Results 1 -
5 of
5
A Survey of Automated Text Simplification
"... Abstract—Text simplification modifies syntax and lexicon to improve the understandability of language for an end user. This survey identifies and classifies simplification research within the period 1998-2013. Simplification can be used for many applications, including: Second language learners, pre ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract—Text simplification modifies syntax and lexicon to improve the understandability of language for an end user. This survey identifies and classifies simplification research within the period 1998-2013. Simplification can be used for many applications, including: Second language learners, preprocessing in pipelines and assistive technology. There are many approaches to the simplification task, including: lexical, syntactic, statistical machine translation and hybrid techniques. This survey also explores the current challenges which this field faces. Text simplification is a non-trivial task which is rapidly growing into its own field. This survey gives an overview of contemporary research whilst taking into account the history that has brought text simplification to its current state.
Reliable Lexical Simplification for Non-Native Speakers
"... Abstract Lexical Simplification is the task of modifying the lexical content of complex sentences in order to make them simpler. Due to the lack of reliable resources available for the task, most existing approaches have difficulties producing simplifications which are grammatical and that preserve ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract Lexical Simplification is the task of modifying the lexical content of complex sentences in order to make them simpler. Due to the lack of reliable resources available for the task, most existing approaches have difficulties producing simplifications which are grammatical and that preserve the meaning of the original text. In order to improve on the state-of-the-art of this task, we propose user studies with nonnative speakers, which will result in new, sizeable datasets, as well as novel ways of performing Lexical Simplification. The results of our first experiments show that new types of classifiers, along with the use of additional resources such as spoken text language models, produce the state-of-the-art results for the Lexical Simplification task of SemEval-2012.
The Case for Readability of Crisis Communications in Social Media
"... ABSTRACT The readability of text documents has been studied from a linguistic perspective long before people began to regularly communicate via Internet technologies. Typically, such studies look at books or articles containing many paragraphs and pages. However, the readability of short messages c ..."
Abstract
- Add to MetaCart
(Show Context)
ABSTRACT The readability of text documents has been studied from a linguistic perspective long before people began to regularly communicate via Internet technologies. Typically, such studies look at books or articles containing many paragraphs and pages. However, the readability of short messages comprising a few sentences, common on today's social networking sites and microblogging services, has received less attention from researchers working on "readability". Emergency management specialists, crisis response practitioners, and scholars have long recognized that clear communication is essential during crises. To the best of our knowledge, the work we present here is the first to study the readability of crisis communications posted on Twitter-by governments, non-governmental organizations, and mainstream media. The data we analyze is comprised of hundreds of tweets posted during 15 different crises in English-speaking countries, which happened between 2012 and 2013. We describe factors which negatively affect comprehension, and consider how understanding can be improved. Based on our analysis and observations, we conclude with several recommendations for how to write brief crisis messages on social media that are clear and easy to understand.
www.ijacsa.thesai.org Editorial Preface From the Desk of Guest Editor …
"... NLP has got many new challenging and interesting areas of research. It has gone much beyond ordinary translation of text from one language to another. Existing translation tools are becoming more and more accurate and are preserving the context nicely. Till few years, there were only applications la ..."
Abstract
- Add to MetaCart
(Show Context)
NLP has got many new challenging and interesting areas of research. It has gone much beyond ordinary translation of text from one language to another. Existing translation tools are becoming more and more accurate and are preserving the context nicely. Till few years, there were only applications laced with other areas of AI like image processing (for OCR), speech recognition, etc. These days, due to the evolution of web technologies, there are many applications coming up using NLP as a key domain. Name entity recognition (NER) is a huge addition these days in almost languages. In this Special Issue on Natural Language Processing, we have papers in the area of pure NLP as well as with application areas of soft computing, ontology, etc. It is good to see papers coming from all across the globe; they are from India,
Text Rewriting Improves Semantic Role Labeling
"... Large-scale annotated corpora are a prerequisite to developing high-performance NLP systems. Such corpora are expensive to produce, limited in size, often demanding linguistic expertise. In this paper we use text rewriting as a means of increasing the amount of labeled data available for model train ..."
Abstract
- Add to MetaCart
(Show Context)
Large-scale annotated corpora are a prerequisite to developing high-performance NLP systems. Such corpora are expensive to produce, limited in size, often demanding linguistic expertise. In this paper we use text rewriting as a means of increasing the amount of labeled data available for model training. Our method uses automatically extracted rewrite rules from comparable corpora and bitexts to generate multiple versions of sentences annotated with gold standard labels. We apply this idea to semantic role labeling and show that a model trained on rewritten data outperforms the state of the art on the CoNLL-2009 benchmark dataset. 1.
