| E14-2013 | the original term with the same | MT engine | . We show that we partially overcome |
| E14-2008 | translation from each of the different | MT engines | , without any additional information |
| E06-1005 | hypotheses Ei , ... , EM from M | MT engines | . We first choose one of the |
| D13-1008 | translations from three standard web | MT engines | . While not perfect , the translations |
| E06-1005 | from Span ish to English . The | MT engines | for this task had been trained |
| E14-2013 | new language pair or underlying | MT engine | . Our approach is close to the |
| E14-2013 | an external black-box generic | MT engine | extended with available domain-specific |
| D14-1172 | highlight strengths and weaknesses of | MT engines | or to investigate the influence |
| C04-1154 | ) , is a language-independent | MT engine | which exploits parsed , aligned |
| A94-1016 | usefulness of this method . Individual | MT engines | will be reported separately and |
| D15-1122 | along with decoding paths from all | MT engines | ' decoders . Another phrase-level |
| D15-1122 | target hypotheses from multiple | MT engines | , i.e , the consensus among occurrences |
| C94-1019 | heuristic will also serve tile EI ' , | MT engine | . A heuristic uscfut spccilically |
| D15-1122 | target hypotheses from multiple | MT engines | through its hierarchical paraphrases |
| C04-1071 | our SA system , which utilizes a | MT engine | , where techniques for parsing |
| E14-2013 | terminology verification method is both | MT engine | and language independent , does |
| A94-1016 | of the operation of each of the | MT engines | , new edges are added to the |
| C02-2006 | prepositional phrase is Prep , but EtoJ | MT engine | 's head is N . In most cases |
| E14-2013 | propose a postprocessing step for an | MT engine | , where a wrongly translated |
| D15-1122 | appear in the target hypotheses of | MT engines | . Huang and Papineni ( 2007 ) |
