Automatic training of lemmatization rules that handle morphological changes in pre-, in- and suffixes alike

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


We propose a method to automatically train lemmatization rules that handle prefix, infix and suffix changes to generate the lemma from the full form of a word. We explain how the lemmatization rules are created and how the lemmatizer works. We trained this lemmatizer on Danish, Dutch, English, German, Greek, Icelandic, Norwegian, Polish, Slovene and
Swedish full form-lemma pairs respectively.
We obtained significant improvements of 24 percent for Polish, 2.3 percent for Dutch, 1.5 percent for English, 1.2 percent for German and 1.0 percent for Swedish compared to plain suffix lemmatization using a suffix-only lemmatizer.
Icelandic deteriorated with 1.9 percent. We also made an observation regarding the number of produced lemmatization rules as a function of the number of training pairs.
Original languageEnglish
Title of host publicationProceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP
Number of pages9
PublisherAssociation for Computational Linguistics
Publication date2009
ISBN (Print)978-1-932432-61-9
ISBN (Electronic)1-932432-61-2
Publication statusPublished - 2009
EventACL-IJCNLP 2009 - Singapore, Singapore
Duration: 2 Aug 20097 Aug 2009
Conference number: 47


ConferenceACL-IJCNLP 2009

Number of downloads are based on statistics from Google Scholar and

No data available

ID: 14093025