To what extent does sentence-internal realisation reflect discourse context? A study on word order

We compare the impact of sentenceinternal vs. sentence-external features on word order prediction in two generation settings: starting out from a discriminative surface realisation ranking model for an LFG grammar of German, we enrich the feature set with lexical chain features from the discourse context which can be robustly detected and reflect rough grammatical correlates of notions from theoretical approaches to discourse coherence. In a more controlled setting, we develop a constituent ordering classifier that is trained on a German treebank with gold coreference annotation. Surprisingly, in both settings, the sentence-external features perform poorly compared to the sentenceinternal ones, and do not improve over a baseline model capturing the syntactic functions of the constituents.