no code implementations • 26 May 2023 • Tao Yang, Zhichao Xu, Zhenduo Wang, Qingyao Ai
However, we find that most existing fair ranking methods adopt greedy algorithms that only optimize rankings for the next immediate session or request.
no code implementations • 17 Apr 2023 • Zhenduo Wang, Zhichao Xu, Qingyao Ai
In this paper, we propose a reward-free conversation policy imitation learning framework, which can train a conversation policy without annotated conversation data or manually designed rewards.
no code implementations • 17 Apr 2023 • Zhenduo Wang, Zhichao Xu, Qingyao Ai, Vivek Srikumar
Our goal is to supplement existing work with an insightful hand-analysis of unsolved challenges by the baseline and propose our solutions.
no code implementations • 30 Jan 2023 • Zhenduo Wang, Yuancheng Tu, Corby Rosset, Nick Craswell, Ming Wu, Qingyao Ai
In this work, we innovatively explore generating clarifying questions in a zero-shot setting to overcome the cold start problem and we propose a constrained clarifying question generation system which uses both question templates and query facets to guide the effective and precise question generation.
2 code implementations • 18 Dec 2022 • Tao Yang, Zhichao Xu, Zhenduo Wang, Anh Tran, Qingyao Ai
In MCFair, we first develop a ranking objective that includes uncertainty, fairness, and user utility.
1 code implementation • 1 Jan 2022 • Zhenduo Wang, Qingyao Ai
These works assume asking clarifying questions is a safe alternative to retrieving results.
1 code implementation • 15 Jan 2021 • Zhenduo Wang, Qingyao Ai
In this work, we propose a risk-aware conversational search agent model to balance the risk of answering user's query and asking clarifying questions.
1 code implementation • 13 Jul 2020 • Zhenduo Wang, Yijie Wang, Biao Wu
We propose a physical distance between two quantum states.
Quantum Physics
no code implementations • SEMEVAL 2018 • Kevin Swanberg, Madiha Mirza, Ted Pedersen, Zhenduo Wang
This paper describes the ALANIS system that participated in Task 3 of SemEval-2018.
no code implementations • SEMEVAL 2018 • Zhenduo Wang, Ted Pedersen
This paper describes the UMDSub system that participated in Task 2 of SemEval-2018.