@inproceedings{L16-1171,
 abstract = {This paper discusses the internal structure of complex Esperanto words (CWs). Using a morphological analyzer, possible affixation and compounding is checked for over 50,000 Esperanto lexemes against a list of 17,000 root words. Morpheme boundaries in the resulting analyses were then checked manually, creating a CW dictionary of 28,000 words, representing 56.4\% of the lexicon, or 19.4\% of corpus tokens. The error percentage of the EspGram morphological analyzer for new corpus CWs was 4.3\% for types and 6.4\% for tokens, with a recall of almost 100\%, and wrong/spurious boundaries being more common than missing ones. For pedagogical purposes a morpheme frequency dictionary was constructed for a 16 million word corpus, confirming the importance of agglutinative derivational morphemes in the Esperanto lexicon. Finally, as a means to reduce the morphological ambiguity of CWs, we provide POS likelihoods for Esperanto suffixes.
},
 address = {Portorož, Slovenia},
 author = {Eckhard Bick},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {1075--1078},
 publisher = {European Language Resources Association (ELRA)},
 title = {A Morphological Lexicon of Esperanto with Morpheme Frequencies},
 url = {https://www.aclweb.org/anthology/L16-1171},
 year = {2016}
}