Referential Translation Machines for Predicting Translation Quality and Related Statistics
By Ergun Biçici, Qun Liu, Andy Way. 2015
13 citations recorded by the source corpus.
We use referential translation machines (RTMs) for predicting translation performance. RTMs pioneer a language independent approach to all similarity tasks and remove the need to access any task or domain specific information or resource. We improve our RTM models with the
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Ondrej Bojar
- Lucia Specia
- Chris Hokamp
- Carolina Scarton
- Daniel Beck
- Kashif Shah
- André F. T. Martins
- Ergun Biçici
Citations in the corpus
- Findings of the 2015 Workshop on Statistical Machine Translation (2015, neutral): “, 2015) LORIA Lorraine Laboratory of Research in Computer Science and its Applications, France (Langlois, 2015) RTM-DCU Dublin City University, Ireland (Bicici et al., 2015) SAU-KERC Shenyang Aerospace University, China (Shang et al.”
- Referential Translation Machines for Predicting Translation Performance (2016, methodology): “RTMs are powerful enough to be applicable in different domains and tasks while achieving top performance in both monolingual (Biçici and Way, 2015) and bilingual settings (Biçici et al., 2015b).”
- Word embeddings and discourse information for Quality Estimation (2016, methodology): “Bic¸ici et al. (2015) apply referential translation machines for paragraph-level QE and obtain the best overall results in the shared task.”
- Bilingual Embeddings and Word Alignments for Translation Quality Estimation (2016, methodology): “As illustrated in Tables 6 and 7, our model outperforms the baseline system as well as the Ref-erential Translation Machine model (RTM), the best performing system in WMT15 (Bicici et al., 2015), in both scoring and ranking sub-tasks on WMT16 IT-domain datasets.”
- Pushing the Limits of Translation Quality Estimation (2017, methodology): “report the performance of the two best systems in the sentence-level QE tasks at WMT15 and WMT16 (Bicici et al., 2015; Langlois, 2015; Kozlova et al., 2016; Kim and Lee, 2016).”
- Referential translation machines for predicting semantic similarity (2015, methodology): “We use ParFDA instance selection model, which is developed for fast deployment of accurate SMT systems (Bic¸ici et al. 2015a; Bic¸ici and Yuret 2015), for selecting the interpretants, and build an MTPPS model.”