Filters








35,859 Hits in 5.0 sec

Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs

Fernando Alva-Manchego, Joachim Bingel, Gustavo Henrique Paetzold, Carolina Scarton, Lucia Specia
2017 Zenodo  
While the recently introduced Newsela corpus has alleviated the first problem, simplifications still need to be learned directly from parallel text using black-box, end-to-end approaches rather than from  ...  These complex-simple parallel sentence pairs often differ to such a high degree that generalization becomes difficult.  ...  Introduction Text Simplification (TS) is the task of reducing the complexity of a text without changing its meaning.  ... 
doi:10.5281/zenodo.1042505 fatcat:vcmaka3d7fgxdiclvdx4qxo4f4

EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing

Yue Dong, Zichao Li, Mehdi Rezagholizadeh, Jackie Chi Kit Cheung
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
These methods learn to simplify sentences as a byproduct of the fact that they are trained on complex-simple sentence pairs.  ...  Most current neural sentence simplification systems are variants of sequence-to-sequence models adopted from machine translation.  ...  We thank Sanqiang Zhao and Xin Jiang for sharing their pearls of wisdom, Xingxing Zhang for providing the datasets and three anonymous reviewers for giving their insights and comments.  ... 
doi:10.18653/v1/p19-1331 dblp:conf/acl/DongLRC19 fatcat:lsdt5e5mw5c6npaek3ein2dgs4

A Survey on Text Simplification [article]

Punardeep Sikka, Vijay Mago
2020 arXiv   pre-print
Text Simplification (TS) aims to reduce the linguistic complexity of content to make it easier to understand.  ...  Research in TS has been of keen interest, especially as approaches to TS have shifted from manual, hand-crafted rules to automated simplification.  ...  ACKNOWLEDGMENTS We would like to thank Canada Revenue Agency (CRA) for providing funding for our research in Text Simplification.  ... 
arXiv:2008.08612v2 fatcat:ki3l25kwr5hhpprxhuxr7b672a

A Survey on Lexical Simplification

Gustavo H. Paetzold, Lucia Specia
2017 The Journal of Artificial Intelligence Research  
ranking of the selected substitutes according to their simplicity.  ...  Lexical Simplification is the process of replacing complex words in a given sentence with simpler alternatives of equivalent meaning.  ...  Implicit Sense Labelling An intuitive way to address some of the limitations of explicit sense labelling is to use automatic methods to learn sense classes of complex words, instead of querying them from  ... 
doi:10.1613/jair.5526 fatcat:vdzvoemabjh3pftykyyyz5a2me

Discourse Level Factors for Sentence Deletion in Text Simplification [article]

Yang Zhong, Chao Jiang, Wei Xu, Junyi Jessy Li
2020 arXiv   pre-print
We find that discourse level factors contribute to the challenging task of predicting sentence deletion for simplification.  ...  We reveal that professional editors utilize different strategies to meet readability standards of elementary and middle schools.  ...  The views and conclusions contained in this publication are those of the authors and should not be interpreted as representing official policies or endorsements of the U.S. Government.  ... 
arXiv:1911.10384v4 fatcat:qksdwxockjd3vhmvh3oqsdl4kq

An Analysis of Crowdsourced Text Simplifications

Marcelo Amancio, Lucia Specia
2014 Proceedings of the 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR)  
from data.  ...  The aim is to understand whether a complex-simple parallel corpus involving this version of Wikipedia is appropriate as data source to induce simplification rules, and whether we can automatically categorise  ...  Features We extract simple features from the source (original, complex) and target (simplified) sentences.  ... 
doi:10.3115/v1/w14-1214 dblp:conf/acl-pitr/AmancioS14 fatcat:sxe5l6o3jvavrn2hldyfjd7dpa

Discourse Level Factors for Sentence Deletion in Text Simplification

Yang Zhong, Chao Jiang, Wei Xu, Junyi Jessy Li
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We find that discourse level factors contribute to the challenging task of predicting sentence deletion for simplification.  ...  We reveal that professional editors utilize different strategies to meet readability standards of elementary and middle schools.  ...  The views and conclusions contained in this publication are those of the authors and should not be interpreted as representing official policies or endorsements of the U.S. Government.  ... 
doi:10.1609/aaai.v34i05.6520 fatcat:vi4dmubg5bgdrfiqzk3gaql7oe

A Corpus for Automatic Readability Assessment and Text Simplification of German [article]

Alessia Battisti, Sarah Ebling
2019 arXiv   pre-print
As a novel contribution, it contains information on text structure, typography, and images, which can be exploited as part of machine learning approaches to readability assessment and text simplification  ...  The corpus is compiled from web sources and consists of approximately 211,000 sentences.  ...  simplification experiments on the data. 52 websites and 233 PDFs (amounting to approximately 26,000 sentences) have an explicit language level label.  ... 
arXiv:1909.09067v1 fatcat:5xkxq2tjpjckvkjziioz7pqcxm

Data-Driven Sentence Simplification: Survey and Benchmark

Fernando Alva-Manchego, Carolina Scarton, Lucia Specia
2020 Computational Linguistics  
In this article, we survey research on SS, focusing on approaches that attempt to learn how to simplify using corpora of aligned original-simplified sentence pairs in English, which is the dominant paradigm  ...  We also include a benchmark of different approaches on common datasets so as to compare them and highlight their strengths and limitations.  ...  Although instances formed by identical sentence pairs are important for learning when not to simplify, misalignments add noise to the data and prevent models from learning how to perform the task accurately  ... 
doi:10.1162/coli_a_00370 fatcat:k7mlggplrreudk5pgq62x2fmva

ESL Reading: More on text comprehensibility

Heather Lotherington-Woloszyn
1987 The TESL Canada Journal  
Research about the comprehensibility of simplified texts is conflicting due, no doubt, to the enormous complexity of the reading process.  ...  Their purposes for reading, to learn about Canadian history, to understand how to assemble a model airplane, to follow a recipe, to appreciate modern poetry, together with their choice of subject matter  ... 
doi:10.18806/tesl.v5i1.520 fatcat:zuycfvstszcnjlylg3zexrfngy

Adult Learning and Language Simplification

Mark Atkinson, Kenny Smith, Simon Kirby
2018 Cognitive Science  
A possible explanation for this is that languages with a greater number of speakers tend to also be those with higher proportions of non-native speakers, who may simplify language during learning.  ...  In Experiment 2, we explore how these simplifications may then propagate through subsequent learning.  ...  The funders had no involvement in study design; in the collection, analysis, and interpretation of the data; in the writing of the report; or in the decision to submit the article for publication.  ... 
doi:10.1111/cogs.12686 pmid:30320460 fatcat:sbrkdmdnmrcg7oe2iep4zf3hyy

Par4Sim -- Adaptive Paraphrasing for Text Simplification [article]

Seid Muhie Yimam, Chris Biemann
2018 arXiv   pre-print
In this work, we have developed an adaptive learning system for text simplification, which improves the underlying learning-to-rank model from usage data, i.e. how users have employed the system for the  ...  Learning from a real-world data stream and continuously updating the model without explicit supervision is a new challenge for NLP applications with machine learning components.  ...  Special thanks goes to Rawda Assefa and Sisay Adugna for the proofreading of the Amharic abstract translation.  ... 
arXiv:1806.08309v1 fatcat:yitm5zywcjcyvphsbcjrdpw4eq

Simplification Using Paraphrases and Context-Based Lexical Substitution

Reno Kriz, Eleni Miltsakaki, Marianna Apidianaki, Chris Callison-Burch
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
Lexical simplification involves identifying complex words or phrases that need to be simplified, and recommending simpler meaningpreserving substitutes that can be more easily understood.  ...  They also highlight the limited contribution of context features for CWI, which nonetheless improve simplification compared to contextunaware models.  ...  Acknowledgements We would like to thank the anonymous reviewers for their helpful comments and feedback on this work, and Anne Cocos for sharing with us her implementation of the AddCos model with PPDB  ... 
doi:10.18653/v1/n18-1019 dblp:conf/naacl/KrizMAC18 fatcat:bqj5g2qzcfgxxdx72wkax6ahje

Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification [article]

Neha Srikanth, Junyi Jessy Li
2021 arXiv   pre-print
Much of modern-day text simplification research focuses on sentence-level simplification, transforming original, more complex sentences into simplified versions.  ...  We introduce a new annotated dataset of 1.3K instances of elaborative simplification in the Newsela corpus, and analyze how entities, ideas, and concepts are elaborated through the lens of contextual specificity  ...  Com- from the simplified document). pared to text from the simplified document, text With elaboration.  ... 
arXiv:2010.10035v3 fatcat:k35bhb5dtveo3h2dghsrsltnui

A Survey on Extraction of Causal Relations from Natural Language Text [article]

Jie Yang, Soyeon Caren Han, Josiah Poon
2021 arXiv   pre-print
As an essential component of human cognition, cause-effect relations appear frequently in text, and curating cause-effect relations from text helps in building causal networks for predictive tasks.  ...  In the past few years, deep learning techniques attract substantial attention from NLP researchers because of its' powerful representation learning ability and the rapid increase in computational resources  ...  of GCN in complex texts.  ... 
arXiv:2101.06426v2 fatcat:hd3ikb7mejcndlq6wsgojv4uoa
« Previous Showing results 1 — 15 out of 35,859 results