May 4, 2019

1158 words 6 mins read

Paper Group NANR 166

Paper Group NANR 166

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Selecting Syntactic, Non-redundant Segments in Active Learning for Machine Translation. A Neural Network based Approach to Automatic Post-Editing. Learning Sparse Gaussian Graphical Models with Overlapping …

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Title Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Authors
Abstract
Tasks
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1000/
PDF https://www.aclweb.org/anthology/N16-1000
PWC https://paperswithcode.com/paper/proceedings-of-the-2016-conference-of-the
Repo
Framework

Selecting Syntactic, Non-redundant Segments in Active Learning for Machine Translation

Title Selecting Syntactic, Non-redundant Segments in Active Learning for Machine Translation
Authors Akiva Miura, Graham Neubig, Michael Paul, Satoshi Nakamura
Abstract
Tasks Active Learning, Machine Translation
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1003/
PDF https://www.aclweb.org/anthology/N16-1003
PWC https://paperswithcode.com/paper/selecting-syntactic-non-redundant-segments-in
Repo
Framework

A Neural Network based Approach to Automatic Post-Editing

Title A Neural Network based Approach to Automatic Post-Editing
Authors Santanu Pal, Sudip Kumar Naskar, Mihaela Vela, Josef van Genabith
Abstract
Tasks Automatic Post-Editing, Machine Translation
Published 2016-08-01
URL https://www.aclweb.org/anthology/P16-2046/
PDF https://www.aclweb.org/anthology/P16-2046
PWC https://paperswithcode.com/paper/a-neural-network-based-approach-to-automatic
Repo
Framework

Learning Sparse Gaussian Graphical Models with Overlapping Blocks

Title Learning Sparse Gaussian Graphical Models with Overlapping Blocks
Authors Mohammad Javad Hosseini, Su-In Lee
Abstract We present a novel framework, called GRAB (GRaphical models with overlApping Blocks), to capture densely connected components in a network estimate. GRAB takes as input a data matrix of p variables and n samples, and jointly learns both a network among p variables and densely connected groups of variables (called `blocks’). GRAB has four major novelties as compared to existing network estimation methods: 1) It does not require the blocks to be given a priori. 2) Blocks can overlap. 3) It can jointly learn a network structure and overlapping blocks. 4) It solves a joint optimization problem with the block coordinate descent method that is convex in each step. We show that GRAB reveals the underlying network structure substantially better than four state-of-the-art competitors on synthetic data. When applied to cancer gene expression data, GRAB outperforms its competitors in revealing known functional gene sets and potentially novel genes that drive cancer. |
Tasks
Published 2016-12-01
URL http://papers.nips.cc/paper/6097-learning-sparse-gaussian-graphical-models-with-overlapping-blocks
PDF http://papers.nips.cc/paper/6097-learning-sparse-gaussian-graphical-models-with-overlapping-blocks.pdf
PWC https://paperswithcode.com/paper/learning-sparse-gaussian-graphical-models
Repo
Framework

Exponentially Decaying Bag-of-Words Input Features for Feed-Forward Neural Network in Statistical Machine Translation

Title Exponentially Decaying Bag-of-Words Input Features for Feed-Forward Neural Network in Statistical Machine Translation
Authors Jan-Thorsten Peter, Weiyue Wang, Hermann Ney
Abstract
Tasks Language Modelling, Machine Translation, Speech Recognition
Published 2016-08-01
URL https://www.aclweb.org/anthology/P16-2048/
PDF https://www.aclweb.org/anthology/P16-2048
PWC https://paperswithcode.com/paper/exponentially-decaying-bag-of-words-input
Repo
Framework

WMT 2016 Multimodal Translation System Description based on Bidirectional Recurrent Neural Networks with Double-Embeddings

Title WMT 2016 Multimodal Translation System Description based on Bidirectional Recurrent Neural Networks with Double-Embeddings
Authors Sergio Rodr{'\i}guez Guasch, Marta R. Costa-juss{`a}
Abstract
Tasks Image Captioning, Language Modelling, Machine Translation, Multimodal Machine Translation
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2362/
PDF https://www.aclweb.org/anthology/W16-2362
PWC https://paperswithcode.com/paper/wmt-2016-multimodal-translation-system
Repo
Framework

A Classification-based Approach to Economic Event Detection in Dutch News Text

Title A Classification-based Approach to Economic Event Detection in Dutch News Text
Authors Els Lefever, V{'e}ronique Hoste
Abstract Breaking news on economic events such as stock splits or mergers and acquisitions has been shown to have a substantial impact on the financial markets. As it is important to be able to automatically identify events in news items accurately and in a timely manner, we present in this paper proof-of-concept experiments for a supervised machine learning approach to economic event detection in newswire text. For this purpose, we created a corpus of Dutch financial news articles in which 10 types of company-specific economic events were annotated. We trained classifiers using various lexical, syntactic and semantic features. We obtain good results based on a basic set of shallow features, thus showing that this method is a viable approach for economic event detection in news text.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1051/
PDF https://www.aclweb.org/anthology/L16-1051
PWC https://paperswithcode.com/paper/a-classification-based-approach-to-economic
Repo
Framework

MoBiL: A Hybrid Feature Set for Automatic Human Translation Quality Assessment

Title MoBiL: A Hybrid Feature Set for Automatic Human Translation Quality Assessment
Authors Yu Yuan, Serge Sharoff, Bogdan Babych
Abstract In this paper we introduce MoBiL, a hybrid Monolingual, Bilingual and Language modelling feature set and feature selection and evaluation framework. The set includes translation quality indicators that can be utilized to automatically predict the quality of human translations in terms of content adequacy and language fluency. We compare MoBiL with the QuEst baseline set by using them in classifiers trained with support vector machine and relevance vector machine learning algorithms on the same data set. We also report an experiment on feature selection to opt for fewer but more informative features from MoBiL. Our experiments show that classifiers trained on our feature set perform consistently better in predicting both adequacy and fluency than the classifiers trained on the baseline feature set. MoBiL also performs well when used with both support vector machine and relevance vector machine algorithms.
Tasks Feature Selection, Language Modelling
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1581/
PDF https://www.aclweb.org/anthology/L16-1581
PWC https://paperswithcode.com/paper/mobil-a-hybrid-feature-set-for-automatic
Repo
Framework

Detecting ``Smart’’ Spammers on Social Network: A Topic Model Approach

Title Detecting ``Smart’’ Spammers on Social Network: A Topic Model Approach |
Authors Linqing Liu, Yao Lu, Ye Luo, Renxian Zhang, Laurent Itti, Jianwei Lu
Abstract
Tasks
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-2007/
PDF https://www.aclweb.org/anthology/N16-2007
PWC https://paperswithcode.com/paper/detecting-smart-spammers-on-social-network-a-1
Repo
Framework

LVF-lemon ― Towards a Linked Data Representation of ``Les Verbes fran\ccais’’

Title LVF-lemon ― Towards a Linked Data Representation of ``Les Verbes fran\ccais’’ |
Authors Ingrid Falk, Achim Stein
Abstract In this study we elaborate a road map for the conversion of a traditional lexical syntactico-semantic resource for French into a linguistic linked open data (LLOD) model. Our approach uses current best-practices and the analyses of earlier similar undertakings (lemonUBY and PDEV-lemon) to tease out the most appropriate representation for our resource.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1380/
PDF https://www.aclweb.org/anthology/L16-1380
PWC https://paperswithcode.com/paper/lvf-lemon-a-towards-a-linked-data
Repo
Framework

IBC-C: A Dataset for Armed Conflict Analysis

Title IBC-C: A Dataset for Armed Conflict Analysis
Authors Andrej {\v{Z}}ukov-Gregori{\v{c}}, Zhiyuan Luo, Bartal Veyhe
Abstract
Tasks Named Entity Recognition, Slot Filling
Published 2016-08-01
URL https://www.aclweb.org/anthology/P16-2061/
PDF https://www.aclweb.org/anthology/P16-2061
PWC https://paperswithcode.com/paper/ibc-c-a-dataset-for-armed-conflict-analysis
Repo
Framework

Word Embeddings with Limited Memory

Title Word Embeddings with Limited Memory
Authors Shaoshi Ling, Yangqiu Song, Dan Roth
Abstract
Tasks Dependency Parsing, Word Embeddings
Published 2016-08-01
URL https://www.aclweb.org/anthology/P16-2063/
PDF https://www.aclweb.org/anthology/P16-2063
PWC https://paperswithcode.com/paper/word-embeddings-with-limited-memory
Repo
Framework

The GW/UMD CLPsych 2016 Shared Task System

Title The GW/UMD CLPsych 2016 Shared Task System
Authors Ayah Zirikly, Varun Kumar, Philip Resnik
Abstract
Tasks Lemmatization, Tokenization
Published 2016-06-01
URL https://www.aclweb.org/anthology/W16-0321/
PDF https://www.aclweb.org/anthology/W16-0321
PWC https://paperswithcode.com/paper/the-gwumd-clpsych-2016-shared-task-system
Repo
Framework

Controlling Politeness in Neural Machine Translation via Side Constraints

Title Controlling Politeness in Neural Machine Translation via Side Constraints
Authors Rico Sennrich, Barry Haddow, Alex Birch, ra
Abstract
Tasks Machine Translation
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1005/
PDF https://www.aclweb.org/anthology/N16-1005
PWC https://paperswithcode.com/paper/controlling-politeness-in-neural-machine
Repo
Framework

Integer Linear Programming for Discourse Parsing

Title Integer Linear Programming for Discourse Parsing
Authors J{'e}r{'e}my Perret, Stergos Afantenos, Nicholas Asher, Mathieu Morey
Abstract
Tasks Dependency Parsing
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1013/
PDF https://www.aclweb.org/anthology/N16-1013
PWC https://paperswithcode.com/paper/integer-linear-programming-for-discourse
Repo
Framework
comments powered by Disqus