Bridging Background Knowledge Gaps in Translation with Automatic Explicitation
This work addresses a specific issue in NLP for translation by providing a method to enhance understanding for users with cultural or knowledge gaps, though it is incremental as it builds on existing translation and dataset collection approaches.
The paper tackled the problem of translations being incomprehensible due to background knowledge gaps by introducing automatic techniques for generating explicitations, using a new dataset called WikiExpl, and showed that these explicitations improve question answering accuracy in a multilingual framework.
Translations help people understand content written in another language. However, even correct literal translations do not fulfill that goal when people lack the necessary background to understand them. Professional translators incorporate explicitations to explain the missing context by considering cultural differences between source and target audiences. Despite its potential to help users, NLP research on explicitation is limited because of the dearth of adequate evaluation methods. This work introduces techniques for automatically generating explicitations, motivated by WikiExpl: a dataset that we collect from Wikipedia and annotate with human translators. The resulting explicitations are useful as they help answer questions more accurately in a multilingual question answering framework.