The analysis phase
The first phase in rule-based machine translation is the analysis phase, in which the source language text is analyzed to extract information related to morphology, parts of speech, named entity recognition, as well as word sense disambiguation. Morphological information concerns the structure of words, how their stems are derived, the detection of root words, and so on. A part-of-speech tagger tags each word in the text with a possible speech tag, such as noun, verb, adverb, adjective, and so on. This is followed by a named entity recognition (NER) task that tries to classify named entities into predefined buckets such as the name of a person, location, the name of an organization, and so on. NER is followed by word-sense ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access