We present experiments in using discourse structure for improving machine translation evaluation. We first design two discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory. Then, we show that these measures can help improve a number of existing machine translation evaluation metrics both at the segm...

We present discourse-level annotation of newspaper texts in German and English, as part of an ongoing project aimed at investigating information structure from a cross-linguistic perspective. Rather than annotating some specific notion of information structure, we propose a theory-neutral annotation of basic features at the levels of syntax, prosody and discourse, using treebank data as a start...

This study investigates the relationship between prosody and information/discourse structure in spontaneous spoken folk tales in the tonal Mon-Khmer language Northern Kammu, a language that behaves as a typical phrase language where available boundary tones are enhanced to mark information structuring. Topic is always placed before Comment by syntactic movement if necessary. There is a prosodic...

Cue phrases are words and phrases such as now and by the way which may be used to convey explicit information about the structure of a discourse. However, while cue phrases may convey discourse structure, each may also be used to different effect. The question of how speakers and hearers distinguish between such uses of cue phrases has not been addressed in discourse studies to date. Based on a...

generation is, like Machine Translation, one of the ultimate goal of Natural Language Processing. However, since conventional word–frequency– based abstract generation systems(e.g. [Kuhn 58]) are lacking in inter-sentential or discourse-structural analysis, they are liable to generate incoherent abstracts. On the other hand, conventional knowledge or script–based abstract generation systems(e.g...

In order to analyze, generate and use documents containing both text and graphics, it is important to have a theory of their structure. We argue that it is possible to develop a semantics for graphics, as well as text, and generate an integrated representation of text/graphics discourse, building on previous theories of text discourse. A major component of our theory is an integrated natural la...

The paper presents a preliminary study on discourse connectives (DC) in Czech. Aiming to build a computerized language corpus capturing discourse relations in Czech, we base our observations on current foreign projects with the same purpose. In this study, first, the different methods of linguistic analysis of the discourse structure and discourse connectives are described, next, the nature and...

In this paper we consider the problem of analysing sentence-level discourse structure. We introduce discourse chunking (i.e., the identification of intra-sentential nucleus and satellite spans) as an alternative to full-scale discourse parsing. Our experiments show that the proposed modelling approach yields results comparable to state-of-the-art while exploiting knowledge-lean features and sma...

A central but still unsettled question in formal theories about discourse interpretation is: What are the key theoretical structures on which discourse interpretation should depend? If we take our cue from theories that analyze the meanings of individual sentences, the meaning of the discourse's parts should determine the meaning of the whole; some sort principle of compositionality of meaning ...