2018
EMNLP
EMNLP 2018
ITER: Improving Translation Edit Rate through Optimizable Edit Costs
Abstract
AbstractThe paper presents our participation in the WMT 2018 Metrics Shared Task. We propose an improved version of Translation Edit/Error Rate (TER). In addition to including the basic edit operations in TER, namely - insertion, deletion, substitution and shift, our metric also allows stem matching, optimizable edit costs and better normalization so as to correlate better with human judgement scores. The proposed metric shows much higher correlation with human judgments than TER.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Mathematics & Optimization and Natural Language Processing
🐣
Hot Topic Early Bird
- automatic evaluation
Authors
Topics
Artificial Intelligence > Learning Paradigms > Transfer Learning
Machine Learning > Optimization & Theory > Optimization
Natural Language Processing > Applications > Machine Translation
Mathematics & Optimization > Optimization > Optimization
Machine Learning > Application Areas > Text Classification