Evaluating HILDA in the CODA Project: A Case Study in Question Generation Using Automatic Discourse Analysis
نویسندگان
چکیده
Recent studies on question generation identify the need for automatic discourse analysers. We evaluated the feasibility of integrating an available discourse analyser called HILDA for a specific question generation system called CODA; introduce an approach by extracting a discourse corpus from the CODA parallel corpus; and identified future work towards automatic discourse analysis in the domain of question generation.
منابع مشابه
The Open University ’ s repository of research publications and other research outputs Question generation in the CODA project
In the ongoing CODA project, we are developing a system for automatically converting monologue into dialogue. The dialogue is generated in a two-step approach. Firstly, snippets of input monologue are mapped to dialogue act sequences. Secondly, these sequences are verbalized. The conversion relies partly on analysing input monologue in terms of its discourse relations. This short paper briefly ...
متن کاملQuestion Generation in the CODA project
In the ongoing CODA project, we are developing a system for automatically converting monologue into dialogue. The dialogue is generated in a two-step approach. Firstly, snippets of input monologue are mapped to dialogue act sequences. Secondly, these sequences are verbalized. The conversion relies partly on analysing input monologue in terms of its discourse relations. This short paper briefly ...
متن کاملHILDA: A Discourse Parser Using Support Vector Machine Classification
Discourse structures have a central role in several computational tasks, such as question–answering or dialogue generation. In particular, the framework of the Rhetorical Structure Theory (RST) offers a sound formalism for hierarchical text organization. In this article, we present HILDA, an implemented discourse parser based on RST and Support Vector Machine (SVM) classification. SVM classifie...
متن کاملLEARNER INITIATIVES ACROSS QUESTION-ANSWER SEQUENCES: A CONVERSATION ANALYTIC ACCOUNT OF LANGUAGE CLASSROOM DISCOURSE
This paper investigates learner-initiated responses to English language teachers’ referential questions and learner initiatives after teachers’ feedback moves in meaning-focused question-answer sequences to analyze how interactional practices of language teachers, their initiation and feedback moves, facilitate learner initiatives. Classroom discourse research has largely neglected learner init...
متن کاملPrioritizing Organizational Projects with Fuzzy Data Envelopment Analysis Approach (Case Study of Educational Research Plans)
The right choice of research projects is one of the most important effective ways to increase the productivity of research projects and allocate the resources appropriately. Training and education is one of the most important institutions for educating the students and prosperous people of the country. Due to the limited resources of this organization and, on the other hand, the expansion of sc...
متن کامل