PaperPersiChat: Scientific Paper Discussion Chatbot using Transformers and Discourse Flow Management

Alexander Chernyavskiy, Max Bregeda, Maria Nikiforova


Abstract
The rate of scientific publications is increasing exponentially, necessitating a significant investment of time in order to read and comprehend the most important articles. While ancillary services exist to facilitate this process, they are typically closed-model and paid services or have limited capabilities. In this paper, we present PaperPersiChat, an open chatbot-system designed for the discussion of scientific papers. This system supports summarization and question-answering modes within a single end-to-end chatbot pipeline, which is guided by discourse analysis. To expedite the development of similar systems, we also release the gathered dataset, which has no publicly available analogues.
Anthology ID:
2023.sigdial-1.54
Volume:
Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2023
Address:
Prague, Czechia
Editors:
Svetlana Stoyanchev, Shafiq Joty, David Schlangen, Ondrej Dusek, Casey Kennington, Malihe Alikhani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
584–587
Language:
URL:
https://aclanthology.org/2023.sigdial-1.54
DOI:
10.18653/v1/2023.sigdial-1.54
Bibkey:
Cite (ACL):
Alexander Chernyavskiy, Max Bregeda, and Maria Nikiforova. 2023. PaperPersiChat: Scientific Paper Discussion Chatbot using Transformers and Discourse Flow Management. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 584–587, Prague, Czechia. Association for Computational Linguistics.
Cite (Informal):
PaperPersiChat: Scientific Paper Discussion Chatbot using Transformers and Discourse Flow Management (Chernyavskiy et al., SIGDIAL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.sigdial-1.54.pdf