Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Natural Language Processing for Text Adaptation [Self-Funded Students Only]

   Cardiff School of Computer Science & Informatics

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Fernando Alva Manchego  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Lots of informative publicly available content is written in a language that may not be easy to understand by everyone. For example, the latest research on a disease, terms and conditions for using an app, documents in public administration, etc. Could we develop systems that automatically rewrite these types of documents so that a target reader can more easily understand them?

To accomplish the previous goal, we could work with several areas within Natural Language Processing. The main one would be Text Simplification, which aims to modify the content and structure of a text to make it easier to read and understand, while preserving its original meaning. Depending on the type of document and application, Text Summarization technology could also be included, aiming to generate a shorter version of the original text that contains the most relevant information. In addition, depending on the target reader, we could also consider a Machine Translation component, if the original texts are in one language (e.g. English) and the rewritten documents should be in another (e.g. Spanish).

Possible lines of research for a PhD that could be studied with the previous motivation are:

  • Automatic Text Simplification for specific domains, such as medical, legal or public administration. Important progress has been done in simplifying news. However, tackling other domains incorporates new challenges, such as handling domain-specific terminology and reduced availably of resources.
  • Readability-controlled Translation, combining Text Simplification with Machine Translation. Recent research has attempted to guide the “complexity” or readability of automatically translated texts. However, these works are limited in the type of documents explored, and progress has been measured only using automatic metrics, and not more reliable human judgments.
  • Document-level Text Simplification, a more realistic use case for Simplification technology aiming to rewrite entire documents or webpages, instead of single sentences as is mostly done in current research. This line of work would potently involve Summarization technology as well.

Other projects could certainly be explored, depending on the specific research interests of the applicant. During their research, the PhD student would work on collecting appropriate datasets for training and evaluation, implementing machine learning models for the task, and designing suitable evaluation methodologies and metrics. 

For further information on the project please contact: Dr Fernando Alva Manchego ([Email Address Removed])

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas. 

Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component. 

How to apply:

Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below

This project is accepting applications all year round, for self-funded candidates via 

In order to be considered candidates must submit the following information: 

  • Supporting statement 
  • CV 
  • In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD
  • Qualification certificates and Transcripts
  • Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded)
  • References x 2 
  • Proof of English language (if applicable)

Interview - If the application meets the entrance requirements, you will be invited to an interview

If you have any additional questions or need more information, please contact [Email Address Removed] 

Computer Science (8)

Funding Notes

This project is offered for self-funded students only, or those with their own sponsorship or scholarship award.
Please note that a PhD Scholarship may also available for this PhD project. If you are interested in applying for a PhD Scholarship, please search FindAPhD for this specific project title, supervisor or School within its Scholarships category.


Fernando Alva-Manchego, Carolina Scarton, and Lucia Specia. 2020. Data-Driven Sentence Simplification: Survey and Benchmark. Computational Linguistics, 46(1):135–187.
Sweta Agrawal and Marine Carpuat. 2019. Controlling Text Complexity in Neural Machine Translation. In EMNLP-IJCNLP 2019.
Ashwin Devaraj, Iain J. Marshall, Byron C. Wallace, and Junyi Jessy Li (2021). Paragraph-level Simplification of Medical Texts. In NAACL 2021.

How good is research at Cardiff University in Computer Science and Informatics?

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Where will I study?

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.