Abstract
The most challenging task of Community Question Answering (CQA) is to provide high-quality answers to users’ questions. Currently, a variety of expert recommendation methods have been proposed and greatly improved the effective matching between questions and potential good answerers. However, the performance of existing methods can be adversely affected by many common factors such as data sparsity and noise problem, which cause less precise user modeling. Moreover, existing methods often model user-question interactions through simple ways, failing to capture the multiple scale interactions of question and answerers, which make it difficult to find answerers who are able to provide the best answers. In this paper, we propose an attention-based variant of Factorization Machines (FM) called Hierarchical Attentional Factorization Machines (HaFMRank) for answerer recommendation in CQA, which not only models the interactions between pairs of individual features but emphasizes the roles of crucial features and pairwise interactions. Specifically, we introduce the within-field attention layer to capture the inner structure of features belonging to the same field, while a feature-interaction attention layer is adopted to examine the importance of each pairwise interaction. A pre-training procedure is designed to generate latent FM feature embedding that encode question context and user history into the training process of HaFMRank. The performance of the proposed HaFMRank is evaluated by using real-world datasets of Stack Exchange and experimental results demonstrate that it outperforms several state-of-the-art methods in best answerer recommendation.
Highlights
This decade of years has seen the prosperity of numerous online systems that support question answering (Q&A) activities
For the sake of capturing the importance of each feature and feature interaction, we propose an attention-based factorization machine models, i.e. Hierarchical Attentional Factorization Machine (HaFMRank)
Based on the attentional features in multi-valent field that contains answer entry information, we propose the final target score of HaFMRank as follows: p yHA_FM (x) = w0 + wixi i=1 pp aij(αifi vi i=1 j=i+1 αifj vj)xixj where p ∈ Rk denotes the weights for the prediction layer
Summary
This decade of years has seen the prosperity of numerous online systems that support question answering (Q&A) activities. Crowdsourcing-based Community Question Answering (CQA) forums provide platforms for people to share and obtain knowledge in the form of asking and answering questions. Existing CQA forums can be roughly divided into two categories: open-domain oriented and specific-domain oriented. The associate editor coordinating the review of this manuscript and approving it for publication was Guanjun Liu. of topics, such as Yahoo! Baidu Knows, Quora and Zhihu, are useful information sources for common internet users to broaden the scope of knowledge. Q&A sites related to specific domains, like Stack Exchange networks, are popular communities that gather professionals and amateurs for exchanging ideas on specific issues. Despite the rapid growth in popularity, CQA faces a number of unique
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.