Annotation for and Robust Parsing of Discourse Structure on Unrestricted Texts

Predicting discourse structure on naturally occurring texts and dialogs is challenging and computationally intensive. Attempts to construct hand-built systems have run into problems both in how to specify the required knowledge and how to perform the necessary computations in an efficient manner. Data-driven approaches have recently been shown to be successful for handling challenging aspects of discourse without using lots of fine-grained semantic detail, but they require annotated material for training. We describe our effort to annotate Segmented Discourse Representation Structures on Wall Street Journal texts, arguing that graph-based representations are necessary for adequately capturing the dependencies found in the data. We then explore two data-driven parsing strategies for recovering discourse structures. We show that the generative PCFG model of Baldridge & Lascarides (2005b) is inherently limited by its inability to incorporate new features when learning from small data sets, and we show how recent developments in dependency parsing and discriminative learning can be utilized to get around this problem and thereby improve parsing accuracy. Results from exploratory experiments on Verbmobil dialogs and our annotated news wire texts are given; these results suggest that these methods do indeed enhance performance and have the potential for significant further improvements by developing richer feature sets.

Robust parsing with weighted constraints

Based on constraint optimization techniques, an architecture for robust parsing of natural language utterances has been developed. The resulting system is able to combine possibly contradicting evidence from a variety of information sources, using a plausibility-based arbitration procedure to derive fairly rich structural representations, comprising aspects of syntax, semantics and other description levels of language. The results of a series of experiments are reported which demonstrate the high potential for robust behaviour with respect to ungrammaticality, incomplete utterances, and temporal pressure.