A Survey of Automated Text Simplification

Shardlow, Matthew

doi:10.14569/specialissue.2014.040109

Cited by 153 publications

(164 citation statements)

References 46 publications

(52 reference statements)

Supporting

Mentioning

133

Contrasting

Unclassified

Order By: Relevance

“…For instance, linking named entities like species, chemicals or locations to unique concepts in appropriate ontologies/taxonomies would support generalisations such as iron is a metal or a diatom is a plankton. Generalisation also bears a strong resemblance to other text-to-text generation tasks such as paraphrasing (Androutsopoulos and Malakasiotis, 2010), sentence compression (Jing, 2000) and sentence simplification (Shardlow, 2014). Given suitable training data, ML approaches may therefore be applied, e.g.…”

Section: Discussionmentioning

confidence: 99%

Extraction and generalisation of variables from scientific publications

Marsi

Öztürk

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Scientific theories and models in Earth science typically involve changing variables and their complex interactions, including correlations, causal relations and chains of positive/negative feedback loops. Variables tend to be complex rather than atomic entities and expressed as noun phrases containing multiple modifiers, e.g. oxygen depletion in the upper 500 m of the ocean or timing and magnitude of surface temperature evolution in the Southern Hemisphere in deglacial proxy records. Text mining from Earth science literature is therefore significantly different from biomedical text mining and requires different approaches and methods. Our approach aims at automatically locating and extracting variables and their direction of variation: increasing, decreasing or just changing. Variables are initially extracted by matching tree patterns onto the syntax trees of the source texts. Next, variables are generalised in order to enhance their similarity, facilitating hierarchical search and inference. This generalisation is accomplished by progressive pruning of syntax trees using a set of tree transformation operations. Text mining results are presented as a browsable variable hierarchy which allows users to inspect all mentions of a particular variable type in the text as well as any generalisations or specialisations. The approach is demonstrated on a corpus of 10k abstracts of Nature publications in the field of Marine science. We discuss experiences with this early prototype and outline a number of possible improvements and directions for future research.

show abstract

Section: Discussionmentioning

confidence: 99%

Extraction and generalisation of variables from scientific publications

Marsi

Öztürk

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…While the former has been the strategy used in the early works and in lesser resourced languages, the latter has been more frequent in the last years for English. Detailed surveys about ATS can be found in the works by Gonzalez-Dios et al (2013), Shardlow (2014) and Siddharthan (2014). In both approaches corpora of simplified texts are needed (not necessarily parallel) (1) to write and revise the rules and (2) to learn them automatically or establish weights and priorities among them.…”

Section: Related Workmentioning

confidence: 99%

The corpus of Basque simplified texts (CBST)

Gonzalez-Dios

Aranzabe

Ilarraza

2017

Lang Resources & Evaluation

View full text Add to dashboard Cite

In this paper we present the corpus of Basque simplified texts. This corpus compiles 227 original sentences of science popularisation domain and two simplified versions of each sentence. The simplified versions have been created following different approaches: the structural, by a court translator who considers easy-to-read guidelines and the intuitive, by a teacher based on her experience. The aim of this corpus is to make a comparative analysis of simplified text. To that end, we also present the annotation scheme we have created to annotate the corpus. The annotation scheme is divided into eight macro-operations: delete, merge, split, transformation, insert, reordering, no operation and other. These macro-operations can be classified into different operations. We also relate our work and results to other languages. This corpus will be used to corroborate the decisions taken and to improve the design of the automatic text simplification system for Basque.

show abstract

“…We have also constructed a lexical simplification system using four typical mechanisms of lexical simplification (Shardlow, 2014) shown in Figure1. We expect the standard system to be used as a baseline of Japanese lexical simplification.…”

Section: Constructing Japanese Lexical Simplification Systemmentioning

confidence: 99%

Proceedings of the ACL-IJCNLP 2015 Student Research Workshop

Chen¹,

Ivanova

Pavlick

et al. 2015

View full text Add to dashboard Cite

ISBN 978-1-941643-74-7 ii Introduction Welcome to the ACJ-IJCNLP 2015 Student Research Workshop! Following the tradition of the previous years' workshops, we have two tracks: research papers and thesis proposals. The research papers track is as a venue for Ph.D. students, masters students, and advanced undergraduates to describe completed work or work-in-progress along with preliminary results. The thesis proposal track is offered for advanced Ph.D. students who have decided on a thesis topic and are interested in feedback about their proposal and ideas about future directions for their work.We received in total 18 submissions: 5 thesis proposals and 13 research papers. Of these, we accepted 3 thesis proposals and 4 research papers, giving an acceptance rate of 39% overall: 60% for thesis proposals and 31% for research papers.This year, all of the accepted papers will be presented as posters alongside the main conference short paper posters on the second day of the conference. In addition, authors will each have a chance to give a short oral presentation to advertise their work. The oral session will be held on immediately prior to the poster session.Mentoring programs are a central part of the SRW. This year, students had the opportunity to participate in a pre-submission mentoring program prior to the submission deadline. The mentoring offers students a chance to receive comments from an experienced researcher in the field, in order to improve the quality of the writing and presentation before making their final submission. Fourteen authors participated in the pre-submission mentoring, more than twice as many as participated last year.In addition, authors of accepted papers are matched with mentors who will meet with the students in person during the workshop. This year, each research paper is assigned two mentors and each thesis proposal is assigned one mentor. Each mentor will prepare in-depth comments and questions prior to the student's presentation, and will provide discussion and feedback during the workshop.We are very grateful for the generous financial support from BAOBAG Language Solutions, Google, the Don and Betty Walker Scholarship Fund, and the National Science Foundation. The support of our sponsors allows the SRW to cover the travel and lodging expenses of the authors, keeping the workshop accessible to all students.We would also like to thank our program committee members for their constructive reviews for each paper and all of our mentors for donating their time to work one-on-one with our student authors. Thank you to our faculty advisers for their advice and guidance, and to the ACL-IJCNLP 2015 organizing committee for their constant support. Finally, a huge thank you to all students for their submissions and their participation in this year's SRW. Looking forward to a wonderful workshop! AbstractSpoken dialogue systems (SDS) are rapidly appearing in various smart devices (smartphone, smart-TV, in-car navigating system, etc). The key role in a successful SDS is a spoken language under...

show abstract

A Survey of Automated Text Simplification

Cited by 153 publications

References 46 publications

Extraction and generalisation of variables from scientific publications

Extraction and generalisation of variables from scientific publications

The corpus of Basque simplified texts (CBST)

Proceedings of the ACL-IJCNLP 2015 Student Research Workshop

Contact Info

Product

Resources

About