This paper describes our two discourse parsers (i.e., English discourse parser and Chinese discourse parser) for submission to CoNLL-2016 shared task on Shallow Discourse Parsing. For English discourse parser, we build two separate argument extractors for single sentence (SS) case, and adopt a convolutional neural network for Non-Explicit sense classification based on (Wang and Lan, 2015b)’s wo...

Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse framework such as PDTB or RST to improve the classification performance on discourse relations. Actually, under different discourse annotation frameworks, there exist multiple corpor...

adopting a discourse-pragmatic approach, this study examines the synchronic multifunctionality of the discourse marker hâlâ from the perspective of (inter)subjectification. the findings obtained from the synchronic corpus of colloquial persian indicates that hâlâ has proceeded along the (inter)subjectification cline identified by traugott and dasher (2002), der (2010), and degand and vandenberg...

Previous researches on Text-level discourse parsing mainly made use of constituency structure to parse the whole document into one discourse tree. In this paper, we present the limitations of constituency based discourse parsing and first propose to use dependency structure to directly represent the relations between elementary discourse units (EDUs). The state-of-the-art dependency parsing tec...

Discourse relation parsing is an important task with the goal of understanding text beyond the sentence boundaries. With the availability of annotated corpora (Penn Discourse Treebank) statistical discourse parsers were developed. In the literature it was shown that the discourse parsing subtasks of discourse connective detection and relation sense classification do not generalize well across d...

This study concerned the role of gestures that accompany discourse in deep learning processes. We assumed that co-speech gestures favor the construction of a complete mental representation of the discourse content, and we tested the predictions that a discourse accompanied by gestures, as compared with a discourse not accompanied by gestures, should result in better recollection of conceptual i...

Discourse connectives play an important role in making a text coherent and helping humans to infer relations between spans of text. Using the Penn Discourse Treebank, we investigate what information relevant to inferring discourse relations is conveyed by discourse connectives, and whether the specificity of discourse relations reflects general cognitive biases for establishing coherence. We al...

This paper takes a critical look at the news reports of the Islamic Republic of Iran and Saudi Arabia on Mina stampede. Previous studies have indicated that media discourse contributes to public opinion and ideology. Little, however, has been mentioned on how variation in media discourse affects the process. This study analyzed 24 news reports from the two countries from 24 to 31 September 2015...