Nhat Tran
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nhat Tran has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Diane Litman
Department of Computer Science Learning Research & Development Center University of Pittsburgh 15260 Pittsburgh Pennsylvania USA
3 shared publications - Benjamin Pierce
University of Pittsburgh
1 shared publication - Lindsay Clare Matsumura
University of Pittsburgh
1 shared publication - Richard Correnti
Learning Research and Development Center University of Pittsburgh RAND Corporation Pittsburgh PA USA
1 shared publication
Latest Publications
- Open Access
Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue
Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant knowledge sentences. In this work, we propose an approach that utilizes topic modeling on the knowledge base to further improve retrieval accuracy and as a result, improve response generation. Additionally, we experiment with a large language model, ChatGPT, to take advantage of the improved retrieval performance to further improve the generation results. Experimental results on two datasets show that our approach can increase retrieval and generation performance. The results also indicate that ChatGPT is a better response generator for knowledge-grounded dialogue when relevant knowledge is provided.
Open AccessEnhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue
Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant knowledge sentences. In this work, we propose an approach that utilizes topic modeling on the knowledge base to further improve retrieval accuracy and as a result, improve response generation. Additionally, we experiment with a large language model, ChatGPT, to take advantage of the improved retrieval performance to further improve the generation results. Experimental results on two datasets show that our approach can increase retrieval and generation performance. The results also indicate that ChatGPT is a better response generator for knowledge-grounded dialogue when relevant knowledge is provided.
- 30 June 2023
- Published by Springer Nature
- p. 490-496
Utilizing Natural Language Processing for Automated Assessment of Classroom Discussion
- 30 June 2023
- Published by Springer Nature
- p. 490-496
Utilizing Natural Language Processing for Automated Assessment of Classroom Discussion
- Open Access
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 368-375
Getting Better Dialogue Context for Knowledge Identification by Leveraging Document-level Topic Shift
Nhat Tran, Diane Litman. Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2022.
- 1 January 2022
- Published by Association for Computational Linguistics (ACL)
- p. 368-375
Open AccessGetting Better Dialogue Context for Knowledge Identification by Leveraging Document-level Topic Shift
Nhat Tran, Diane Litman. Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2022.