Discourse relations between two text segments play an important role in many natural language processing (NLP) tasks. The connectives strongly indicate the sense of discourse relations, while in fact, there are no connectives in a large proportion of discourse relations, i.e., implicit discourse relations. The key for implicit relation prediction is to correctly model the semantics of the two d...

Previous research has shown that readers generate mental images of events. Most studies have investigated imagery during the reading of short texts, which also included explicit judgment tasks. In two fMRI studies, we assessed whether modality-specific imagery occurs during naturalistic, discourse comprehension. We identified clauses in the texts that elicited auditory, motor, or visual imagery...

To overcome the shortage of labeled data for implicit discourse relation recognition, previous works attempted to automatically generate training data by removing explicit discourse connectives from sentences and then built models on these synthetic implicit examples. However, a previous study (Sporleder and Lascarides, 2008) showed that models trained on these synthetic data do not generalize ...

We present a joint modeling approach to identify salient discussion points in spoken meetings as well as to label the discourse relations between speaker turns. A variation of our model is also discussed when discourse relations are treated as latent variables. Experimental results on two popular meeting corpora show that our joint model can outperform state-of-the-art approaches for both phras...

Rhetorical structure analysis (RSA) explores discourse relations among elementary discourse units (EDUs) in a text. It is very useful in many text processing tasks employing relationships among EDUs such as text understanding, summarization, and question-answering. Thai language with its distinctive linguistic characteristics requires a unique technique. This article proposes an approach for Th...

The paper describes data collection and transcription to develop the Croatian discourse corpus of speakers with aphasia (CroDA), developed within the framework of the project Adult Language Processing (HRZZ-2421-UIP-11-2013) and available from 2017 as part of the AphasiaBank database of multimedia interactions for studying communication among speakers with aphasia. In accordance with the Aphasi...

This paper presents a quantitative approach to multimodal discourse analysis for analyzing online collaborative learning. The coding framework draws together the fields of systemic functional linguistics and Activity Theory to analyze interactions between collaborative-, contentand technology-related discourse. The approach is used to examine how the task subject matter, the activity design, an...

Identification of visually presented words is facilitated by implicit memory, or visual priming, for past visual experiences with those words. There is disagreement over the neuro-anatomical substrates of this form of implicit memory. Several studies have suggested that this form of priming relies on a visual word-form system localized in the right occipital lobe, whereas other studies have ind...

Previous work by Lin et al. (2011) demonstrated the effectiveness of using discourse relations for evaluating text coherence. However, their work was based on discourse relations annotated in accordance with the Penn Discourse Treebank (PDTB) (Prasad et al., 2008), which encodes only very shallow discourse structures; therefore, they cannot capture long-distance discourse dependencies. In this ...