rbawden Goto Github PK

academic-kickstart

diabla-chat-interface

Bilingual chat interface for dialogues mediated by machine translation (MT) systems.

diabla-dataset

English-French MT dialogue dataset

discomt17-pronouns

discourse-mt-test-sets

evaluating-discourse-in-nmt

fairseq

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

freemmax_oa

Corpus for a language model of (early) modern French

large-contrastive-pronoun-testset-en-fr

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

lsystem_display

Project OCaml, graphically displays Lindenmayer Systems

marian-dev-diverse-beam

Fast Neural Machine Translation in C++ - development repository

modfr-norm

mt-bigscience

Evaluation results for Machine Translation within the BigScience project

mva_2024_sl

MVA Course "Algorithms for speech and language processing", 2024, Clavel, Wisniewski, Sagot, Bawden & Seddah

nematus

Multi-encoder nematus

paraphrasing-bleu

prepcorpus-opensubs

promptsource

Toolkit for collecting and applying templates of prompting instances

rbawden.github.io

rocs-mt

sacrebleu

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

seg17

Script processing segmentation, normalization and lemmatization of XML-TEI encoded files.

similarity-cour-de-cassation

tag-questions

thebigbangtheory

"The Big Bang Theory" TVD plugin

token_questeval

QuestEval (https://github.com/ThomasScialom/QuestEval) on a token level

token_questeval-backup

tutoriel-normalisation

xlm

PyTorch original implementation of Cross-lingual Language Model Pretraining.