Journal article
On improving knowledge graph facilitated simple question answering system
Neural Computing & Applications, Vol.33, pp.10587-10596
2021
Abstract
Leveraging knowledge graph will benefit question answering tasks, as KG contains well-structured informative data. However, training knowledge graph-based simple question answering systems is known computationally expensive due to the complex predicate extraction and candidate pool generation. Moreover, the existing methods based on convolutional neural network (CNN) or recurrent neural network (RNN) overestimate the importance of predicate features thus reduce performance. To address these challenges, we propose a time-efficient and resource-effective framework. We use leaky n-gram to balance recall and candidate pool size in candidate pool generation. For predicate extraction, we propose a soft-histogram and self-attention (SHSA) module which serves the role of preserving the global information of questions via feature matrices. And this leads to reduce the RNN module as the simple feedforward network in predicate representation. We also designed a Hamming lower-bound label encoding algorithm to encode the label representations in lower dimensions. Experiments on benchmark datasets show that our method outperforms the competitive work for end-tasks and achieves better recall with a significantly pruned candidate space.
Details
- Title
- On improving knowledge graph facilitated simple question answering system
- Authors
- Xin Li (Corresponding Author) - Beijing Institute of TechnologyHongyu Zang (Author) - Beijing Institute of TechnologyXiaoyun Yu (Author) - Beijing Institute of TechnologyHao Wu (Author) - Beijing Institute of TechnologyZijian Zhang (Author) - Beijing Institute of TechnologyJiamou Liu (Author) - University of AucklandMingzhong Wang (Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
- Publication details
- Neural Computing & Applications, Vol.33, pp.10587-10596
- Publisher
- Springer UK
- DOI
- 10.1007/s00521-021-05762-9
- ISSN
- 1433-3058
- Organisation Unit
- University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering; USC Business School - Legacy
- Language
- English
- Record Identifier
- 99518307502621
- Output Type
- Journal article
Metrics
26 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- International collaboration
- Web Of Science research areas
- Computer Science, Artificial Intelligence
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites