Abstract: Domain-specific named entity recognition on Computer Science (CS) scholarly articles is an information extraction task that is arguably more challenging and less studied than named entity recognition (NER) for the general domain. Given that significant progress has been made on NER, we believe that scholarly domain-specific NER will receive increasing attention in the NLP community. Nevertheless, progress on the task is currently hampered in part by its recency and the lack of standardized concept types for scientific entities/terms. This paper presents a survey of the current state of research on scholarly domain-specific NER with a focus on language resources; further, it creates a novel dataset and model for CS NER.
0 Replies
Loading