Abstract | ||
---|---|---|
Commonsense knowledge acquisition is one of the fundamental issues in the implementation of human-level AI. However, commonsense is difficult to obtain, because it is a human consensus and rarely explicitly appears in texts or other data. In this paper, we focus on the automatic acquisition of a typical kind of implicit verb-oriented commonsense knowledge (e.g., "person eats food"), which is the concept level knowledge of verb phrases. For this purpose, we propose a knowledge-driven approach to mine verb-oriented commonsense knowledge from verb phrases with the help of taxonomy. First, we design an entropy-based filter to cope with noisy input verb phrases. Then, we propose a joint model based on minimum description length and a neural language model to generate verb-oriented commonsense knowledge. We conduct extensive experiments to show that our solution is more effective to mine verb-oriented commonsense knowledge than competitors, and finally, we harvest 18K verb oriented commonsense knowledge. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICDE48307.2020.00181 | 2020 IEEE 36TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2020) |
Keywords | DocType | ISSN |
commonsense knowledge, verb phrases, probabilistic taxonomy | Conference | 1084-4627 |
Citations | PageRank | References |
1 | 0.36 | 0 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jingping Liu | 1 | 3 | 3.43 |
Yuanfu Zhou | 2 | 1 | 0.36 |
Dan Wu | 3 | 1 | 0.36 |
Chao Wang | 4 | 2 | 1.72 |
Haiyun Jiang | 5 | 3 | 2.76 |
Sheng Zhang | 6 | 2 | 2.75 |
Bo Xu | 7 | 25 | 5.31 |
Yanghua Xiao | 8 | 482 | 54.90 |