Exploring heterogeneous features for query-focused summarization of categorized community answers
Exploring heterogeneous features for query-focused summarization of categorized community answers
复制标题
DOI：
10.1016/j.ins.2015.10.024
复制
发表时间：
2016-02
期刊：
影响因子：
--
通讯作者：
Wei Wei-Wei;Zhaoyan Ming;Liqiang Nie;Guohui Li;Jianjun Li;Feida Zhu;Tianfeng Shang;Changyin Luo
中科院分区：
文献类型：
--
作者：
Wei Wei-Wei;Zhaoyan Ming;Liqiang Nie;Guohui Li;Jianjun Li;Feida Zhu;Tianfeng Shang;Changyin Luo
基于社区的问答（cQA）是一种流行的在线知识共享网络服务，用户提出问题并获得他人提供的答案。为了加强知识共享，cQA还为用户提供了历史问答对的检索功能。然而，它仍然是无效的，因为检索结果通常是潜在相关问答的排序列表，而不是简洁和信息丰富的答案。为了缓解这个问题，本文提出了一个三层方案，该方案旨在从两个因素（即新颖性和冗余性）来生成以查询为中心的摘要式答案。具体来说，我们首先检索给定查询的一组问答，然后开发一个平滑的朴素贝叶斯模型，通过利用其相关的类别信息来识别答案的主题。接下来，为了计算答案的全局排名分数，我们首先提出了一种基于参数化图的方法，在由答案的异构特征参数化的图上建模马尔可夫随机漫步，然后将排名分数与答案的相关分数结合起来。基于计算的全局排名分数，我们使用两种不同的策略来构建top- k候选答案集，最后在top- k答案的句子集上求解约束优化问题，生成针对用户查询的摘要。与基线相比，现实世界数据的实验证明了我们提出的方法的有效性。
Community-based question answering (cQA) is a popular type ofonlineknowledge-sharing web service where users ask questions and obtain answers contributed by others. To enhance knowledge sharing, cQA also provides users with a retrieval function to access the historical question-answer pairs (QAs). However, it is still ineffective in that the retrieval result is typically a ranking list of potentially relevant QAs, rather than a succinct and informative answer. To alleviate the problem, this paper proposes a three-level scheme, which aims to generate a query-focusedsummary-styleanswer in terms of two factors, i.e.,noveltyandredundancy. Specifically, we first retrieve a set of QAs to the given query, and then develop a smoothed Naive Bayes model to identify the topics of answers, by exploiting their associated category information. Next, to compute the global ranking scores of answers, we first propose a parameterized graph-based method to model a Markov random walk on a graph that is parameterized by the heterogeneous features of answers, and then combine the ranking scores with the relevance scores of answers. Based on the computed global ranking scores, we utilize two different strategies to construct top-Kcandidate answer set, and finally solve a constrained optimization problem on the sentence set of top-Kanswers to generate a summary towards a user’s query. Experiments on real-world data demonstrate the effectiveness of our proposed approach as compared to the baselines.