Congratulations to Serge Sharoff (CTS), who has been awarded a two-year grant from the Technology Strategy Board (TSB), value £216,411, to conduct a project entitled: PALODIEM, Process Automation for Localisation of Dialogue in Entertainment Media.
The two-year project is funded by the Technology Strategy Board (TSB) and is headed by Serge Sharoff in collaboration with a local SME. It calls for original research contributions to be provided in the following areas:
(1) Development of Statistical Machine Translation (SMT) engines for closely related languages, and (2) Selection of an optimal SMT path for related languages.
Statistical Machine Translation for closely related languages
SMT methods require a substantial source of data consisting of parallel translations of text between the required languages (an aligned corpus).
We will explore the topic of developing new high-quality SMT engines using automatic detection of cognate words, i.e., words having similarities in their spelling and meaning in two languages, e.g., maladie (French for 'disease') versus malattia (Italian equivalent).
Such lists can be generated from large monolingual resources in order to improve the coverage of the related pairs beyond the contents available in (smaller) aligned corpora.
Statistical Machine Translation path selection
Once we have a range of SMT engines tuned for our text types, we can investigate the influence of high-quality pivot translation on sharing the translation load across a range of related languages. We can expect that it may be better to create, say, an Italian translation of English dialogue by starting with a Spanish human translation rather than translating directly from English.