Mārcis Pinnis's repositories
mp-aligner
The MPAligner is a toolkit for cross-lingual term mapping in term tagged documents. The toolkit is specifically designed to address term mapping between European languages. The source code has been released.
nlp-example
The code here provides a simple example of some NLP tasks for plain text processing for English and Latvian
dict-filtering
Giza++ dictionary filtering tool and (initial) transliteration dictionary acquisition tool
latvian-tweet-corpus
The Latvian Tweet Corpus and Twitter Monitor
citation-graph-builder
Semantic Scholar citation graph builder - allows to build a graph that includes all citations and (if specified) also references for all papers of an author given the Semantic Scholar author ID.
acl-anthology
Data and software for building the ACL Anthology.
cyrillic-transliteration
Transliterate Cyrillic script to Latin script and vice versa.
mosesdecoder
Moses, the machine translation system
self-adaptive-marian-test-scripts
Scripts and test data for the self-adaptive NMT functionality in Marian
Twitterizer
Twitterizer is a .NET class library that provides an easy-to-use interface for the Twitter web api. It is written for developers. It's features are easy to discover and follow a consistent design pattern.