sheffieldnlp Goto Github PK

amr-preprocessing

AMR preprocessing and postprocessing scripts

amr2text-summ

AMR-to-Text Generator with Side Information

apeimitaion

Automatic Post Editing in MT with imitation learning

book_club

ML Book Club

build-linux

cmu-multimodaldatasdk

CMU MultimodalSDK provides tools to easily load well-known multimodal datasets such as CMU-MOSEI, CMU-MOSI, POM, and ICT-MMMO.

cwi

Cross-lingual Complex Word Identification

cwisharedtask2018-teaching

Resources for the CWI Shared Task 2018 for COM4513/6513 modules

deepquest

Framework for neural-based Quality Estimation

deepquest-py

Large and Distilled Models for Quality Estimation of Machine Translation

emojiprediction

Emoji Prediction

experiment-nmt-uncertainty

fakenewschallenge-teaching

Resources for the FNC challenge for COM4513/6513 modules

fever-evidence-annotation

fever-scorer

foildataset

Experiments on Foil Dataset

highres

imitationlearninglecture

imitationlearningtutorialeacl2017

Repo for the EACL2017 tutorial on imitation learning

mlqe-pe

Multilingual Quality Estimation and Automatic Post-editing Dataset

mlt

Multimodal Lexical Translation

multeval

Easy Bootstrap Resampling and Approximate Randomization for BLEU, METEOR, and TER using Multiple Optimizer Runs. This implements "Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability" from ACL 2011.

naacl2018-fever

Fact Extraction and VERification baseline published in NAACL2018

qe-eval-scripts

Scripts to process & score QE predictions into WMT format.

reading_group

stance-conditional

Stance Detection with Conditional Encoding

stance-semeval2016

USFD submission code for Semeval 2016 Task 6, Subtask B

submodular_summ

svcca

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.