no code implementations • 29 Feb 2024 • Hongbang Yuan, Pengfei Cao, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao
Large Language Models (LLMs) have shown impressive capabilities but still suffer from the issue of hallucinations.
no code implementations • 28 Feb 2024 • Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao
Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT).
no code implementations • 13 Jan 2022 • Chao Zhao, Daojian Zeng, Lu Xu, Jianhua Dai
Document-level Relation Extraction (DRE) aims to recognize the relations between two entities.
Ranked #5 on Relation Extraction on CDR
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan, Heng Ji, Daojian Zeng, Fei Cheng, Daisuke Kawahara, Sadao Kurohashi
We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets.
2 code implementations • 24 Nov 2019 • Daojian Zeng, Ranran Haoran Zhang, Qianying Liu
The model is extremely weak at differing the head and tail entity, resulting in inaccurate entity extraction.
Ranked #12 on Relation Extraction on WebNLG
no code implementations • IJCNLP 2019 • Xiangrong Zeng, Shizhu He, Daojian Zeng, Kang Liu, Shengping Liu, Jun Zhao
Existing works didn{'}t consider the extraction order of relational facts in a sentence.
1 code implementation • ACL 2018 • Xiangrong Zeng, Daojian Zeng, Shizhu He, Kang Liu, Jun Zhao
The relational facts in sentences are often complicated.
Ranked #12 on Relation Extraction on NYT11-HRL