Semantic Scholar uses AI to extract papers important to this topic.
Unsupervised machine translation - i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations… Expand Most methods to learn bilingual word embeddings rely on large parallel corpora, which is difficult to obtain for most language… Expand Mapping word embeddings of different languages into a single space has multiple applications. In order to map from a source space… Expand We introduce bilingual word embeddings: semantic embeddings associated across two languages in the context of neural language… Expand Looking at the development of bilingual dictionaries in South Africa this article discusses the change from an externally to an… Expand We present and compare various methods for computing word alignments using statistical or heuristic models. We consider the five… Expand We present a new method for aligning sentences with their translations in a parallel bilingual corpus. Previous approaches have… Expand In recent years, there is a phenomenal growth in the amount of online text material available from the greatest information… Expand The bilingual child is seen as a unique source of information about the relation between input and intake. The strength of the… Expand Collocations are notoriously difficult for non-native speakers to translate, primarily because they are opaque and cannot be… Expand