publication . Conference object . 2017

Lexical Simplification with Neural Ranking

Paetzold, Gustavo Henrique; Specia, Lucia;
Open Access
  • Published: 03 Apr 2017
  • Publisher: Association for Computational Linguistics (ACL)
We present a new Lexical Simplification approach that exploits Neural Networks to learn substitutions from the Newsela corpus - a large set of professionally produced simplifications. We extract candidate substitutions by combining the Newsela corpus with a retrofitted context-aware word embeddings model and rank them using a new neural regression model that learns rankings from annotated data. This strategy leads to the highest Accuracy, Precision and F1 scores to date in standard datasets for the task.
ACM Computing Classification System: InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL
free text keywords: Artificial intelligence, business.industry, business, Computer science, Artificial neural network, Lexical simplification, Ranking, Regression analysis, Natural language processing, computer.software_genre, computer
Related Organizations
Communities with gateway
OpenAIRE Connect image
Funded by
SIMplifying the interaction with Public Administration Through Information technology for Citizens and cOmpanies
  • Funder: European Commission (EC)
  • Project Code: 692819
  • Funding stream: H2020 | RIA
Download fromView all 3 versions
Open Access
Conference object . 2017
Provider: ZENODO
Open Access
Conference object . 2017
Provider: Datacite
Open Access
Conference object . 2017
Provider: Datacite
Any information missing or wrong?Report an Issue