ygraham

crowd-alone

Crowd-sourcing System-level MT Evaluations

da-wmt16

Instructions and Code needed for WMT-16 Direct Assessment (DA)

direct-assessment

Direct Assesment for Human Evaluation of MT

eacl2017

Human Evaluation Data for Document-level Quality Estimation

MT-metric-confidence-intervals

mt-qe-eval

MT Quality Estimation Significance Test

nlp-williams

Significance test of increase in correlation for NLP evaluations

segment-mteval

Crowd-sourcing Segment-level MT Evaluations

significance-williams

MT Document-level METRICS Significance Test - is an increase in correlation with human judgment significant?

summarization-sigtest

Code for evaluating summarization metrics like ROUGE

ygraham/direct-assessment

Direct Assesment for Human Evaluation of MT

ygraham/crowd-alone

Crowd-sourcing System-level MT Evaluations

ygraham/mt-qe-eval

MT Quality Estimation Significance Test

ygraham/significance-williams

MT Document-level METRICS Significance Test - is an increase in correlation with human judgment significant?

ygraham/eacl2017

Human Evaluation Data for Document-level Quality Estimation

ygraham/nlp-williams

Significance test of increase in correlation for NLP evaluations

ygraham/segment-mteval

Crowd-sourcing Segment-level MT Evaluations

ygraham/da-wmt16

Instructions and Code needed for WMT-16 Direct Assessment (DA)

ygraham/MT-metric-confidence-intervals

ygraham/summarization-sigtest

Code for evaluating summarization metrics like ROUGE

ygraham/wmt17-website

Website for WMT17 - Second Conference in Machine Translation