Applying the Constraint Grammar Parser of English to the Helsinki Corpus1
Merja Kytö · 1997
The international break-through of the ENGCG Parser, or the Constraint Grammar Parser of English (Karlsson et al. 1995), as a system suitable for analysing Present-day English, opened the field for applications capable of dealing with regional, diachronic and other varieties of English. Using the parser on historical data is an obvious extension. To what extent should one teach the parser to cope with language from earlier periods? To what extent does Present-day English differ from early English and to what extent is it possible to formalize this difference for the parser? In this pilot study we will report some recent findings, after applying the ENGCG parser to a number of texts from the Early Modern English section of the Helsinki Corpus of English Texts. We first explain how the parser works and its relevance to our study. We then introduce our data, explain how we carried out the ENGCG analysis, and discuss the parser’s difficulties in dealing with early English. Finally, we evaluate our experiment and the ENGCG parser’s potential in diachronic multipurpose corpora such as the Helsinki Corpus.