October 15, 2019

1888 words 9 mins read

Paper Group NANR 217

Paper Group NANR 217

Comparing Automatic and Human Evaluation of Local Explanations for Text Classification. Detecting Figurative Word Occurrences Using Recurrent Neural Networks. LiDAR-Video Driving Dataset: Learning Driving Policies Effectively. Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines. Proceedings of the Workshop on Generalization in th …

Comparing Automatic and Human Evaluation of Local Explanations for Text Classification

Title Comparing Automatic and Human Evaluation of Local Explanations for Text Classification
Authors Dong Nguyen
Abstract Text classification models are becoming increasingly complex and opaque, however for many applications it is essential that the models are interpretable. Recently, a variety of approaches have been proposed for generating local explanations. While robust evaluations are needed to drive further progress, so far it is unclear which evaluation approaches are suitable. This paper is a first step towards more robust evaluations of local explanations. We evaluate a variety of local explanation approaches using automatic measures based on word deletion. Furthermore, we show that an evaluation using a crowdsourcing experiment correlates moderately with these automatic measures and that a variety of other factors also impact the human judgements.
Tasks Recommendation Systems, Text Classification
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1097/
PDF https://www.aclweb.org/anthology/N18-1097
PWC https://paperswithcode.com/paper/comparing-automatic-and-human-evaluation-of
Repo
Framework

Detecting Figurative Word Occurrences Using Recurrent Neural Networks

Title Detecting Figurative Word Occurrences Using Recurrent Neural Networks
Authors Agnieszka Mykowiecka, Aleks Wawer, er, Malgorzata Marciniak
Abstract The paper addresses detection of figurative usage of words in English text. The chosen method was to use neural nets fed by pretrained word embeddings. The obtained results show that simple solutions, based on words embeddings only, are comparable to complex solutions, using many sources of information which are not available for languages less-studied than English.
Tasks Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0916/
PDF https://www.aclweb.org/anthology/W18-0916
PWC https://paperswithcode.com/paper/detecting-figurative-word-occurrences-using
Repo
Framework

LiDAR-Video Driving Dataset: Learning Driving Policies Effectively

Title LiDAR-Video Driving Dataset: Learning Driving Policies Effectively
Authors Yiping Chen, Jingkang Wang, Jonathan Li, Cewu Lu, Zhipeng Luo, Han Xue, Cheng Wang
Abstract Learning autonomous-driving policies is one of the most challenging but promising tasks for computer vision. Most researchers believe that future research and applications should combine cameras, video recorders and laser scanners to obtain comprehensive semantic understanding of real traffic. However, current approaches only learn from large-scale videos, due to the lack of benchmarks that consist of precise laser-scanner data. In this paper, we are the first to propose a LiDAR-Video dataset, which provides large-scale high-quality point clouds scanned by a Velodyne laser, videos recorded by a dashboard camera and standard drivers’ behaviors. Extensive experiments demonstrate that extra depth information help networks to determine driving policies indeed.
Tasks Autonomous Driving
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Chen_LiDAR-Video_Driving_Dataset_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_LiDAR-Video_Driving_Dataset_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/lidar-video-driving-dataset-learning-driving
Repo
Framework

Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines

Title Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines
Authors Bin Gu, Zhouyuan Huo, Cheng Deng, Heng Huang
Abstract Asynchronous parallel stochastic gradient optimization has been playing a pivotal role to solve large-scale machine learning problems in big data applications. Zeroth-order (derivative-free) methods estimate the gradient only by two function evaluations, thus have been applied to solve the problems where the explicit gradient calculations are computationally expensive or infeasible. Recently, the first asynchronous parallel stochastic zeroth-order algorithm (AsySZO) was proposed. However, its convergence rate is O(1/SQRT{T}) for the smooth, possibly non-convex learning problems, which is significantly slower than O(1/T) the best convergence rate of (asynchronous) stochastic gradient algorithm. To fill this gap, in this paper, we first point out the fundamental reason leading to the slow convergence rate of AsySZO, and then propose a new asynchronous stochastic zerothorder algorithm (AsySZO+). We provide a faster convergence rate O(1/bT) (b is the mini-batch size) for AsySZO+ by the rigorous theoretical analysis, which is a significant improvement over O(1/SQRT{T}). The experimental results on the application of ensemble learning confirm that our AsySZO+ has a faster convergence rate than the existing (asynchronous) stochastic zeroth-order algorithms.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2022
PDF http://proceedings.mlr.press/v80/gu18a/gu18a.pdf
PWC https://paperswithcode.com/paper/faster-derivative-free-stochastic-algorithm
Repo
Framework

Proceedings of the Workshop on Generalization in the Age of Deep Learning

Title Proceedings of the Workshop on Generalization in the Age of Deep Learning
Authors
Abstract
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-1000/
PDF https://www.aclweb.org/anthology/W18-1000
PWC https://paperswithcode.com/paper/proceedings-of-the-workshop-on-generalization
Repo
Framework

PhraseCTM: Correlated Topic Modeling on Phrases within Markov Random Fields

Title PhraseCTM: Correlated Topic Modeling on Phrases within Markov Random Fields
Authors Weijing Huang
Abstract Recent emerged phrase-level topic models are able to provide topics of phrases, which are easy to read for humans. But these models are lack of the ability to capture the correlation structure among the discovered numerous topics. We propose a novel topic model PhraseCTM and a two-stage method to find out the correlated topics at phrase level. In the first stage, we train PhraseCTM, which models the generation of words and phrases simultaneously by linking the phrases and component words within Markov Random Fields when they are semantically coherent. In the second stage, we generate the correlation of topics from PhraseCTM. We evaluate our method by a quantitative experiment and a human study, showing the correlated topic modeling on phrases is a good and practical way to interpret the underlying themes of a corpus.
Tasks Topic Models
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-2083/
PDF https://www.aclweb.org/anthology/P18-2083
PWC https://paperswithcode.com/paper/phrasectm-correlated-topic-modeling-on
Repo
Framework

Encoding Gated Translation Memory into Neural Machine Translation

Title Encoding Gated Translation Memory into Neural Machine Translation
Authors Qian Cao, Deyi Xiong
Abstract Translation memories (TM) facilitate human translators to reuse existing repetitive translation fragments. In this paper, we propose a novel method to combine the strengths of both TM and neural machine translation (NMT) for high-quality translation. We treat the target translation of a TM match as an additional reference input and encode it into NMT with an extra encoder. A gating mechanism is further used to balance the impact of the TM match on the NMT decoder. Experiment results on the UN corpus demonstrate that when fuzzy matches are higher than 50{%}, the quality of NMT translation can be significantly improved by over 10 BLEU points.
Tasks Machine Translation, Semantic Textual Similarity, Sentence Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1340/
PDF https://www.aclweb.org/anthology/D18-1340
PWC https://paperswithcode.com/paper/encoding-gated-translation-memory-into-neural
Repo
Framework
Title Classification of Medication-Related Tweets Using Stacked Bidirectional LSTMs with Context-Aware Attention
Authors Orest Xherija
Abstract This paper describes the system that team UChicagoCompLx developed for the 2018 Social Media Mining for Health Applications (SMM4H) Shared Task. We use a variant of the Message-level Sentiment Analysis (MSA) model of (Baziotis et al., 2017), a word-level stacked bidirectional Long Short-Term Memory (LSTM) network equipped with attention, to classify medication-related tweets in the four subtasks of the SMM4H Shared Task. Without any subtask-specific tuning, the model is able to achieve competitive results across all subtasks. We make the datasets, model weights, and code publicly available.
Tasks Sentiment Analysis, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5910/
PDF https://www.aclweb.org/anthology/W18-5910
PWC https://paperswithcode.com/paper/classification-of-medication-related-tweets
Repo
Framework

Social and Emotional Correlates of Capitalization on Twitter

Title Social and Emotional Correlates of Capitalization on Twitter
Authors Sophia Chan, Alona Fyshe
Abstract Social media text is replete with unusual capitalization patterns. We posit that capitalizing a token like THIS performs two expressive functions: it marks a person socially, and marks certain parts of an utterance as more salient than others. Focusing on gender and sentiment, we illustrate using a corpus of tweets that capitalization appears in more negative than positive contexts, and is used more by females compared to males. Yet we find that both genders use capitalization in a similar way when expressing sentiment.
Tasks Sentiment Analysis
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-1102/
PDF https://www.aclweb.org/anthology/W18-1102
PWC https://paperswithcode.com/paper/social-and-emotional-correlates-of
Repo
Framework

Smart Enough to Talk With Us? Foundations and Challenges for Dialogue Capable AI Systems

Title Smart Enough to Talk With Us? Foundations and Challenges for Dialogue Capable AI Systems
Authors Barbara J. Grosz
Abstract
Tasks Machine Translation
Published 2018-03-01
URL https://www.aclweb.org/anthology/J18-1001/
PDF https://www.aclweb.org/anthology/J18-1001
PWC https://paperswithcode.com/paper/smart-enough-to-talk-with-us-foundations-and
Repo
Framework

The Benefit of Pseudo-Reference Translations in Quality Estimation of MT Output

Title The Benefit of Pseudo-Reference Translations in Quality Estimation of MT Output
Authors Melania Duma, Wolfgang Menzel
Abstract In this paper, a novel approach to Quality Estimation is introduced, which extends the method in (Duma and Menzel, 2017) by also considering pseudo-reference translations as data sources to the tree and sequence kernels used before. Two variants of the system were submitted to the sentence level WMT18 Quality Estimation Task for the English-German language pair. They have been ranked 4th and 6th out of 13 systems in the SMT track, while in the NMT track ranks 4 and 5 out of 11 submissions have been reached.
Tasks Machine Translation
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6460/
PDF https://www.aclweb.org/anthology/W18-6460
PWC https://paperswithcode.com/paper/the-benefit-of-pseudo-reference-translations
Repo
Framework

Proceedings of the Seventh Named Entities Workshop

Title Proceedings of the Seventh Named Entities Workshop
Authors
Abstract
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2400/
PDF https://www.aclweb.org/anthology/W18-2400
PWC https://paperswithcode.com/paper/proceedings-of-the-seventh-named-entities
Repo
Framework

Coverage and Cynicism: The AFRL Submission to the WMT 2018 Parallel Corpus Filtering Task

Title Coverage and Cynicism: The AFRL Submission to the WMT 2018 Parallel Corpus Filtering Task
Authors Grant Erdmann, Jeremy Gwinnup
Abstract The WMT 2018 Parallel Corpus Filtering Task aims to test various methods of filtering a noisy parallel corpus, to make it useful for training machine translation systems. We describe the AFRL submissions, including their preprocessing methods and quality metrics. Numerical results indicate relative benefits of different options and show where our methods are competitive.
Tasks Machine Translation
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6475/
PDF https://www.aclweb.org/anthology/W18-6475
PWC https://paperswithcode.com/paper/coverage-and-cynicism-the-afrl-submission-to
Repo
Framework

GNEG: Graph-Based Negative Sampling for word2vec

Title GNEG: Graph-Based Negative Sampling for word2vec
Authors Zheng Zhang, Pierre Zweigenbaum
Abstract Negative sampling is an important component in word2vec for distributed word representation learning. We hypothesize that taking into account global, corpus-level information and generating a different noise distribution for each target word better satisfies the requirements of negative examples for each training word than the original frequency-based distribution. In this purpose we pre-compute word co-occurrence statistics from the corpus and apply to it network algorithms such as random walk. We test this hypothesis through a set of experiments whose results show that our approach boosts the word analogy task by about 5{%} and improves the performance on word similarity tasks by about 1{%} compared to the skip-gram negative sampling baseline.
Tasks Language Modelling, Representation Learning
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-2090/
PDF https://www.aclweb.org/anthology/P18-2090
PWC https://paperswithcode.com/paper/gneg-graph-based-negative-sampling-for
Repo
Framework

Document Enhancement Using Visibility Detection

Title Document Enhancement Using Visibility Detection
Authors Netanel Kligler, Sagi Katz, Ayellet Tal
Abstract This paper re-visits classical problems in document enhancement. Rather than proposing a new algorithm for a specific problem, we introduce a novel general approach. The key idea is to modify any state- of-the-art algorithm, by providing it with new information (input), improving its own results. Interestingly, this information is based on a solution to a seemingly unrelated problem of visibility detection in R3. We show that a simple representation of an image as a 3D point cloud, gives visibility detection on this cloud a new interpretation. What does it mean for a point to be visible? Although this question has been widely studied within computer vision, it has always been assumed that the point set is a sampling of a real scene. We show that the answer to this question in our context reveals unique and useful information about the image. We demonstrate the benefit of this idea for document binarization and for unshadowing.
Tasks Document Binarization
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Kligler_Document_Enhancement_Using_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Kligler_Document_Enhancement_Using_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/document-enhancement-using-visibility
Repo
Framework
comments powered by Disqus