Unsupervised Neural Text Simplification

Surya, Sai; Mishra, Abhijit; Laha, Anirban; Jain, Parag; Sankaranarayanan, Karthik

doi:10.18653/v1/p19-1198

Cited by 62 publications

(72 citation statements)

References 37 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While unsupervised approaches outperform supervised approaches in terms of coverage, they have the disadvantage of only performing one-to-one substitutions and cannot deal with phrases. They also tend to change the meaning of the sentence and have problems dealing with ambiguous words [30] [31] [32]. However, recently, unsupervised approaches have been improved in this regard by allowing more detailed context information to be obtained [33].…”

Section: Nlp Approaches To Lexical Simplificationmentioning

confidence: 99%

Lexical Simplification System to Improve Web Accessibility

2021

View full text Add to dashboard Cite

People with intellectual, language and learning disabilities face accessibility barriers when reading texts with complex words. Following accessibility guidelines, complex words can be identified, and easy synonyms and definitions can be provided for them as reading aids. To offer support to these reading aids, a lexical simplification system for Spanish has been developed and is presented in this article. The system covers the complex word identification (CWI) task and offers replacement candidates with the substitute generation and selection (SG/SS) task. These tasks have followed machine learning techniques and contextual embeddings using Easy Reading and Plain Language resources, such as dictionaries and corpora. Additionally, due to the polysemy present in the language, the system provides definitions for complex words, which are disambiguated by a rule-based method supported by a state-of-the-art embedding resource. This system is integrated into a web system that provides an easy way to improve the readability and comprehension of Spanish texts. The results obtained are satisfactory; in the CWI task, better results were obtained than with other systems that used the same dataset. The SG/SS task results are comparable to similar works in the English language and provide a solid starting point to improve this task for the Spanish language. Finally, the results of the disambiguation process evaluation were good when evaluated by a linguistic expert. These findings represent an additional advancement in the lexical simplification of texts in Spanish and in a generic domain using easy-to-read resources, among others, to provide systematic support to compliance with accessibility guidelines.

show abstract

Section: Nlp Approaches To Lexical Simplificationmentioning

confidence: 99%

Lexical Simplification System to Improve Web Accessibility

2021

View full text Add to dashboard Cite

show abstract

“…Zhang et al (2017) perform a purely lexical simplification of individual words which must be included in the output set [76]. Most TS solutions use subtypes of recurrent neural networks [5,20,31,39,57,60,61,68,75,76]. The use of recurrent neural networks (RNN) is prevalent in the evaluation of languages, because the respective output depends on the previous or additionally subsequent inputs.…”

Section: The Neuronal Sequence-to-sequence Approachmentioning

confidence: 99%

Machine Learning for Readability Assessment and Text Simplification in Crisis Communication: A Systematic Review

Hansen¹,

Widera²,

Ponge³

et al. 2021

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

In times of social media, crisis managers can interact with the citizens in a variety of ways. Since machine learning has already been used to classify messages from the population, the question is, whether such technologies can play a role in the creation of messages from crisis managers to the population. This paper focuses on an explorative research revolving around selected machine learning solutions for crisis communication. We present systematic literature reviews of readability assessment and text simplification. Our research suggests that readability assessment has the potential for an effective use in crisis communication, but there is a lack of sufficient training data. This also applies to text simplification, where an exact assessment is only partly possible due to unreliable or non-existent training data and validation measures.

show abstract

“…4.4.4 Unsupervised Architectures. Surya et al 2019 proposed an unsupervised approach for developing a simplification system. Their motivation was to design an architecture that could be exploited to train SS models for languages or domains that do not have large resources of parallel original-simplified instances.…”

Section: Figurementioning

confidence: 99%

“…Model architecture for UNTS. Extracted from Surya et al (2019). 4.4.5 Simplification as Sequence Labeling.…”

Section: Figurementioning

confidence: 99%

Data-Driven Sentence Simplification: Survey and Benchmark

Alva-Manchego

Scarton

Specia

2020

Computational Linguistics

View full text Add to dashboard Cite

Sentence Simplification (SS) aims to modify a sentence in order to make it easier to read and understand. In order to do so, several rewriting transformations can be performed such as replacement, reordering, and splitting. Executing these transformations while keeping sentences grammatical, preserving their main idea, and generating simpler output, is a challenging and still far from solved problem. 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 nowadays. We also include a benchmark of different approaches on common data sets so as to compare them and highlight their strengths and limitations. We expect that this survey will serve as a starting point for researchers interested in the task and help spark new ideas for future developments.

show abstract

Unsupervised Neural Text Simplification

Cited by 62 publications

References 37 publications

Lexical Simplification System to Improve Web Accessibility

Lexical Simplification System to Improve Web Accessibility

Machine Learning for Readability Assessment and Text Simplification in Crisis Communication: A Systematic Review

Data-Driven Sentence Simplification: Survey and Benchmark

Contact Info

Product

Resources

About