58890 |
Creator |
8eb9378b0e3dcd225dfc47fcdc9b35f4 |
58890 |
Creator |
ext-04e063da97c9c7bbfae2cbbcc52bafd8 |
58890 |
Date |
2014 |
58890 |
Is Part Of |
repository |
58890 |
abstract |
We present an approach to text simplification based on synchronous dependency grammars.
Our main contributions in this work are (a) a study of how automatically derived lexical
simplification rules can be generalised to enable their application in new contexts
without introducing errors, and (b) an evaluation of our hybrid system that combines
a large set of automatically acquired rules with a small set of hand-crafted rules
for common syntactic simplification. Our evaluation shows significant improvements
over the state of the art, with scores comparable to human simplifications. |
58890 |
authorList |
authors |
58890 |
presentedAt |
ext-611c509e7fddb2677aa63aecd43394e4 |
58890 |
status |
peerReviewed |
58890 |
type |
AcademicArticle |
58890 |
type |
Article |
58890 |
label |
Angrosh, M.A. and Siddharthan, Advaith (2014). Text simplification using synchronous
dependency grammars: Generalising automatically harvested rules. In: 8th International
Natural Language Generation Conference, 19-21 Jun 2014, Philadelphia, Pennsylvania,
pp. 16–25. |
58890 |
label |
Angrosh, M.A. and Siddharthan, Advaith (2014). Text simplification using synchronous
dependency grammars: Generalising automatically harvested rules. In: 8th International
Natural Language Generation Conference, 19-21 Jun 2014, Philadelphia, Pennsylvania,
pp. 16–25. |
58890 |
Title |
Text simplification using synchronous dependency grammars: Generalising automatically
harvested rules |
58890 |
in dataset |
oro |