Joint modeling of users, questions and answers for answer selection in CQA

Abstract

In this paper, we propose solutions to advance answer selection in Community Question Answering (CQA). Automatically selecting correct answers can significantly improve intelligence for CQA, as users are not required to browse the large quantity of texts and select the right answers manually. Also, automatic answers selection can minimize the time for satisfying users seeking the correct answers and maximize user engagement with the site.Unlike previous works, we propose a hybrid attention mechanism to model question-answer pairs. Specifically, for each word, we calculate the intra-sentence attention indicating its local importance and the inter-sentence attention implying its importance to the counterpart sentence. The inter-sentence attention is based on the interactions between question-answer pairs, and the combination of these two attention mechanisms enables us to align the most informative parts in question-answer pairs for sentence matching. Additionally, we exploit user information for answer selection due to the fact that users are more likely to provide correct answers in their areas of expertise. We model users from their written answers to alleviate data sparsity problem, and then learn user representations according to the informative parts in sentences that are useful for question-answer matching task. This mean of modelling users can bridge the semantic gap between different users, as similar users may have the same way of wording their answers. The representations of users, questions and answers are learnt in an end-to-end neural network in a mean that best explains the interrelation between question-answer pairs. We validate the proposed model on a public dataset, and demonstrate its advantages over the baselines with thorough experiments.

Coming to Grips with Age Prediction on Imbalanced Multimodal Community Question Answering Data

“…Recent research topics regarding cQA users relate to modeling their areas of expertise and quantifying their impacts on answer selection [3]; how the evolution of their roles in the community impacts the content relevance between the answerer and the question [4]; the intimacy between askers and answerers [5]. From another angle, current research has focused its attention on discovering informative features of genuine experts [6][7][8], and discovering patterns of interactions between community fellows [9].…”

A hybrid MCDM model combining DANP with TODIM to evaluate the information quality of community question answering in a two‐dimensional linguistic environment

“…With the rapid development of Web 2.0, community question answering (cQA) has become a new platform for information seeking and sharing (Wen, Tu, Cheng, Xie, & Yin, 2019). Given its openness and convenience, cQA attracts millions of users, and many cQA websites have emerged (Li, Lu, Chen, & Wang, 2020).…”

Hybrid CNN-LSTM Model for Answer Identification

“…So as to offer high quality experts, several traditional techniques learn the user representation from their previous QA [17] activities in CQA systems. On the other hand, the previous performances of users in the majority of CQA [18] [19] systems are quite limited, and therefore the user representation might was not properly modelled. Answer assortment in CQA [20] is to identify relevant or good answers for producing constructive QA [21] pairs that are important to develop the knowledge base of numerous intelligent systems, such as, chatbot or automatic QA.…”