1 code implementation • 5 Dec 2022 • Zhengbao Jiang, Luyu Gao, Jun Araki, Haibo Ding, Zhiruo Wang, Jamie Callan, Graham Neubig
Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents to generate answers.
Ranked #1 on Passage Retrieval on Natural Questions
no code implementations • COLING 2022 • Zhengbao Jiang, Jun Araki, Haibo Ding, Graham Neubig
In sum, these results demonstrate that multi-hop reasoning does not emerge naturally in generative QA models, but can be encouraged by advances in training or modeling techniques.
1 code implementation • ACL 2021 • Pei Chen, Haibo Ding, Jun Araki, Ruihong Huang
Named entity recognition (NER) is well studied for the general domain, and recent systems have achieved human-level performance for identifying common entity types.
2 code implementations • ACL 2021 • Jiacheng Li, Haibo Ding, Jingbo Shang, Julian McAuley, Zhe Feng
We study the problem of building entity tagging systems by using a few rules as weak supervision.
1 code implementation • EACL 2021 • Xinyan Zhao, Haibo Ding, Zhe Feng
Instead of using expensive manual annotations, researchers have proposed to train named entity recognition (NER) systems using heuristic labeling rules.
1 code implementation • 2 Dec 2020 • Zhengbao Jiang, Jun Araki, Haibo Ding, Graham Neubig
We examine this question from the point of view of calibration, the property of a probabilistic model's predicted probabilities actually being well correlated with the probabilities of correctness.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Haibo Ding, Zhe Feng
We study the problem of learning an event classifier from human needs category descriptions, which is challenging due to: (1) the use of highly abstract concepts in natural language descriptions, (2) the difficulty of choosing key concepts.
1 code implementation • EMNLP 2020 • Zhengbao Jiang, Antonios Anastasopoulos, Jun Araki, Haibo Ding, Graham Neubig
We further propose a code-switching-based method to improve the ability of multilingual LMs to access knowledge, and verify its effectiveness on several benchmark languages.
no code implementations • SEMEVAL 2019 • Haibo Ding, Ellen Riloff, Zhe Feng
Human Needs categories have been used to characterize the reason why an affective event is positive or negative.
no code implementations • NAACL 2018 • Haibo Ding, Ellen Riloff
We often talk about events that impact us positively or negatively.