no code implementations • SIGDIAL (ACL) 2022 • Nhat Tran, Diane Litman
To build a goal-oriented dialogue system that can generate responses given a knowledge base, identifying the relevant pieces of information to be grounded in is vital.
no code implementations • EMNLP (ArgMining) 2021 • Nhat Tran, Diane Litman
We utilize multi-task learning to improve argument mining in persuasive online discussions, in which both micro-level and macro-level argumentation must be taken into consideration.
1 code implementation • 7 May 2024 • Nhat Tran, Diane Litman
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.
no code implementations • 21 Jun 2023 • Nhat Tran, Benjamin Pierce, Diane Litman, Richard Correnti, Lindsay Clare Matsumura
Rigorous and interactive class discussions that support students to engage in high-level thinking and reasoning are essential to learning and are a central component of most teaching interventions.
no code implementations • 17 Sep 2020 • Nhat Tran, Jean Gao
Additionally, by successively stacking layer representations, the learned node embedding offers a more interpretable aggregation scheme for nodes of different types at different neighborhood ranges.
no code implementations • 17 Jun 2019 • Nhat Tran, Jean Gao
We proposed a novel deep learning-based framework, rna2rna, which learns from RNA sequences to produce a low-dimensional embedding that preserves the proximities in both the interactions topology and the functional affinity topology.