%0 Conference Paper %1 Bary:2017:MLA:3078081.3078100 %A Bary, Corien %A Berck, Peter %A Hendrickx, Iris %B Proceedings of the 2Nd International Conference on Digital Access to Textual Cultural Heritage %C New York, NY, USA %D 2017 %I ACM %K digitalHumanities greek openPhilology %P 91--95 %R 10.1145/3078081.3078100 %T A Memory-Based Lemmatizer for Ancient Greek %U http://doi.acm.org/10.1145/3078081.3078100 %X In this paper we present the lemmatizer that we developed for Ancient Greek: GLEM. As far as we know, GLEM is the first publicly available lemmatizer for Ancient Greek that uses POS information to disambiguate and that also assigns output to unseen words, words that are not yet in the lexicon. As the basis for the lemmatizer we used an existing memory-based learning tool, Frog, that was originally developed for Dutch and that we converted to work for Ancient Greek. As the results of Frog on Ancient Greek were rather modest, we used Frog to create a smarter lemmatizer, GLEM, that uses a lexicon look up in addition to the memory-based tool Frog. We evaluate and compare the performance of GLEM against the Frog lemmatizer and the already existing CLTK lemmatizer and observe that GLEM achieves the highest accuracy of 93% on an unseen test corpus sample. GLEM's look up component overcomes the difficulty of a relative small training set in combination with a morphologically rich language, while the memory-based learning component enables GLEM to handle unknown words. %@ 978-1-4503-5265-9

@inproceedings{Bary:2017:MLA:3078081.3078100, abstract = {In this paper we present the lemmatizer that we developed for Ancient Greek: GLEM. As far as we know, GLEM is the first publicly available lemmatizer for Ancient Greek that uses POS information to disambiguate and that also assigns output to unseen words, words that are not yet in the lexicon. As the basis for the lemmatizer we used an existing memory-based learning tool, Frog, that was originally developed for Dutch and that we converted to work for Ancient Greek. As the results of Frog on Ancient Greek were rather modest, we used Frog to create a smarter lemmatizer, GLEM, that uses a lexicon look up in addition to the memory-based tool Frog. We evaluate and compare the performance of GLEM against the Frog lemmatizer and the already existing CLTK lemmatizer and observe that GLEM achieves the highest accuracy of 93% on an unseen test corpus sample. GLEM's look up component overcomes the difficulty of a relative small training set in combination with a morphologically rich language, while the memory-based learning component enables GLEM to handle unknown words.}, acmid = {3078100}, added-at = {2018-12-17T19:06:42.000+0100}, address = {New York, NY, USA}, author = {Bary, Corien and Berck, Peter and Hendrickx, Iris}, biburl = {https://www.bibsonomy.org/bibtex/23bf606de84cf7a8902cdcd2a3463d99b/filologanoga}, booktitle = {Proceedings of the 2Nd International Conference on Digital Access to Textual Cultural Heritage}, description = {A Memory-Based Lemmatizer for Ancient Greek}, doi = {10.1145/3078081.3078100}, interhash = {069fd40d137f22355fcc5fc81c66023d}, intrahash = {3bf606de84cf7a8902cdcd2a3463d99b}, isbn = {978-1-4503-5265-9}, keywords = {digitalHumanities greek openPhilology}, location = {G\öttingen, Germany}, numpages = {5}, pages = {91--95}, publisher = {ACM}, series = {DATeCH2017}, timestamp = {2018-12-17T19:06:42.000+0100}, title = {A Memory-Based Lemmatizer for Ancient Greek}, url = {http://doi.acm.org/10.1145/3078081.3078100}, year = 2017 }