Extracting Chatbot Knowledge from Online Discussion Forums
نویسندگان
چکیده
This paper presents a novel approach for extracting high-quality pairs as chat knowledge from online discussion forums so as to efficiently support the construction of a chatbot for a certain domain. Given a forum, the high-quality pairs are extracted using a cascaded framework. First, the replies logically relevant to the thread title of the root message are extracted with an SVM classifier from all the replies, based on correlations such as structure and content. Then, the extracted pairs are ranked with a ranking SVM based on their content qualities. Finally, the Top-N pairs are selected as chatbot knowledge. Results from experiments conducted within a movie forum show the proposed approach is effective.
منابع مشابه
A Structural Support Vector Method for Extracting Contexts and Answers of Questions from Online Forums
This paper addresses the issue of extracting contexts and answers of questions from post discussion of online forums. We propose a novel and unified model by customizing the structural Support Vector Machine method. Our customization has several attractive properties: (1) it gives a comprehensive graphical representation of thread discussion. (2) It designs special inference algorithms instead ...
متن کاملFostering Higher Knowledge Construction Levels in Online Discussion Forums: An Exploratory Case Study
Prior research has suggested that higher levels of knowledge construction (e.g., where opinions are argued, challenged, or negotiated) have rarely been demonstrated in student online discussions. In this study, the authors replicate prior research on group size, discussion duration, and student facilitation techniques to examine the influence of these factors on the attainment of higher level k...
متن کاملA conceptual framework for assessing interaction quality in online discussion forums
The use of discussion forums in education has long been a hot topic in tertiary education. Discussion forums’ activities help learners to share and gain knowledge from each other. However, setting up discussion forums does not ensure that learners interact with each other actively and grading of discussion forum participation is done to ensure qualitative learner participation. Currently, a maj...
متن کاملE-learning: Analysis of online discussion forums in promoting knowledge construction through collaborative learning
Extensive discussions and debates about the advantages of using technology to create a shared space among learning participants have been presented in studies in the field of e-learning. One of the approaches in using or adopting technology for learning is through the use of online discussion forums, which as reported has beneficial impact on the teaching and learning process. Online discussion...
متن کاملPersonalised knowledge representations: the missing half of online discussions
In this paper, we highlight a concern with using online discussion for learning. We argue that there is a lack of technological support for the development of personalised knowledge representation for most online discussion forums. Analyses of existing discussion forums suggest that there is a range of collective knowledge representation mechanisms which support a group or a community of learne...
متن کامل