Strategy-Based Technology for Estimating MT Quality
By Liu Shang, Dongfeng Cai, Duo Ji. 2015
5 citations recorded by the source corpus.
This paper introduces our SAU-KERC system that achieved F1 score of 0.39 in the world-level quality estimation task in WMT2015. The goal is to assign each translated word a “OK” or “BAD” label indicating translation quality. We adopt the sequence labeling model, conditional random fields (CRF), to predict the labels. Since “BAD” labels are rare in the training and development sets, recognition rate of "BAD" is low. To solve this problem, we propose two strategies. One is to replace “OK” label with sub-labels to balance label distribution. The other is to reconstruct the training set to include more "BAD" words.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Philipp Koehn
- Ondrej Bojar
- Lucia Specia
- Matt Post
- Barry Haddow
- Christof Monz
- Rico Sennrich
- Varvara Logacheva
In Natural Language Processing
- Philipp Koehn
- Lucia Specia
- Ondrej Bojar
- Barry Haddow
- Christof Monz
- Matt Post
- Varvara Logacheva
- Matteo Negri
Citations in the corpus
- Findings of the 2015 Workshop on Statistical Machine Translation (2015, background): “…Applications, France (Langlois, 2015) RTM-DCU Dublin City University, Ireland (Bicici et al., 2015) SAU-KERC Shenyang Aerospace University, China (Shang et al., 2015) SHEFF-NN University of Sheffield Team 1, UK (Shah et al., 2015) UAlacant Alicant University, Spain (Espl`a-Gomis et al., 2015a)…”