Interview is a vital part of recruitment process and is especially challenging for the beginners. In an interactive and natural interview, the interviewers would ask follow-up questions or request further elaborations when they are not satisfied with the interviewee's initial response. In this study, as only a small interview corpus is available, a pattern-based sequence to sequence (Seq2seq) model is adopted for follow-up question generation. First, word clustering is employed to automatically transform the question/answer sentences into sentence patterns, in which each sentence pattern is composed of word classes, to decrease the complexity of the sentence structures. Next, the convolutional neural tensor network (CNTN) is used to select a target sentence in an interviewee's answer turn for follow-up question generation. In order to generate the follow-up question pattern, the selected target sentence pattern is fed to a Seq2seq model to obtain the corresponding follow-up question pattern. Then the word class positions in the generated follow-up question sentence pattern is filled in with the words using a word class table obtained from the training corpus. Finally, the n-gram language model is used to rank the candidate follow-up questions and choose the most suitable one as the response to the interviewee. This study collected 3390 follow-up question and answer sentence pairs for training and evaluation. Five-fold cross validation was employed and the experimental results show that the proposed method outperformed the traditional word-based method, and achieved a more favorable performance based on a statistical significance test.
This study proposes an approach to follow-up question generation based on a populated domain ontology in a conversational interview coaching system. The purpose of this study is to generate the follow-up questions which are more related to the meaning beyond the literal content in the user's answer based on the background knowledge in a populated domain ontology. Firstly, a convolutional neural tensor network (CNTN) was applied for selecting a key sentence from the user answer. Secondly, the neural tensor network (NTN) was used to model the relationship between the subjects and objects in the resource description framework (RDF) triple, defined as (subject, predicate, object), in each predicate from the ConceptNet for domain ontology population. The words in the key sentence were then used to retrieve relevant triples from the domain ontology for filling into the slots in the question templates to generate potential follow-up questions. Finally, the CNTN-based sentence matching model was employed to choose the one most related to the answer sentence as the final follow-up question. This study used 5-fold cross-validation for performance evaluation. The experimental results showed the generation performance in the proposed model was higher than the traditional method. The performance of key sentence selection model achieved 81.94%, and the sentence matching model achieved 92.28%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.