USHEF and USAAR-USHEF participation in the WMT15 QE shared task
By Carolina Scarton, Liling Tan, Lucia Specia. 2015
9 citations recorded by the source corpus.
We present the results of the USHEF and USAAR-USHEF submissions for the WMT15 shared task on document-level quality estimation. The USHEF submissions explored several document and discourse-aware features. The USAARUSHEF submissions used an exhaustive search approach to select the best features from the official baseline. Results show slight improvements over the baseline with the use of discourse features. More interestingly, we found that a model of comparable performance can be built with only three features selected by the exhaustive search procedure.
Subfields: 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 Natural Language Processing
- Lucia Specia
- Ondrej Bojar
- Philipp Koehn
- Barry Haddow
- Christof Monz
- Matt Post
- Varvara Logacheva
- Yvette Graham
Citations in the corpus
- Findings of the 2016 Conference on Machine Translation (2016, methodology): “The discourse aware features are the same as the ones used by Scarton et al. (2015a) plus Latent Semantic Analysis (LSA) cohesion features (Scarton and Specia, 2014), number of subtrees and height of the Rhetorical Structure Theory (RST) tree and entity graph-based coherence scores (Sim Smith et…”
- Findings of the 2015 Workshop on Statistical Machine Translation (2015, neutral): “The network was pre-trained by initialising the word lookup-table with distributed word representations, ID Participating team DCU-SHEFF Dublin City University, Ireland and University of Sheffield, UK (Logacheva et al., 2015) HDCL Heidelberg University, Germany (Kreutzer et al., 2015) LORIA Lorraine ”
- Word embeddings and discourse information for Quality Estimation (2016, methodology): “Finally, Scarton (2015), Scarton and Specia (2015) and Scarton et al. (2015b) analyse the task of document-level QE from the perspective of defining reliable labels.”
- Metrics for Evaluation of Word-level Machine Translation Quality Estimation (2016, background): “…estimation (i.e. estimation of how confident a particular MT system is on a word or a phrase (Gan-drabur and Foster, 2003)) it evolved to system-independent QE and is performed at the word level (Luong et al., 2014), sentence level (Shah et al., 2013) and document level (Scarton et al., 2015).”