Pinned Repositories
C-3MA
Scripts for Tartu Neural MT systems for WMT 17
C5-Syntactic-Analyser
php & javascript conll format dependency parser
chunker
A sentence chunker PHP class + visualizer for Berkeley Parser parse trees
ChunkMT
Combining machine translated sentence chunks from multiple MT systems
ConfidenceThroughAttention
Confidence Through Attention
MWE-Tools
A set of useful tools for use with multiword expression extraction from parallel corpora for Moses statistical machine translation system
parallel-corpora-tools
Tools for filtering and cleaning parallel and monolingual corpora for machine translation and other natural language processing tasks.
SoftAlignments
Neural macine translation soft alignment visualisations for web and command line
TweetTool
A tool for collecting and analyzing tweets
TwitEdiens
Tvītu par ēšanu vākšana
M4t1ss's Repositories
M4t1ss/SoftAlignments
Neural macine translation soft alignment visualisations for web and command line
M4t1ss/parallel-corpora-tools
Tools for filtering and cleaning parallel and monolingual corpora for machine translation and other natural language processing tasks.
M4t1ss/MWE-Tools
A set of useful tools for use with multiword expression extraction from parallel corpora for Moses statistical machine translation system
M4t1ss/ConfidenceThroughAttention
Confidence Through Attention
M4t1ss/TwitEdiens
Tvītu par ēšanu vākšana
M4t1ss/C-3MA
Scripts for Tartu Neural MT systems for WMT 17
M4t1ss/google_home_window
Open windows using a Raspberry Pi controlled by Google Home
M4t1ss/instruct-ner-mt-t5
M4t1ss/Multi-System-Hybrid-Translator
A hybrid machine translation solution that employs a language model and online translation APIs
M4t1ss/vardulis
Vārdu minēšanas spēle latviešu valodā
M4t1ss/bashrc
Useful bits to add to .bashrc
M4t1ss/datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
M4t1ss/K-Translate
Interactive Machine Translation Combination
M4t1ss/Latvian-food-NER-corpus
M4t1ss/Latvian-Twitter-Eater-Corpus
The Latvian Twitter Eater Corpus (LTEC), manually annotated sub-corpora, and processing tools.
M4t1ss/Latvian-Twitter-Eater-Corpus-Processing
Scripts for Processing the Latvian Twitter Eater Corpus
M4t1ss/LatvianStemmer
A word stemming algorithm for Latvian implemented in Python
M4t1ss/marian
Fast Neural Machine Translation in C++
M4t1ss/MT-EQuAl
a Toolkit for Manual Assessment of Machine Translation Output
M4t1ss/NMTInspector
Tools to inspect hidden representation of NMT
M4t1ss/OpenNMT
Open-Source Neural Machine Translation in Torch
M4t1ss/Opus-MT
Open neural machine translation models and web services
M4t1ss/phirehose
PHP interface to Twitter Streaming API
M4t1ss/sentiment-analysis-toolkit
Sentiment Analysis Toolkit
M4t1ss/SentimentAnalyserLVTwitter
Scripts for training and predicting sentiments of Latvian tweets. "Pretraining and Fine-Tuning Strategies for Sentiment Analysis of Latvian Tweets 2020"
M4t1ss/text-image-relationship
Text-Image Relationships (ACL 2019)
M4t1ss/Touchfolio
Free responsive portfolio WordPress theme with touch navigation
M4t1ss/TwEater
A Python Bot for Scraping Conversations from Twitter
M4t1ss/wmt17-website
Website for WMT17 - Second Conference in Machine Translation
M4t1ss/worldcuisines
WorldCuisines is an extensive multilingual and multicultural benchmark that spans 30 languages, covering a wide array of global cuisines.