“This sentence is wrong.” Detecting errors in machine-translated sentences
By Sylvain Raybaud, David Langlois, Kamel Smaïli. 2011
46 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Information Systems, 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
- Lucia Specia
- Philipp Koehn
- Varvara Logacheva
- Matt Post
- Ondrej Bojar
- Christof Monz
- Chris Hokamp
- Chris Callison-Burch
In Information Systems
- Philipp Koehn
- Christof Monz
- Chris Callison-Burch
- Matt Post
- Lucia Specia
- Laurent Besacier
- Varvara Logacheva
- Radu Soricut
In Natural Language Processing
- Lucia Specia
- Philipp Koehn
- Varvara Logacheva
- Matt Post
- Ondrej Bojar
- Chris Hokamp
- Christof Monz
- Benjamin Van Durme
Citations in the corpus
- Findings of the 2016 Conference on Machine Translation (2016, neutral): “– Backoff behaviour of the ngrams (ti−2, ti−1, ti), (ti−1, ti, ti+1), (ti, ti+1, ti+2), where ti is the target token (the backoff behaviour was computed as described in (Raybaud et al., 2011)).”
- Findings of the 2015 Workshop on Statistical Machine Translation (2015, neutral): “– Backoff behaviour of the n-grams , where t i is the target token (the backoff behaviour is computed as described in (Raybaud et al., 2011)).”
- LIG System for WMT13 QE Task: Investigating the Usefulness of Features in Word Confidence Estimation for MT (2013, background): “• Backoff behaviour: a score assigned to the word according to how many times the target Language Model has to back-off in order to assign a probability to the word sequence, as described in (Raybaud et al., 2011).”
- Data enhancement and selection strategies for the word-level Quality Estimation (2015, background): “The “BAD” labels thus correspond to the “addition” and “substitution” edit operations in the word-level string alignment between the MT hypothesis and the post-edited segment.”
- Findings of the 2012 Workshop on Statistical Machine Translation (2012, methodology): “The official submission use the baseline features and a number of features proposed in previous work (Raybaud et al., 2011), amounting to 66 features.”
- Strategy-Based Technology for Estimating MT Quality (2015, background): “Back-off: a score assigned to the word according to how many times the target Language Model has to Back-off in order to assign a probability to the word sequence, as described in (Raybaud et al., 2011).”
- Referential translation machines for predicting semantic similarity (2015, unknown): “We use both forward ({24, 18}) and backward ({12, 9}) LM features (Raybaud et al. 2011) for S ({36, 27}) and T ({36, 27}).”