Translation Quality Estimation using Recurrent Neural Network
By Raj Nath Patel, Madhavan Sasikumar. 2016
25 citations recorded by the source corpus.
This paper describes our submission to the shared task on word/phrase level Quality Estimation (QE) in the First Conference on Statistical Machine Translation (WMT16). The objective of the shared task was to predict if the given word/phrase is a correct/incorrect (OK/BAD) translation in the given sentence. In this paper, we propose a novel approach for word level Quality Estimation using Recurrent Neural Network Language Model (RNN-LM) architecture. RNN-LMs have been found very effective in different Natural Language Processing (NLP) applications. RNN-LM is mainly used for vector space language modeling for different NLP problems. For this task, we modify the architecture of RNNLM. The modified system predicts a label (OK/BAD) in the slot rather than predicting the word. The input to the system is a word sequence, similar to the standard RNN-LM. The approach is language independent and requires only the translated text for QE. To estimate the phrase level quality, we use the output of the word level QE system.
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): “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”
- Findings of the 2017 Conference on Machine Translation (WMT17) (2017, methodology): “CDACM (T2, T3): The submissions from CDACM use a recurrent neural network language model (RNN-LM) architecture for word-level QE as described in (Patel and M, 2016), and explore the word-level predictions for phrase-level QE.”