A comparative analysis of embedding models for patent similarity

arXiv:2403.16630v1 Announce Type: cross
Abstract: This paper makes two contributions to the field of text-based patent similarity. First, it compares the performance of different kinds of patent-specific pretrained embedding models, namely static word embeddings (such as word2vec and doc2vec models) and contextual word embeddings (such as transformers based models), on the task of patent similarity calculation. Second, it compares specifically the performance of Sentence Transformers (SBERT) architectures with different training phases on the patent similarity task. To assess the models' …

abstract analysis arxiv comparative analysis cs.cl cs.ir cs.lg embedding embedding models embeddings paper patent performance text transformers type word word2vec word embeddings