Discourse parsing aims to identify the relationship between different discourse units, where most previous works focus on recovering the constituency structure among discourse units with carefully designed features. In this paper, we propose to exploit Long Short Term Memory (LSTM) to properly represent discourse units, while using as few feature engineering as possible. Our transition based pa...

abstract through the interpretation of texts, and subsequent creation of social reality, mediated representations are often seen to be presented within the certain of ideological discourses that reflect the existing power structures. the main objective of this paper is to analyze television commercials with an emphasis on gender roles to decode the main elements of a dominant discourse (preferr...

This paper surveys work on applying the insights of lexicalized grammars to low-level discourse, to show the value of positing an autonomous grammar for low-level discourse in which words (or idiomatic phrases) are associated with discourse-level predicate–argument structures or modification structures that convey their syntactic-semantic meaning and scope. It starts by describing a lexicalized...

Cognitive Grammar presupposes an inherent and intimate relation between linguistic structures and discourse. Linguistic units are abstracted from usage events, retaining as part of their value any recurring facet of the interactive and discourse context. Linguistic structures thus incorporate discourse expectations and are interpretable as instructions to modify the current discourse state. The...

The paper shows how sentences containing scope ambiguities can be assigned syntactic and semantic structures by means of sloppy deterministic processing techniques only. The semantic framework is Discourse Representation Theory, and the sloppy deterministic parser is described in Nordgård (1993). Of primary concern for the article is the transition from syntactic structures to discourse represe...

The eeects of discourse on disambiguating (sub)expressions and the problem of computing those eeects are treated formally by imposing a labeling structure over discourse representation structures, leading to barebones forms of Segmented and Underspeciied Discourse Representation Theory.

The efficacy of genre-based approach to teaching writing has been regarded as an influential practice in L2 writing pedagogy (Hyland, 2007). However, there is still gap between actual structures found in reading materials recommended as textbooks and discourse patterns recommended for L2 writing in EFL contexts, the gap which would highlight the problems of genre and rhetorical patterns for tea...

We describe a data-driven approach to building interpretable discourse structures for appointment scheduling dialogues. We represent discourse structures as headed trees and model them with probabilistic head-driven parsing techniques. We show that dialogue-based features regarding turn-taking and domain specific goals have a large positive impact on performance. Our best model achieves an f sc...

We propose a statistical dialogue analysis model to determine discourse structures as well as speech acts using maximum entropy model. The model can automatically acquire probabilistic discourse knowledge from a discourse tagged corpus to resolve ambiguities. We propose the idea of tagging discourse segment boundaries to represent the structural information of discourse. Using this representati...