@inproceedings{Percillier:2020a,
  title = {{{Lemmatising}} {{Verbs}} in {{Middle}} {{English}} {{Corpora}}: {{The}} {{Benefit}} of {{Enrichin}}g the {{Penn-Helsinki}} {{Parsed}} {{Corpus}} of {{Middle}} {{English}} 2 ({{PPCME2}}), the {{Parsed}} {{Corpus}} of {{Middle}} {{English}} {{Poetry}} ({{PCMEP}}), and {{A}} {{Parsed}} {{Linguistic}} {{Atlas}} of {{Early}} {{Middle}} {{English}} ({{PLAEME}})},
  booktitle = {Proceedings of the 12th Language Resources and Evaluation Conference},
  author = {Percillier, Michael and Trips, Carola},
  year = {2020},
  pages = {7170--7178},
  publisher = {{European Language Resources Association}},
  address = {{Marseille, France}},
  abstract = {This paper describes the lemmatisation of three annotated corpora of Middle English\textemdash the Penn-Helsinki Parsed Corpus of Middle English 2 (PPCME2), the Parsed Corpus of Middle English Poetry (PCMEP), and A Parsed Linguistic Atlas of Early Middle English (PLAEME) \textemdash{} which is a prerequisite for systematically investigating the argument structures of verbs of the given time. Creating this tool and enriching existing parsed corpora of Middle English is part of the project Borrowing of Argument Structure in Contact Situations (BASICS) which seeks to explain to which extent verbs copied from Old French had an impact on the grammar of Middle English. First, we lemmatised the PPCME2 by (1) creating an inventory of form-lemma correspondences linking forms in the PPCME2 to lemmas in the MED, and (2) inserting this lemma information into the corpus (precision: 94.85\%, recall: 98.92\%). Second, we enriched the PCMEP and PLAEME, which adopted the annotation format of the PPCME2, with verb lemmas to undertake studies that fill the well-known data gap in the subperiod (1250\textendash 1350) of the PPCME2. The case study of reflexives shows that with our method we gain much more reliable results in terms of diachrony, diatopy and contact-induced change.},
  file = {/Users/michaelpercillier/Literature/2020.lrec-1.886.pdf}
}