SHEF-LIUM-NN: Sentence level Quality Estimation with Neural Network Features
By Kashif Shah, Fethi Bougares, Loïc Barrault, Lucia Specia. 2016
17 citations recorded by the source corpus.
This paper describes our systems for Task 1 of the WMT16 Shared Task on Quality Estimation. Our submissions use (i) a continuous space language model (CSLM) to extract sentence embeddings and cross-entropy scores, (ii) a neural network machine translation (NMT) model, (iii) a set of QuEst features, and (iv) a combination of features produced by QuEst and with CSLM and NMT. Our primary submission achieved third place in the scoring task and second place in the ranking task. Another interesting finding is the good performance obtained from us-ing as features only CSLM sentence embeddings, which are learned in an unsupervised fashion without any additional hand-crafted features.
Subfields: Artificial Intelligence, Natural Language Processing, Machine Translation
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
- Barry Haddow
- Matt Post
- Felix Stahlberg
- Rico Sennrich
In Natural Language Processing
- Ondrej Bojar
- Philipp Koehn
- Lucia Specia
- Graham Neubig
- Barry Haddow
- Christof Monz
- Yvette Graham
- Matt Post
In Machine Translation
- Lucia Specia
- Philipp Koehn
- Ondrej Bojar
- Varvara Logacheva
- Matt Post
- Frédéric Blain
- Barry Haddow
- Christian Federmann
Citations in the corpus
- Findings of the 2016 Conference on Machine Translation (2016, background): “CDACM Centre for Development of Advanced Computing, India (Patel and M, 2016) POSTECH Pohang University of Science and Technology, Republic of Korea (Kim and Lee, 2016) RTM Referential Translation Machines, Turkey (Bicici, 2016b) SHEF University of Sheffield, UK (Paetzold and Specia, 2016) SHEF-LIUM”
- Enhancement of Encoder and Attention Using Target Monolingual Corpora in Neural Machine Translation (2018, methodology): “The sentence features are computed by averaging all word embeddings (Shah et al., 2016).”
- USFD’s Phrase-level Quality Estimation Systems (2016, methodology): “The sentence-level score is produced by the SHEF-LIUM-NN system, a sentence-level QE system with neural network features as described in (Shah et al., 2016).”