Manawi: Using Multi-Word Expressions and Named Entities to Improve Machine Translation
By Liling Tan, Santanu Pal. 2014
26 citations recorded by the source corpus.
We describe the Manawi 1 (mAnEv) system submitted to the 2014 WMT translation shared task. We participated in the English-Hindi (EN-HI) and Hindi-English (HI-EN) language pair and achieved 0.792 for the Translation Error Rate (TER) score 2 for EN-HI, the lowest among the competing systems. Our main innovations are (i) the usage of outputs from NLP tools, viz. billingual multi-word expression extractor and named-entity recognizer to improve SMT quality and (ii) the introduction of a novel filter method based on sentence-alignment features. The Manawi system showed the potential of improving translation quality by incorporating multiple NLP tools within the MT pipeline.
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
- Josef van Genabith
- Sudip Kumar Naskar
- Santanu Pal
- Shamil Chollampatt
- Raymond Hendy Susanto
- Ewa Szymańska
- Sivaji Bandyopadhyay
- Alapan Kuila
In Natural Language Processing
- Josef van Genabith
- Sudip Kumar Naskar
- Santanu Pal
- Shamil Chollampatt
- Raymond Hendy Susanto
- Ewa Szymańska
- Liling Tan
- Sivaji Bandyopadhyay
In Machine Translation
- Josef van Genabith
- Sudip Kumar Naskar
- Raymond Hendy Susanto
- Shamil Chollampatt
- Ewa Szymańska
- Santanu Pal
- Sivaji Bandyopadhyay
- Alapan Kuila
Citations in the corpus
- Findings of the 2014 Workshop on Statistical Machine Translation (2014, neutral): “MANAWI-* Universität des Saarlandes (Tan and Pal, 2014)”
- UdS-Sant: English–German Hybrid Machine Translation System (2015, methodology): “Successively, the corpus cleaning process was carried out first by calculating the global mean ratio of the number of characters in a source sentence to that in a target sentence and then filter-ing out sentence pairs that exceed or fall below 20% of the global ratio (Tan and Pal, 2014).”
- JU-USAAR: A Domain Adaptive MT System (2016, methodology): “…the corpus cleaning process was carried out first by calculating the global mean ratio of the number of characters in a source sentence to that in the corresponding target sentence and then filtering out sentence pairs that exceed or fall below 20% of the global ratio (Tan and Pal, 2014).”
- Can Automatic Post-Editing Improve NMT? (2020, methodology): “We use an adaptation of Gale-Church filtering (Tan and Pal, 2014) used for machine translation for filtering the triplets.”