lingsoft/lv-morph repository overview

ELG compatible⁠ Flask based REST API for Morphological Analyzer for Latvian Language⁠ (v. 2.2.5)

⁠Deploying the service

docker run -d -p <port>:8000 --init lv-morph:<tagname>

⁠Usage

See instructions from GitHub⁠.

curl -H 'Content-Type: application/json' -d '{"type": "text", "content": "roku"}' http://localhost:8000/process/word_analysis

curl -H 'Content-Type: application/json' -d '{"type": "text", "content": "rakt"}' http://localhost:8000/process/wordforms

The word_analysis endpoint takes a single word as an input and outputs all possible morphological readings of this word. Each reading is given:

1. a morphological tag (e.g. 'ncmsa1'), whose first letter denotes the part of speech (e.g. 'n' – noun),
2. a set of features, partly depending on the part of speech: 'Pamatforma' (lemma), 'Skaitlis' (number), 'Locījums' (case), 'Dzimte' (gender), etc.

The wordforms endpoint takes a single word as an input and outputs all morphological forms of this word, their morphological tags and features.

⁠Authors

⁠Original authors

The analyzer is licensed under the GNU General Public Licence⁠ and was developed by Pēteris Paikens from the University of Latvia, Institute of Mathematics and Computer science.

⁠ELG API integration

The ELG API was developed by Lingsoft⁠ as part of the Connecting Europe Facility (CEF) project Microservices at your service: bridging the gap between NLP research and industry⁠.

⁠License

GNU General Public License v3.0