Translator’s tools. For the translator’s tools, there are three different use cases: restricted source o production of source in the first place o modifying source produced earlier unrestricted source. Working with restricted source language recognizable by a GF grammar is straightforward for the translating tool to cope with, except when there is ambiguity in the text. The real challenge is to help the author to keep inside the restricted language. This help is provided by predictive parsing, a technique recently developed for GF (Angelov 2009). Incremental parsing yields word predictions, which guide the author in a way similar to the T9 method27 in mobile phones. The difference from T9 is, however, that GF’s work prediction is sensitive to the grammatical context. Thus it does not suggest all existing words, but only those words that are grammatically correct in the context. Figure 2 shows an example of the parser at work. The author has started a sentence as la femme qui remplit le formulaire est co ("the woman who fills the form is co"), and a menu shows a list of words beginning with co that are given in the French grammar and possible in the context at hand; all these words are adjectives in the feminine form. Figure 2: French word prediction in GF parser, suggesting feminine adjectives that agree with the subject la femme. Notice that the very example shown in Figure 2 is one that is difficult for n-gram-based statistical translators: the adjective is so far from the subject with which it agrees that it cannot easily be related to it. Predictive parsing is a good way to help users produce translatable content in the first place. When modifying the content later, e.g. in a wiki, it may not be optimal, in particular if the text is long. The text can contain parts that depend on each other but are located far apart. For instance, if the word femme ("woman") in the previous example is changed to homme, the preceding article la has to be changed to l’, and the adjective has to be changed to the masculine form: thus connue ("known") would become connu, and so on. Such changes are notoriously difficult even for human authors and translators, and can easily leave a document in an inconsistent state. This is where another utility of the abstract syntax comes in: in the abstract syntax tree, all that is changed is the noun, and the regenerated concrete syntax string automatically obeys all the agreement rules. The process is shown in Figure 3. The one-word change generating the...
