Logo Lanfrica

JosephSefara/AfricanWordNet

Domain:

natural language processing

Record type:

software
Creator:
Jos
Host:
AfricanWordNet: Implementation of WordNets for African languages. Citation paper "Practical Approach on Implementation of WordNets for South African Languages" aclweb.org # AfricanWordNet: Implementation of WordNets for African languages This library extends OMW implemented in NLTK to add support for the following African languages. - Sepedi (nso) - Xitsonga (tsn) - Tshivenda (ven) - isiZulu (zul) - isiXhosa (xho) ) ## Requirements * Python 3 * NLTK ## Installation - From Pypi - ```pip install africanwordnet``` - From source - ```pip install github.com``` ## Citation Paper ``` @inproceedings{sefara2021practical, title={Practical Approach on Implementation of WordNets for South African Languages}, author={Sefara, Tshephisho and Mokgonyane, Tumisho and Marivate, Vukosi}, booktitle={Proceedings of the 11th Global Wordnet Conference}, pages={20--25}, year={2021}, } ``` ## Usage ```python >>> from nltk.corpus import wordnet as wn >>> import africanwordnet >>> wn.langs() ['nso', 'tsn', 'ven', 'zul', 'xho'] ``` ### Setswana WordNet ```python >>> wn.synsets('phêpafatsa',lang=('tsn')) [Synset('scavenge.v.04'), Synset('tidy.v.01'), Synset('refine.v.04'), Synset('refine.v.03'), Synset('purify.v.01'), Synset('purge.v.04'), Synset('purify.v.02'), Synset('clean.v.08'), Synset('clean.v.01'), Synset('houseclean.v.01')] >>> wn.lemmas('phêpafatsa', lang='tsn') [Lemma('scavenge.v.04.phêpafatsa'), Lemma('tidy.v.01.phêpafatsa'), Lemma('refine.v.04.phêpafatsa'), Lemma('refine.v.03.phêpafatsa'), Lemma('purify.v.01.phêpafatsa'), Lemma('purge.v.04.phêpafatsa'), Lemma('purify.v.02.phêpafatsa'), Lemma('clean.v.08.phêpafatsa'), Lemma('clean.v.01.phêpafatsa'), Lemma('houseclean.v.01.phêpafatsa')] >>> wn.synset('purify.v.01').lemma_names('tsn') ['phêpafatsa'] >>> lemma = wn.lemma('purify.v.01.phêpafatsa', lang='tsn') >>> whole_lemma.lang() 'tsn' ``` ### Sepedi WordNet ```python >>> wn.synsets('taelo',lang=('nso')) [Synset('call.n.12'), Synset('mandate.n.03'), Synset('command.n.01'), Synset('order.n.01'), Synset('commission.n.06'), Synset('commandment.n.01'), Synset('directive.n.01'), Synset('injunction.n.01' …