GateNLP-UShef at SemEval-2022 Task 8: Entity-Enriched Siamese Transformer for Multilingual News Article Similarity. (arXiv:2205.15812v2 [cs.CL] UPDATED)

This paper describes the second-placed system on the leaderboard of
SemEval-2022 Task 8: Multilingual News Article Similarity. We propose an
entity-enriched Siamese Transformer which computes news article similarity
based on different sub-dimensions, such as the shared narrative, entities,
location and time of the event discussed in the news article. Our system
exploits a Siamese network architecture using a Transformer encoder to learn
document-level representations for the purpose of capturing the narrative
together with the auxiliary entity-based features extracted from the …

article arxiv news transformer