In this paper we explore the idea of using verb valency information to improve verb phrase extraction from historical text. As a case study, we perform experiments on Early Modern Swedish data, but the approach could easily be transferred to other languages and/or time periods as well. We show that by using verb valency information in a post-processing step to the verb phrase extraction system, it is possible to remove improbable complements extracted by the parser and insert probable complements not extracted by the parser, leading to an increase in both precision and recall for the extracted complements.
展开▼
