Unsupervised Lexical Simplification for Non-Native Speakers

AAAI 2016 pp. 3761-3767

doi:10.1609/AAAI.V30I1.9885 /aaai/2016/paetzold2016aaai-unsupervised/

Abstract

Lexical Simplification is the task of replacing complex words with simpler alternatives. We propose a novel, unsupervised approach for the task. It relies on two resources: a corpus of subtitles and a new type of word embeddings model that accounts for the ambiguity of words. We compare the performance of our approach and many others over a new evaluation dataset, which accounts for the simplification needs of 400 non-native English speakers. The experiments show that our approach outperforms state-of-the-art work in Lexical Simplification.

PDF AAAI Semantic Scholar

Cite

Text

Paetzold and Specia. "Unsupervised Lexical Simplification for Non-Native Speakers." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.9885

Markdown

[Paetzold and Specia. "Unsupervised Lexical Simplification for Non-Native Speakers." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/paetzold2016aaai-unsupervised/) doi:10.1609/AAAI.V30I1.9885

BibTeX

@inproceedings{paetzold2016aaai-unsupervised,
  title     = {{Unsupervised Lexical Simplification for Non-Native Speakers}},
  author    = {Paetzold, Gustavo H. and Specia, Lucia},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {3761-3767},
  doi       = {10.1609/AAAI.V30I1.9885},
  url       = {https://mlanthology.org/aaai/2016/paetzold2016aaai-unsupervised/}
}