WueDevils at SemEval-2022 Task 8: Multilingual News Article Similarity via Pair-Wise Sentence Similarity Matrices
2022-07-01SemEval (NAACL) 2022Unverified0· sign in to hype
Dirk Wangsadirdja, Felix Heinickel, Simon Trapp, Albin Zehe, Konstantin Kobs, Andreas Hotho
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
We present a system that creates pair-wise cosine and arccosine sentence similarity matrices using multilingual sentence embeddings obtained from pre-trained SBERT and Universal Sentence Encoder (USE) models respectively. For each news article sentence, it searches the most similar sentence from the other article and computes an average score. Further, a convolutional neural network calculates a total similarity score for the article pairs on these matrices. Finally, a random forest regressor merges the previous results to a final score that can optionally be extended with a publishing date score.