The reduction of morphological complexity has been accompanied by the emergence of a more rigid order of sentence elements.
Translation between Japanese and English is notoriously difficult and one of the major reasons for this is the ability of the speaker within the former to omit all manner of sentence elements – subject, object, even verb – where the implied meaning is clear by context.
Using a tree representation, the structure of a sentence can be clearly shown by applying PSG rules at each level of the tree to map sentence elements at the current level to the sentence elements at a higher level.
There are many such confusing sentence elements: complex objects that consist of and-, or-, or comma-separated elements; quotations; prepositions and articles; proper names; punctuation marks.
Even with the presence of the context of situation, drawing a sharp line between sentence elements in terms of the degree of CD they carry may be inaccurate as it differs from one interpretation to another.
In sentence type F3, the noun 'Anna' conveys a focus accent which also influences the realization of surrounding sentence elements.
Rather, words preceding or following the focus position or information center, respectively, are also influenced in their prosodic properties, i.e. to enhance the prominence of the focus with respect to surrounding sentence elements ([ 4] for a longer linguistics-based discussion).
Sentence elements are the parts that play different grammatical roles in a sentence.
The core sentence elements are Subject, Predicate, Object (Just like those in English!); Other elements accompanying noun, verb and sentence: Attributive, Adverbial, Complement.
When a sentence includes a time element, tense becomes moot.
The fact that we used only one sentence per element, while building our training data, is a strong limiting factor.
