focusing on path-based and embedding based methods. We then describe DeepPath, a recent attempt of using deep reinforcement learning to combine the best of both worlds for knowledge base reasoning.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-6003/
PDF https://www.aclweb.org/anthology/N18-6003
PWC https://paperswithcode.com/paper/scalable-construction-and-reasoning-of
Repo
Framework

CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition

Title CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition
Authors Jedrzej Kozerawski, Matthew Turk
Abstract This work addresses the novel problem of one-shot one-class classification. The goal is to estimate a classification decision boundary for a novel class based on a single image example. Our method exploits transfer learning to model the transformation from a representation of the input, extracted by a Convolutional Neural Network, to a classification decision boundary. We use a deep neural network to learn this transformation from a large labelled dataset of images and their associated class decision boundaries generated from ImageNet, and then apply the learned decision boundary to classify subsequent query images. We tested our approach on several benchmark datasets and significantly outperformed the baseline methods.
Tasks Transfer Learning
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Kozerawski_CLEAR_Cumulative_LEARning_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Kozerawski_CLEAR_Cumulative_LEARning_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/clear-cumulative-learning-for-one-shot-one
Repo
Framework

Leveraging Lexical Resources and Constraint Grammar for Rule-Based Part-of-Speech Tagging in Welsh

Title Leveraging Lexical Resources and Constraint Grammar for Rule-Based Part-of-Speech Tagging in Welsh
Authors Steven Neale, Kevin Donnelly, Gareth Watkins, Dawn Knight
Abstract
Tasks Part-Of-Speech Tagging
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1623/
PDF https://www.aclweb.org/anthology/L18-1623
PWC https://paperswithcode.com/paper/leveraging-lexical-resources-and-constraint
Repo
Framework
comments powered by Disqus