Abstract
We present a new, structured approach to text simplification using conditional random fields over top-down traversals of dependency graphs that jointly predicts possible compressions and paraphrases. Our model reaches readability scores comparable to word-based compression approaches across a range of metrics and human judgements while maintaining more of the important information.
Originalsprog | Engelsk |
---|---|
Titel | The 54th Annual Meeting of the Association for Computational Linguistics : Proceedings of the Conference |
Antal sider | 7 |
Vol/bind | 2 |
Udgivelsessted | Berlin |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2016 |
Sider | 337-343 |
ISBN (Trykt) | 9781626012945 |
Status | Udgivet - 2016 |
Begivenhed | ACL 2016 - Varighed: 7 aug. 2016 → 12 aug. 2016 |
Konference
Konference | ACL 2016 |
---|---|
Periode | 07/08/2016 → 12/08/2016 |