Breaking the HISCO Barrier: Automatic Occupational Standardization with OccCANINE
This tool addresses a tedious and error-prone task for researchers in economics, economic history, and related disciplines, though it is incremental as it finetunes an existing language model.
The paper tackles the problem of manually classifying occupational descriptions into the HISCO system, which is error-prone and time-consuming, by introducing OccCANINE, a tool that automates this process with accuracy, recall, and precision above 90%, reducing processing time from days to seconds or minutes.
This paper introduces a new tool, OccCANINE, to automatically transform occupational descriptions into the HISCO classification system. The manual work involved in processing and classifying occupational descriptions is error-prone, tedious, and time-consuming. We finetune a preexisting language model (CANINE) to do this automatically, thereby performing in seconds and minutes what previously took days and weeks. The model is trained on 14 million pairs of occupational descriptions and HISCO codes in 13 different languages contributed by 22 different sources. Our approach is shown to have accuracy, recall, and precision above 90 percent. Our tool breaks the metaphorical HISCO barrier and makes this data readily available for analysis of occupational structures with broad applicability in economics, economic history, and various related disciplines.