The present paper combines two lines of research from discourse analysis and psychology by investigating thinking-aloud data and retrospective reports related to a cognitively demanding task, namely, a variant of the well-known Traveling Salesman Problem involving navigation to a set of goals. The analysis addresses the linguistic variability emerging from a discourse-analytic comparison of thr...

Despite widespread interests in reinforcement-learning for task-oriented dialogue systems, several obstacles can frustrate research and development progress. First, reinforcement learners typically require interaction with the environment, so conventional dialogue corpora cannot be used directly. Second, each task presents specific challenges, requiring separate corpus of task-specific annotate...

In this paper, we present findings from a human judgement task we conducted on the effectiveness of syntax filtering in a word completion task. Human participants were asked to review a series of incomplete sentences and identify which words from accompanying lists extend the expressions in a grammatically appropriate way. The accompanying word lists were generated by two word completion system...

Presently, advanced (redundant) manipulators are used sparingly and inefficiently to complete complex tasks despite the many advantages they have when compared to their non-redundant counterparts. Attempts by the Department of Energy to apply the potential advantages of redundancy to decontamination and dismantling processes have met with numerous complications. Yet, the decision to use them ex...

This study proposes a computational model of the discourse segments in lyrics to understand and to model the structure of lyrics. To test our hypothesis that discourse segmentations in lyrics strongly correlate with repeated patterns, we conduct the first large-scale corpus study on discourse segments in lyrics. Next, we propose the task to automatically identify segment boundaries in lyrics an...

We experiment with different ways of training LSTM networks to predict RST discourse trees. The main challenge for RST discourse parsing is the limited amounts of training data. We combat this by regularizing our models using task supervision from related tasks as well as alternative views on discourse structures. We show that a simple LSTM sequential discourse parser takes advantage of this mu...

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...

Penn Discourse Treebank style discourse parsing is a composite task of identifying discourse relations (explicit or nonexplicit), their connective and argument spans, and assigning a sense to these relations from the hierarchy of senses. In this paper we describe University of Trento parser submitted to CoNLL 2015 Shared Task on Shallow Discourse Parsing. The span detection tasks for explicit r...

This paper describes the submitted English shallow discourse parsing system from the natural language processing (NLP) group of Soochow university (SoNLP-DP) to the CoNLL-2016 shared task. Our System classifies discourse relations into explicit and non-explicit relations and uses a pipeline platform to conduct every subtask to form an end-to-end shallow discourse parser in the Penn Discourse Tr...