Pinned Repositories
adobo-2021
Shared task on Automatic Detection of Borrowings 2021
mot
Multilingual Open Text
paranames
ParaNames: A multilingual resource for parallel names
seqscore
SeqScore: Scoring for named entity recognition and other sequence labeling tasks
Codeswitchador
Fast, simple identification of codeswitching in Tweets and other short messages.
CTFTools
Tools and documentation to help use CTF MEG/EEG Tools.
MORSEL
MORphological Sparsity Embiggens Learning: A simple unsupervised morphological learning model.
nyt-corpus-reader
A parser and MongoDB backed store for searching the New York Times Annotated Corpus (LDC2008T19)
ConstantineLignos's Repositories
ConstantineLignos/MORSEL
MORphological Sparsity Embiggens Learning: A simple unsupervised morphological learning model.
ConstantineLignos/Codeswitchador
Fast, simple identification of codeswitching in Tweets and other short messages.
ConstantineLignos/CTFTools
Tools and documentation to help use CTF MEG/EEG Tools.
ConstantineLignos/nyt-corpus-reader
A parser and MongoDB backed store for searching the New York Times Annotated Corpus (LDC2008T19)
ConstantineLignos/StateoftheUnion
A repository for teaching simple text analysis and web scraping using the SOTU address.
ConstantineLignos/ArtificialLangLearning
Tools and data related to artificial language learning experiments.
ConstantineLignos/mt-clir-emnlp-2019
Experiments for the EMNLP 2019 paper "The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval"
ConstantineLignos/nerpy
A Python named entity recognition framework
ConstantineLignos/WordSegmentation
Experiments in infant word segmentation.
ConstantineLignos/DetectorMorse
Fast supervised sentence boundary detection using the averaged perceptron
ConstantineLignos/ersatz
ConstantineLignos/joeynmt
Minimalist NMT for educational purposes
ConstantineLignos/NCRFpp
NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
ConstantineLignos/NCRFpp-insights-emnlp-2020
ConstantineLignos/nlp-in-ling
Natural Language Processing Research in North American Linguistics Departments
ConstantineLignos/py-flac2mp3
flac2mp3 implementation using the Mutagen ID3 library: Can operate incrementally, converts album art.
ConstantineLignos/python-sutime
Python wrapper for Stanford CoreNLP's SUTime
ConstantineLignos/quickvec
Fast loading of word vectors in Python
ConstantineLignos/SubSimNL
A Natural Language SubSim for SS-RICS
ConstantineLignos/word2vec
This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently used in many natural language processing applications and for further research.