Projects per year
Abstract
In recent years, neural networks have achieved impressive performance on dialogue response generation. However, most of these models still suffer from some shortcomings, such as yielding uninformative responses and lacking explainable ability. This article proposes a Two-stage Dialogue Response Generation model (TSRG), which specifies a method to generate diverse and informative responses based on an interpretable procedure between stages. TSRG involves a two-stage framework that generates a candidate response first and then instantiates it as the final response. The positional information and a resident token are injected into the candidate response to stabilize the multi-stage framework, alleviating the shortcomings in the multi-stage framework. Additionally, TSRG allows adjusting and interpreting the interaction pattern between the two generation stages, making the generation response somewhat explainable and controllable. We evaluate the proposed model on three dialogue datasets that contain millions of single-turn message-response pairs between web users. The results show that, compared with the previous multi-stage dialogue generation models, TSRG can produce more diverse and informative responses and maintain fluency and relevance.
Original language | English |
---|---|
Article number | 3551869 |
Journal | ACM Transactions on Asian and Low-Resource Language Information Processing |
Volume | 22 |
Issue number | 3 |
DOIs | |
Publication status | Published - 10 Mar 2023 |
MoE publication type | A1 Journal article-refereed |
Keywords
- Asian language
- explainable text generation
- Natural language processing
- neural response generation
Fingerprint
Dive into the research topics of 'Toward Explainable Dialogue System Using Two-stage Response Generation'. Together they form a unique fingerprint.-
INTERVENE: International consortium for integrative genomics prediction
Kaski, S. (Principal investigator)
01/01/2021 → 31/12/2025
Project: EU: Framework programmes funding
-
DATALIT: Data Literacy for Responsible Decision-Making
Marttinen, P. (Principal investigator), Ji, S. (Project Member), Gröhn, T. (Project Member), Honkamaa, J. (Project Member), Kumar, Y. (Project Member), Pöllänen, A. (Project Member), Ojala, F. (Project Member), Raj, V. (Project Member) & Tiwari, P. (Project Member)
01/10/2020 → 30/09/2023
Project: Academy of Finland: Strategic research funding
-
-: Intelligent Crop Production: Data-integrative, Multi-task Learning Meets Crop Simulator
Mamitsuka, H. (Principal investigator), Nariman Zadeh, H. (Project Member), Strahl, J. (Project Member), Guvenc, B. (Project Member), Ji, S. (Project Member), Rissanen, S. (Project Member), Honkamaa, J. (Project Member), Pöllänen, A. (Project Member), Hiremath, S. (Project Member) & Ojala, F. (Project Member)
01/01/2018 → 31/12/2022
Project: Academy of Finland: Other research funding