This paper presents a mutual learning method using hierarchical deep semantics for the classification of implicit discourse relations in English. With the absence of explicit discourse markers, traditional discourse techniques mainly concentrate on discrete linguistic features in this task, which always leads to data sparse problem. To relieve this problem, we propose a mutual learning neural m...

A dedicated resource, consisting of annotated speech data, tools, and workflow design, was developed for the detailed investigation of discourse phenomena in Taiwan Mandarin. The discourse phenomena have functions which are associated with positions in utterances, and temporal properties, and include discourse markers (‘NAGE’, ’NA’, e.g. ‘hesitation’, ‘utterance initiation’), discourse particle...

Deep neural networks have shown recent promise in many language-related tasks such as the modeling of conversations. We extend RNN-based sequence to sequence models to capture the long range discourse across many turns of conversation. We perform a sensitivity analysis on how much additional context affects performance, and provide quantitative and qualitative evidence that these models are abl...

To understand a discourse, the reader needs to recover the relations between the discourse elements as intended by the writer. Writers can, and very often do, help the reader along by providing explicit lexical signals of the intended discourse relations through the use of lexicalised discourse markers. In this paper we present a novel approach for generating texts containing multiple, embedded...

Deep neural networks have shown recent promise in many language-related tasks such as the modelling of conversations. We extend RNN-based sequence to sequence models to capture the long-range discourse across many turns of conversation. We perform a sensitivity analysis on how much additional context affects performance, and provide quantitative and qualitative evidence that these models can ca...

This paper presents DiZer, an automatic DIscourse analyZER for Brazilian Portuguese. Given a source text, the system automatically produces its corresponding rhetorical analysis, following Rhetorical Structure Theory – RST (Mann and Thompson, 1987). A rhetorical repository, which is DiZer main component, makes the automatic analysis possible. This repository, produced by means of a corpus analy...

As has been shown by Traugott & Dasher (2002), discourse markers proceed along the following grammaticalization cline; non-subjective > subjective > intersubjective uses. We look for evidence of this grammaticalization cline using a previously unexamined discourse marker in Spanish no sé (‘I don’t know’). Inline with Bybee & Sheibman (1999), we show that no sé seems to be stored in lexical repr...

In order to develop an understanding of the rhetorical conventions in the Persian language and to find out the metadiscursive cultural norms of Iranian writers in their native language writings, it is necessary to probe into the implicit rhetorical features of academic writing which has so far eluded a comprehensive systematic characterization. Metadiscourse marking, which is supposed to be one...

Discourse marker is a common language phenomenon in verbal communication including parts of conjunctions, adverbs, interjections, some phrases and small words. From the perspective grammar, these modifiers do not have many semantic meanings they are less related to sentences. However, from pragmatics discourse, discourse plays role organizing attracting hearer’s attention, expressing emotion at...

In example (1), a sentence from a Wall Street Journal article taken from the Penn TreeBank corpus is further segmented into four EDUs, (1a), (1b), (1c) and (1d) (RST, 2002). Discourse segmentation, clearly, is not as easy as sentence boundary detection. The lack of consensus with regards to what constitutes an elementary discourse unit adds to the difficulty. Building a rule based discourse seg...