Discourse parsing is considered as one of the most challenging natural language processing (NLP) tasks. Implicit discourse relation classification is the bottleneck for discourse parsing. Without the guide of explicit discourse connectives, the relation of sentence pairs are very hard to be inferred. This paper proposes a stacking neural network model to solve the classification problem in whic...

The annotations of explicit and implicit discourse connectives in the Penn Discourse Treebank make it possible to investigate on a large scale how different types of discourse relations are expressed. Assuming an account of the Uniform Information Density hypothesis, we expect that discourse relations should be expressed explicitly with a discourse connector when they are unexpected, but may be...

This paper presents a review of the main results of an application of discourse analysis in aphasics with the left hemisphere damages and in the right hemisphere damaged (RHD) patients. Research findings indicate that aphasics have marked deficits on the level of microstructure, especially cohesion of discourse, whereas the coherence and superstructure of their texts are relatively well preserv...

This paper is concerned with an approach to discourse processing via a new more general interpretation of Tree Adjoining Grammars (TAG) proposed by Vijay-Shanker (1992). This formalism is based on so-called Description trees (D-trees) (Marcus et al. 1983, Back-ofen 1995). I will discuss a discourse phenomenon commonly used as a stylistic device, namely ashback sequences. These sequences are par...

Some recent studies in computat ional l inguist ics have aimed to take advantage of various cues presented by punctuation marks. This short survey is intended to summarise these research efforts and additionally, to outline a current perspect ive for the usage and functions of punctuation marks. We conclude by presenting an information-based f ramework for punctuation, influenced by treatments ...

In the spirit of the neuroscience theme of this year’s meeting, I will describe a set of cognitive and neurophysiological phenomena that are important for the processing of narrative text at the discourse level. Text processing depends on sequential structure in language and also in the events that language describes. Semantic representations of events capture perceptual and motor properties of...

This paper describes the submitted English shallow discourse parsing system from the natural language processing (NLP) group of Soochow university (SoNLP-DP) to the CoNLL-2016 shared task. Our System classifies discourse relations into explicit and non-explicit relations and uses a pipeline platform to conduct every subtask to form an end-to-end shallow discourse parser in the Penn Discourse Tr...

In this article we are concerned with identifying topics of utterances in texts, which are discourse elements reflecting the links between a sentence and its context. The information carried by the topics can be used to contribute to a number of natural language processing applications, such as information retrieval, text categorization and discourse segmentation etc. However, the phenomenon of...

The goal of this study was to examine how lexical association and discourse congruence affect the time course of processing incoming words in spoken discourse. In an ERP norming study, we presented prime-target pairs in the absence of a sentence context to obtain a baseline measure of lexical priming. We observed a typical N400 effect when participants heard critical associated and unassociated...