Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/40600
Title: Natural language generation with tree conditional random fields
Authors: Lu, W. 
Ng, H.T. 
Lee, W.S. 
Issue Date: 2009
Source: Lu, W.,Ng, H.T.,Lee, W.S. (2009). Natural language generation with tree conditional random fields. EMNLP 2009 - Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: A Meeting of SIGDAT, a Special Interest Group of ACL, Held in Conjunction with ACL-IJCNLP 2009 : 400-409. ScholarBank@NUS Repository.
Abstract: This paper presents an effective method for generating natural language sentences from their underlying meaning representations. The method is built on top of a hybrid tree representation that jointly encodes both the meaning representation as well as the natural language in a tree structure. By using a tree conditional random field on top of the hybrid tree representation, we are able to explicitly model phrase-level dependencies amongst neighboring natural language phrases and meaning representation components in a simple and natural way. We show that the additional dependencies captured by the tree conditional random field allows it to perform better than directly inverting a previously developed hybrid tree semantic parser. Furthermore, we demonstrate that the model performs better than a previous state-of-the-art natural language generation model. Experiments are performed on two benchmark corpora with standard automatic evaluation metrics. © 2009 ACL and AFNLP.
Source Title: EMNLP 2009 - Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: A Meeting of SIGDAT, a Special Interest Group of ACL, Held in Conjunction with ACL-IJCNLP 2009
URI: http://scholarbank.nus.edu.sg/handle/10635/40600
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

56
checked on Dec 9, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.