Combining Language and Graph Models for Semi-structured Information Extraction on the Web

arXiv:2402.14129v1 Announce Type: cross
Abstract: Relation extraction is an efficient way of mining the extraordinary wealth of human knowledge on the Web. Existing methods rely on domain-specific training data or produce noisy outputs. We focus here on extracting targeted relations from semi-structured web pages given only a short description of the relation. We present GraphScholarBERT, an open-domain information extraction method based on a joint graph and language model structure. GraphScholarBERT can generalize to previously unseen domains without additional data or …

abstract arxiv cs.cl cs.ir data domain extraction focus graph human information information extraction knowledge language mining relations training training data type wealth web