1 code implementation • 13 Oct 2023 • Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin
Knowledge Base Question Answering (KBQA) aims to derive answers to natural language questions over large-scale knowledge bases (KBs), which are generally divided into two research components: knowledge retrieval and semantic parsing.
Ranked #1 on Knowledge Base Question Answering on WebQuestionsSP
2 code implementations • ACL 2019 • Haihong E, Peiqing Niu, Zhongfu Chen, Meina Song
The joint model for the two tasks is becoming a tendency in SLU.
Ranked #6 on Intent Detection on SNIPS
1 code implementation • 7 Dec 2023 • Jiawei Fan, Chao Li, Xiaolong Liu, Meina Song, Anbang Yao
In order to address this problem, we present Augmentation-free Dense Contrastive Knowledge Distillation (Af-DCD), a new contrastive distillation learning paradigm to train compact and accurate deep neural networks for semantic segmentation applications.
1 code implementation • ACL 2023 • Haoran Luo, Haihong E, Yuhao Yang, Yikai Guo, Mingzhi Sun, Tianyu Yao, Zichen Tang, Kaiyang Wan, Meina Song, Wei Lin
The global-level attention can model the graphical structure of HKG using hypergraph dual-attention layers, while the local-level attention can learn the sequential structure inside H-Facts via heterogeneous self-attention layers.
Ranked #1 on Link Prediction on Wikipeople
1 code implementation • 8 Oct 2023 • Haoran Luo, Haihong E, Yuhao Yang, Tianyu Yao, Yikai Guo, Zichen Tang, Wentai Zhang, Kaiyang Wan, Shiyao Peng, Meina Song, Wei Lin
To address these restrictions, we propose Text2NKG, a novel fine-grained n-ary relation extraction framework for n-ary relational knowledge graph construction.
Event-based N-ary Relaiton Extraction Hypergraph-based N-ary Relaiton Extraction +3
no code implementations • NAACL 2021 • Youri Xu, E Haihong, Meina Song, wenyu song, Xiaodong Lv, wang haotian, yang jinrui
Since RTFE learns each timestamp recursively, it can naturally transit to future timestamps.
no code implementations • 23 Dec 2021 • Haihong E, Jiawen He, Tianyi Hu, Lifei Wang, Lifei Yuan, Ruru Zhang, Meina Song
With the introduction of a priori knowledge of 10 lesion signs of input images into the KFWC, we aim to accelerate the KFWC by means of multi-label classification pre-training, to locate the decisive image features in the fine-grained disease classification task and therefore achieve better classification.