tailieunhanh - Báo cáo khoa học: "To what extent does sentence-internal realisation reflect discourse context? A study on word orde"

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. . | To what extent does sentence-internal realisation reflect discourse context A study on word order Sina ZarrieB Jonas Kuhn Institut fur maschinelle Sprachverarbeitung University of Stuttgart Germany zarriesa jonas@ Aoife Cahill Educational Testing Service Princeton NJ 08541 USA acahill@ Abstract 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. 1 Introduction The task of surface realization especially in a relatively free word order language like German is only partially determined by hard syntactic constraints. The space of alternative realizations that are strictly speaking grammatical is typically considerable. Nevertheless for any given choice of lexical items and prior discourse context only a few realizations will come across as natural and will contribute to a coherent text. Hence any NLP application involving a non-trivial generation step is confronted with the issue of soft constraints on grammatical alternatives in one way or another. There are countless approaches to modelling these soft constraints taking into account their interaction with various aspects of the discourse context givenness or salience of particular referents prior mentioning of particular concepts . Since so many factors are .