Word embeddings and discourse information for Quality Estimation
By Carolina Scarton, Daniel Beck, Kashif Shah, Karin Sim Smith, Lucia Specia. 2016
11 citations recorded by the source corpus.
In this paper we present the results of the University of Sheffield (SHEF) sub-missions for the WMT16 shared task on document-level Quality Estimation (Task 3 ). Our submission explore discourse and document-aware information and word embeddings as features, with Support Vector Regression and Gaussian Process used to train the Quality Estimation models. The use of word embeddings (combined with baseline features) and a Gaussian Process model with two kernels led to the winning submission in the shared task.
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
- Ondrej Bojar
- Philipp Koehn
- Lucia Specia
- Graham Neubig
- Matt Post
- Barry Haddow
- Felix Stahlberg
- Rico Sennrich
In Natural Language Processing
- Ondrej Bojar
- Philipp Koehn
- Lucia Specia
- Barry Haddow
- Matt Post
- Christof Monz
- Yvette Graham
- Graham Neubig
Citations in the corpus
- Findings of the 2016 Conference on Machine Translation (2016, background): “, 2016a) USHEF University of Sheffield, UK (Scarton et al., 2016) UU Uppsala University, Sweden (Sagemo and Stymne, 2016) YSDA Yandex School of Data Analysis, Russia (Kozlova et al.”
- Findings of the 2017 Conference on Machine Translation (WMT17) (2017, methodology): “The QUEST-EMB submission follows the word embeddings approach used by (Scarton et al., 2016) for document-level QE.”