A Tree-to-Sequence Model for Neural NLG in Task-Oriented Dialog

Jinfeng Rao, Kartikeya Upasani, Anusha Balakrishnan, Michael White, Anuj Kumar, Rajen Subba


Abstract
Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Sequence-to-sequence models on flat meaning representations (MR) have been dominant in this task, for example in the E2E NLG Challenge. Previous work has shown that a tree-structured MR can improve the model for better discourse-level structuring and sentence-level planning. In this work, we propose a tree-to-sequence model that uses a tree-LSTM encoder to leverage the tree structures in the input MR, and further enhance the decoding by a structure-enhanced attention mechanism. In addition, we explore combining these enhancements with constrained decoding to improve semantic correctness. Our experiments not only show significant improvements over standard seq2seq baselines, but also is more data-efficient and generalizes better to hard scenarios.
Anthology ID:
W19-8611
Volume:
Proceedings of the 12th International Conference on Natural Language Generation
Month:
October–November
Year:
2019
Address:
Tokyo, Japan
Editors:
Kees van Deemter, Chenghua Lin, Hiroya Takamura
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
95–100
Language:
URL:
https://aclanthology.org/W19-8611
DOI:
10.18653/v1/W19-8611
Bibkey:
Cite (ACL):
Jinfeng Rao, Kartikeya Upasani, Anusha Balakrishnan, Michael White, Anuj Kumar, and Rajen Subba. 2019. A Tree-to-Sequence Model for Neural NLG in Task-Oriented Dialog. In Proceedings of the 12th International Conference on Natural Language Generation, pages 95–100, Tokyo, Japan. Association for Computational Linguistics.
Cite (Informal):
A Tree-to-Sequence Model for Neural NLG in Task-Oriented Dialog (Rao et al., INLG 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/W19-8611.pdf