Structural Constraints and Natural Language Inference for End-to-End Flowchart Grounded Dialog Response Generation

Dinesh Raghu, Suraj Joshi, Sachindra Joshi, Mausam -

Abstract
Flowchart grounded dialog systems converse with users by following a given flowchart and a corpus of FAQs. The existing state-of-the-art approach (Raghu et al, 2021) for learning such a dialog system, named FLONET, has two main limitations. (1) It uses a Retrieval Augmented Generation (RAG) framework which represents a flowchart as a bag of nodes. By doing so, it loses the connectivity structure between nodes that can aid in better response generation. (2) Typically dialogs progress with the agent asking polar (Y/N) questions, but users often respond indirectly without the explicit use of polar words. In such cases, it fails to understand the correct polarity of the answer. To overcome these issues, we propose Structure-Aware FLONET (SA-FLONET) which infuses structural constraints derived from the connectivity structure of flowcharts into the RAG framework. It uses natural language inference to better predict the polarity of indirect Y/N answers. We find that SA-FLONET outperforms FLONET, with a success rate improvement of 68% and 123% in flowchart grounded response generation and zero-shot flowchart grounded response generation tasks respectively.
Anthology ID:
2022.emnlp-main.739
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10763–10774
Language:
URL:
https://aclanthology.org/2022.emnlp-main.739
DOI:
10.18653/v1/2022.emnlp-main.739
Bibkey:
Cite (ACL):
Dinesh Raghu, Suraj Joshi, Sachindra Joshi, and Mausam -. 2022. Structural Constraints and Natural Language Inference for End-to-End Flowchart Grounded Dialog Response Generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10763–10774, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Structural Constraints and Natural Language Inference for End-to-End Flowchart Grounded Dialog Response Generation (Raghu et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2022.emnlp-main.739.pdf
PDF Search