01.08.2016 09:33

Invited Talk by Sanja Štajner: Current Trends and Challenges in Text Simplification

The Language Technology Group is pleased to announce the talk of

Sanja Štajner (Post-doctoral researcher, Data and Web Science Group, University of Mannheim) 


with the title


Current Trends and Challenges in Text Simplification


The talk will take place on August 17th from 11:00pm-12:30pm at S2|02 A313.

 


Abstract:

The vast majority of texts we encounter in our everyday lives are lexically and syntactically very complex. This poses difficulties both to humans to understand them and to machines to process them. Text simplification aims to convert complex texts into their simpler variants taking into consideration specific needs of the target population or intended application. The manual simplification of the existing texts following easy-to-read guidelines is expensive and time-consuming. That created the need for this process to be automated. In the last 20 years, many automatic text simplification (ATS) systems have been proposed for various languages. In this talk, we cover several different approaches which have been used for building ATS systems so far giving a particular focus on the current state of the art. We discuss the recently discovered problems in machine translation approach to text simplification (Štajner et al., 2015, Štajner and Saggion, 2015) and present the event-based approach to ATS (Glavaš and Štajner, 2013) which is able to overcome some of the main problems in ATS. Finally, we present the evaluation methodology used in text simplification studies pointing out the need for proposing automatic evaluation systems for this specific task and present the results of the first shared task on automatic evaluation of text simplification systems (Štajner et al, 2016).


Bio:

Sanja Štajner is a post-doctoral researcher in Data and Web Science Group at the University of Mannheim. She holds her bachelors degree in Mathematics and Computer Science from the University of Belgrade (Serbia), multiple Masters degree in Natural Language Processing and Human Language Processing from the Autonomous University of Barcelona (Spain) and University of Wolverhampton (UK), and the PhD degree in Computer Science, on the topic of “Data-Driven Approaches to Text Simplification”, from the University of Wolverhampton (UK). Her main research interests are text simplification, text accessibility and readability.

 

 

 

 

Štajner, S., Popovic, M., Saggion, H., Specia, L. and Fishel M. 2016. Shared Task on Quality Assessment for Text Simplification. In Proceedings of the LREC Workshop on Quality Assessment for Text Simplification, Portoroz, Slovenia, May 28, pp. 22-31.

Štajner, S., Béchara, H. and Saggion, H. 2015. A Deeper Exploration of the Standard PB-SMT Approach to Text Simplification and its Evaluation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (ACL-IJCNLP), Beijing, China, 26-31 July 2015, pp. 823-828.

Štajner, S. and Saggion, H. 2015. Translating from Original to Simplified Sentences using Moses: When does it Actually Work? In Proceedings of the Recent Advances in Natural Language Processing (RANLP), Hissar, Bulgaria, 5-11 September 2015, pp. 611-617.

Glavaš G. and Štajner, S. 2013. Event-Centered Simplification of News Stories. In Proceedings of the Student Research Workshop at the International Conference on Recent Advances in Natural Language Processing (RANLP 2013) , Hissar, Bulgaria, 9-11 September 2013, pp. 71-78.




Related news:


Category:
Allgemeine News



A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Suche Search | Kontakt Contact | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang