kellymarchisio Goto Github PK

align-semisup-bli

An Alignment-Based Approach to Semi-Supervised Bilingual Lexicon Induction with Small Parallel Corpora (Marchisio et al, 2021. MT Summit)

alignment-scripts

Scripts to preprocess training and test data and to run fast_align and giza

angec

Library for implementing RNNs with Theano

cambridge_dl4nlp

Cambridge Computer Lab 2018

doc2vec

Python scripts for training/testing paragraph vectors

ee-giza

Improved word alignment by incorporating monolingual embedding spaces into MGIZA/GIZA++. (Embedding-Enhanced Giza++, Marchisio et al., 2021. Preprint)

euc-v-graph-bli

An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces (Marchisio et al., Findings of EMNLP 2021)

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

gensim

Topic Modelling for Humans

goat

A paper (in progress) on graph matching via optimal transport. On arxiv at https://arxiv.org/abs/2111.05366

goat-for-bli

Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport (EMNLP 2022)

graspologic

Python package for graph statistics

isovec

IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces (EMNLP 2022)

jhu-mt-hw

kellymarchisio.github.io

monoses-1

Unsupervised Statistical Machine Translation

neural-naacl2018

Neural models and instructions on how to reproduce our results for our neural grammatical error correction systems from M. Junczys-Dowmunt, R. Grundkiewicz, S. Guha, K. Heafield: Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task, NAACL 2018.

nmt_gan

generative adversarial nets for neural machine translation

opennmt-py

Open Source Neural Machine Translation in PyTorch

tokenizers-km

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

tufte-css

Style your webpage like Edward Tufte’s handouts.

unsupervisedmt

Phrase-Based & Neural Unsupervised Machine Translation