May 5, 2019

1303 words 7 mins read

Paper Group NANR 94

Paper Group NANR 94

PJAIT Systems for the WMT 2016. TAXI at SemEval-2016 Task 13: a Taxonomy Induction Method based on Lexico-Syntactic Patterns, Substrings and Focused Crawling. Modelling the Combination of Generic and Target Domain Embeddings in a Convolutional Neural Network for Sentence Classification. Text Segmentation of Digitized Clinical Texts. Extractive Summ …

PJAIT Systems for the WMT 2016

Title PJAIT Systems for the WMT 2016
Authors Krzysztof Wolk, Krzysztof Marasek
Abstract
Tasks Domain Adaptation, Language Modelling, Machine Translation, Transliteration, Word Alignment
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2328/
PDF https://www.aclweb.org/anthology/W16-2328
PWC https://paperswithcode.com/paper/pjait-systems-for-the-wmt-2016
Repo
Framework

TAXI at SemEval-2016 Task 13: a Taxonomy Induction Method based on Lexico-Syntactic Patterns, Substrings and Focused Crawling

Title TAXI at SemEval-2016 Task 13: a Taxonomy Induction Method based on Lexico-Syntactic Patterns, Substrings and Focused Crawling
Authors Alex Panchenko, er, Stefano Faralli, Eugen Ruppert, Steffen Remus, Hubert Naets, C{'e}drick Fairon, Simone Paolo Ponzetto, Chris Biemann
Abstract
Tasks Language Modelling
Published 2016-06-01
URL https://www.aclweb.org/anthology/S16-1206/
PDF https://www.aclweb.org/anthology/S16-1206
PWC https://paperswithcode.com/paper/taxi-at-semeval-2016-task-13-a-taxonomy
Repo
Framework

Modelling the Combination of Generic and Target Domain Embeddings in a Convolutional Neural Network for Sentence Classification

Title Modelling the Combination of Generic and Target Domain Embeddings in a Convolutional Neural Network for Sentence Classification
Authors Nut Limsopatham, Nigel Collier
Abstract
Tasks Chunking, Named Entity Recognition, Part-Of-Speech Tagging, Sentence Classification, Text Classification, Word Embeddings
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2918/
PDF https://www.aclweb.org/anthology/W16-2918
PWC https://paperswithcode.com/paper/modelling-the-combination-of-generic-and
Repo
Framework

Text Segmentation of Digitized Clinical Texts

Title Text Segmentation of Digitized Clinical Texts
Authors Cyril Grouin
Abstract In this paper, we present the experiments we made to recover the original page layout structure into two columns from layout damaged digitized files. We designed several CRF-based approaches, either to identify column separator or to classify each token from each line into left or right columns. We achieved our best results with a model trained on homogeneous corpora (only files composed of 2 columns) when classifying each token into left or right columns (overall F-measure of 0.968). Our experiments show it is possible to recover the original layout in columns of digitized documents with results of quality.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1570/
PDF https://www.aclweb.org/anthology/L16-1570
PWC https://paperswithcode.com/paper/text-segmentation-of-digitized-clinical-texts
Repo
Framework

Extractive Summarization under Strict Length Constraints

Title Extractive Summarization under Strict Length Constraints
Authors Yashar Mehdad, Am Stent, a, Kapil Thadani, Dragomir Radev, Youssef Billawala, Karolina Buchner
Abstract In this paper we report a comparison of various techniques for single-document extractive summarization under strict length budgets, which is a common commercial use case (e.g. summarization of news articles by news aggregators). We show that, evaluated using ROUGE, numerous algorithms from the literature fail to beat a simple lead-based baseline for this task. However, a supervised approach with lightweight and efficient features improves over the lead-based baseline. Additional human evaluation demonstrates that the supervised approach also performs competitively with a commercial system that uses more sophisticated features.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1493/
PDF https://www.aclweb.org/anthology/L16-1493
PWC https://paperswithcode.com/paper/extractive-summarization-under-strict-length
Repo
Framework

Building a Dataset for Possessions Identification in Text

Title Building a Dataset for Possessions Identification in Text
Authors Carmen Banea, Xi Chen, Rada Mihalcea
Abstract Just as industrialization matured from mass production to customization and personalization, so has the Web migrated from generic content to public disclosures of one{'}s most intimately held thoughts, opinions and beliefs. This relatively new type of data is able to represent finer and more narrowly defined demographic slices. If until now researchers have primarily focused on leveraging personalized content to identify latent information such as gender, nationality, location, or age of the author, this study seeks to establish a structured way of extracting possessions, or items that people own or are entitled to, as a way to ultimately provide insights into people{'}s behaviors and characteristics. In order to promote more research in this area, we are releasing a set of 798 possessions extracted from blog genre, where possessions are marked at different confidence levels, as well as a detailed set of guidelines to help in future annotation studies.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1592/
PDF https://www.aclweb.org/anthology/L16-1592
PWC https://paperswithcode.com/paper/building-a-dataset-for-possessions
Repo
Framework

BAD LUC@WMT 2016: a Bilingual Document Alignment Platform Based on Lucene

Title BAD LUC@WMT 2016: a Bilingual Document Alignment Platform Based on Lucene
Authors Laurent Jakubina, Phillippe Langlais
Abstract
Tasks Information Retrieval, Machine Translation
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2370/
PDF https://www.aclweb.org/anthology/W16-2370
PWC https://paperswithcode.com/paper/bad-lucwmt-2016-a-bilingual-document
Repo
Framework

USFD’s Phrase-level Quality Estimation Systems

Title USFD’s Phrase-level Quality Estimation Systems
Authors Varvara Logacheva, Fr{'e}d{'e}ric Blain, Lucia Specia
Abstract
Tasks Machine Translation
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2386/
PDF https://www.aclweb.org/anthology/W16-2386
PWC https://paperswithcode.com/paper/usfdas-phrase-level-quality-estimation
Repo
Framework

Unbabel’s Participation in the WMT16 Word-Level Translation Quality Estimation Shared Task

Title Unbabel’s Participation in the WMT16 Word-Level Translation Quality Estimation Shared Task
Authors Andr{'e} F. T. Martins, Ram{'o}n Astudillo, Chris Hokamp, Fabio Kepler
Abstract
Tasks Machine Translation
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2387/
PDF https://www.aclweb.org/anthology/W16-2387
PWC https://paperswithcode.com/paper/unbabels-participation-in-the-wmt16-word
Repo
Framework

Recurrent Neural Network based Translation Quality Estimation

Title Recurrent Neural Network based Translation Quality Estimation
Authors Hyun Kim, Jong-Hyeok Lee
Abstract
Tasks Language Modelling, Machine Translation
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2384/
PDF https://www.aclweb.org/anthology/W16-2384
PWC https://paperswithcode.com/paper/recurrent-neural-network-based-translation
Repo
Framework

SimpleNets: Quality Estimation with Resource-Light Neural Networks

Title SimpleNets: Quality Estimation with Resource-Light Neural Networks
Authors Gustavo Paetzold, Lucia Specia
Abstract
Tasks Machine Translation, Text Simplification, Word Embeddings
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2388/
PDF https://www.aclweb.org/anthology/W16-2388
PWC https://paperswithcode.com/paper/simplenets-quality-estimation-with-resource
Repo
Framework

Newtonian Scene Understanding: Unfolding the Dynamics of Objects in Static Images

Title Newtonian Scene Understanding: Unfolding the Dynamics of Objects in Static Images
Authors Roozbeh Mottaghi, Hessam Bagherinezhad, Mohammad Rastegari, Ali Farhadi
Abstract In this paper, we study the challenging problem of predicting the dynamics of objects in static images. Given a query object in an image, our goal is to provide a physical understanding of the object in terms of the forces acting upon it and its long term motion as response to those forces. Direct and explicit estimation of the forces and the motion of objects from a single image is extremely challenging. We define intermediate physical abstractions called Newtonian scenarios and introduce Newtonian Neural Network (N^3) that learns to map a single image to a state in a Newtonian scenario. Our experimental evaluations show that our method can reliably predict dynamics of a query object from a single image. In addition, our approach can provide physical reasoning that supports the predicted dynamics in terms of velocity and force vectors. To spur research in this direction we compiled Visual Newtonian Dynamics (VIND) dataset that includes more than 6000 videos aligned with Newtonian scenarios represented using game engines, and more than 4500 still images with their ground truth dynamics.
Tasks Scene Understanding
Published 2016-06-01
URL http://openaccess.thecvf.com/content_cvpr_2016/html/Mottaghi_Newtonian_Scene_Understanding_CVPR_2016_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2016/papers/Mottaghi_Newtonian_Scene_Understanding_CVPR_2016_paper.pdf
PWC https://paperswithcode.com/paper/newtonian-scene-understanding-unfolding-the
Repo
Framework

Stochastic Three-Composite Convex Minimization

Title Stochastic Three-Composite Convex Minimization
Authors Alp Yurtsever, Bang Cong Vu, Volkan Cevher
Abstract We propose a stochastic optimization method for the minimization of the sum of three convex functions, one of which has Lipschitz continuous gradient as well as restricted strong convexity. Our approach is most suitable in the setting where it is computationally advantageous to process smooth term in the decomposition with its stochastic gradient estimate and the other two functions separately with their proximal operators, such as doubly regularized empirical risk minimization problems. We prove the convergence characterization of the proposed algorithm in expectation under the standard assumptions for the stochastic gradient estimate of the smooth term. Our method operates in the primal space and can be considered as a stochastic extension of the three-operator splitting method. Finally, numerical evidence supports the effectiveness of our method in real-world problems.
Tasks Stochastic Optimization
Published 2016-12-01
URL http://papers.nips.cc/paper/6127-stochastic-three-composite-convex-minimization
PDF http://papers.nips.cc/paper/6127-stochastic-three-composite-convex-minimization.pdf
PWC https://paperswithcode.com/paper/stochastic-three-composite-convex
Repo
Framework

Proceedings of the Australasian Language Technology Association Workshop 2016

Title Proceedings of the Australasian Language Technology Association Workshop 2016
Authors
Abstract
Tasks
Published 2016-12-01
URL https://www.aclweb.org/anthology/U16-1000/
PDF https://www.aclweb.org/anthology/U16-1000
PWC https://paperswithcode.com/paper/proceedings-of-the-australasian-language
Repo
Framework

Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)

Title Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)
Authors
Abstract
Tasks
Published 2016-12-01
URL https://www.aclweb.org/anthology/W16-3900/
PDF https://www.aclweb.org/anthology/W16-3900
PWC https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-noisy-user
Repo
Framework
comments powered by Disqus