no code implementations • EMNLP 2021 • Xinmeng Li, Qian Li, Wansen Wu, Quanjun Yin
Recently, the focus of dialogue state tracking has expanded from single domain to multiple domains.
no code implementations • 25 Mar 2022 • Xinmeng Li, Hao Zhu, Li-Ping Liu, Soha Hassoun
We show that annotation performance, for ESP and other models, is a strong function of the number of molecules in the candidate set and their similarity to the target molecule.
1 code implementation • 28 Sep 2021 • Xinmeng Li, Li-Ping Liu, Soha Hassoun
We show that each of our auxiliary tasks boosts learning of the embedding vectors, and that contrastive learning using Boost-RS outperforms attribute concatenation and multi-label learning.
no code implementations • 26 Aug 2021 • Wansen Wu, Tao Chang, Xinmeng Li
This paper provides a comprehensive survey and an insightful taxonomy of these tasks based on the different characteristics of language instructions in these tasks.
no code implementations • 3 Aug 2021 • Xinmeng Li, Wansen Wu, Long Qin, Quanjun Yin
Evaluating the quality of a dialogue system is an understudied problem.
no code implementations • 27 Apr 2021 • Xinmeng Li, Mamoun Alazab, Qian Li, Keping Yu, Quanjun Yin
We evaluate QA2MN on PathQuestion and WorldCup2014, two representative datasets for complex multi-hop question answering.