This study aimed to examine the effect of flexible group collaboration on students’ constructive discourse in a principle-based CSCL environment. The participants included 27 Chinese undergraduate students taking a 16-week introductory research methods course. The online discourse adopted a flexible collaboration structure: fixed small group collaboration in the first eight weeks, and opportuni...

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...

Identifying discourse relations in a text is essential for various tasks in Natural Language Processing, such as automatic text summarization, question-answering, and dialogue generation. The first step of this process is segmenting a text into elementary units. In this paper, we present a novel model of discourse segmentation based on sequential data labeling. Namely, we use Conditional Random...

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...

The task of implicit discourse relation classification has received increased attention in recent years, including two CoNNL shared tasks on the topic. Existing machine learning models for the task train on sections 2-21 of the PDTB and test on section 23, which includes a total of 761 implicit discourse relations. In this paper, we’d like to make a methodological point, arguing that the standa...

This study investigated the relations among attachment, mother–child discourse, and theory of mind in a sample of 76 four-year-old children (mean age = 4.48 years; 36 boys). Mother–child conversations about a past event were coded for maternal use of elaborative discourse and mothers’ references to mental states. Mothers completed the attachment q-sort and children completed four false-belief t...

Code completion is one of the techniques used for realizing efficient code implementations. Code completion means adding the lacking code required for finishing a given task. Recently, some researchers have proposed code completion techniques that are intended to support code reuse. However, these existing techniques are designed to support the following programming steps. They cannot add neces...

We present the results of several machine learning tasks designed to predict rhetorical relations that hold between clauses in discourse. We demonstrate that organizing rhetorical relations into different granularity categories (based on relative degree of detail) increases average prediction accuracy from 58% to 70%. Accuracy further increases to 80% with the inclusion of clause types. These r...

We describe a generic set of tools for representing, annotating, and analysing multi-party discourse, including: an ontology of multimodal discourse, a programming interface for that ontology, and NOMOS – a flexible and extensible toolkit for browsing and annotating discourse. We describe applications built using the NOMOS framework to facilitate a real annotation task, as well as for visualisi...

Discourse parsing is a challenging task and is crucial for discourse analysis. In this paper, we focus on labelling argument spans of discourse connectives and sense identification in the CoNLL-2015 shared task setting. We have used syntactic features and have also tried a few semantic features. We employ a pipeline of classifiers, where the best features and parameters were selected for each i...