Name
Abstract | ||
|---|---|---|
The knowledge graph(KG) composed of entities with their descriptions and attributes, and relationship between entities, is finding more and more application scenarios in various natural language processing tasks. In a typical knowledge graph like Wikidata, entities usually have a large number of attributes, but it is difficult to know which ones are important. The importance of attributes can be a valuable piece of information in various applications spanning from information retrieval to natural language generation. In this paper, we propose a general method of using external user generated text data to evaluate the relative importance of an entityu0027s attributes. To be more specific, we use the word/sub-word embedding techniques to match the external textual data back to entitiesu0027 attribute name and values and rank the attributes by their matching cohesiveness. To our best knowledge, this is the first work of applying vector based semantic matching to important attribute identification, and our method outperforms the previous traditional methods. We also apply the outcome of the detected important attributes to a language generation task; compared with previous generated text, the new method generates much more customized and informative messages. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Computation and Language | Natural language generation,Knowledge graph,Embedding,Computer science,Group cohesiveness,Natural language processing,Artificial intelligence,Semantic matching |
DocType | Volume | Citations |
Journal | abs/1810.05320 | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shengjie Sun | 1 | 0 | 1.01 |
| Dong Yang | 2 | 13 | 7.40 |
| Hongchun Zhang | 3 | 0 | 0.68 |
| Yanxu Chen | 4 | 0 | 0.34 |
| Chao Wei | 5 | 0 | 1.01 |
| Xiaonan Meng | 6 | 0 | 3.04 |
| Yi Hu | 7 | 111 | 11.89 |