Leveraging Multilingual Descriptions for Link Prediction: Initial Experiments

Proceedings of the ISWC 2020 Demos and Industry Tracks: From Novel Ideas to Industrial Practice, co-located with 19th International Semantic Web Conference (ISWC 2020)

Gesese, Genet Asefa and Hoppe, Fabian and Alam, Mehwish and Sack, Harald

In most Knowledge Graphs (KGs), textual descriptions of entities are provided in multiple natural languages. Additional information that is not explicitly represented in the structured part of the KG might be available in these textual descriptions. Link prediction models which make use of entity descriptions usually consider only one language. However, descriptions given in multiple languages may provide complementary information which should be taken into consideration for the tasks such as link prediction. In this poster paper, the benefits of multilingual embeddings for incorporating multilingual entity descriptions into the task of link prediction in KGs are investigated.

@inproceedings{gesese_leveraging_2020,
  title = {Leveraging {Multilingual} {Descriptions} for {Link} {Prediction}: {Initial} {Experiments}},
  booktitle = {Proceedings of the {ISWC} 2020 {Demos} and {Industry} {Tracks}: {From} {Novel} {Ideas} to {Industrial} {Practice}, co-located with 19th {International} {Semantic} {Web} {Conference} ({ISWC} 2020)},
  author = {Gesese, Genet Asefa and Hoppe, Fabian and Alam, Mehwish and Sack, Harald},
  year = {2020}
}