.png){kind=icon}
返回
Reference Knowledgeable Network for Machine Reading Comprehension
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2022.3164219.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multi-choice Machine Reading Comprehension (MRC) as a challenge requires models to select the most appropriate answer from a set of candidates with a given passage and question. Most of the existing researches focus on the modeling of specific tasks or complex networks, without explicitly referring to relevant and credible external knowledge sources, which are supposed to greatly make up for the deficiency of the given passage. Thus we propose a novel reference-based knowledge enhancement model called Reference Knowledgeable Network (RekNet), which simulates human reading strategies to refine critical information from the passage and quote explicit knowledge in necessity. In detail, RekNet refines fine-grained critical information and defines it as Reference Span, then quotes explicit knowledge quadruples by the co-occurrence information of Reference Span and candidates. The proposed RekNet is evaluated on three multi-choice MRC benchmarks: RACE, DREAM and Cosmos QA, obtaining consistent and remarkable performance improvement with observable statistical significance level over strong baselines. Our code is available at https://github.com/Yilin1111/RekNet.
Keyword:
Task analysis
Speech processing
Context modeling
Information retrieval
Data mining
Knowledge engineering
Benchmark testing
Natural language processing
machine reading comprehension
knowledge enhancement
reference extraction
reading strategy
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Gastrocnemius and soleus muscle length, velocity, and EMG responses to changes in pedalling cadence
PREAI
分享收藏
分享收藏Chloroplast pH values and buffer capacities in darkened leaves as revealed by CO2 solubilization in vivo.png)
Planta
PlantaIF0
PREAI
分享收藏分享收藏
查看更多内容