Abstract | ||
---|---|---|
Intelligent systems require common sense, but automatically extracting this knowledge from text can be difficult. We propose and assess methods for extracting one type of commonsense knowledge, object-property comparisons, from pre-trained embeddings. In experiments, we show that our approach exceeds the accuracy of previous work but requires substantially less hand-annotated knowledge. Further, we show that an active learning approach that synthesizes common-sense queries can boost accuracy. |
Year | Venue | DocType |
---|---|---|
2018 | PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 | Conference |
Volume | Citations | PageRank |
P18-2 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yiben Yang | 1 | 0 | 1.35 |
Lawrence A. Birnbaum | 2 | 7 | 2.60 |
Ji-Ping Wang | 3 | 3 | 0.75 |
Doug Downey | 4 | 1908 | 119.79 |