Lucia Specia · page 2
Papers
- Findings of the WMT 2022 Shared Task on Quality Estimation (2022 · 91 citations)
This report describes the 11th edition of the WMT shared task on Quality Estimation (QE), which asks systems to judge neural machine translation output at the sentence and word levels without any reference translation. - Findings of the WMT 2021 Shared Task on Quality Estimation (2021 · 80 citations)
Quality Estimation (QE) predicts how good a machine translation is without access to a reference translation. The 2021 edition of the WMT QE shared task ran three subtasks on output from neural MT systems: - MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset (2022 · 76 citations)
MLQE-PE is a public dataset for training and testing machine translation Quality Estimation (QE), which predicts how good a translation is without a reference. - Readability Assessment for Text Simplification (2010 · 68 citations)
The paper tackles automatic readability assessment for Portuguese. Its goal is to help authors who simplify texts for adults with limited literacy. Instead of school grade levels, texts are mapped onto three literacy levels from Brazil's INAF index: advanced (original texts), basic (natural simplification) and… - Taking MT Evaluation Metrics to Extremes: Beyond Correlation with Human Judgments (2019 · 45 citations)
Automatic MT metrics are usually judged by a single global correlation with human scores. That number says little about where a metric succeeds or fails. Fomicheva and Specia run a broad meta-evaluation of many sentence-level metrics, mainly using WMT16 Metrics Task data. The metrics range from BLEU, TER and chrF to… - Understanding the Lexical Simplification Needs of Non-Native Speakers of English (2016 · 22 citations)
The paper asks which words actually cause trouble for non-native readers of English and what a good simpler replacement looks like for them.
This page in Markdown → https://md.research.elamur.ai/free/en/authors/lucia-specia/page/2/