HCA: Hierarchical Compare Aggregate model for question retrieval in community question answering

作者：

Highlights：

• We propose a Hierarchical Compare Aggregate (HCA) model for question retrieval in CQA

• The HCA-model can handle the lengthy question with multiple noisy sentences

• To solve the limited training data, we propose using a sequential transfer learning

• The HCA-model does not require any external resources and task-specific features

• The HCA-model achieves the best results in the both public-domain SemEval datasets and the domain-specific AskUbuntu dataset

摘要

•We propose a Hierarchical Compare Aggregate (HCA) model for question retrieval in CQA•The HCA-model can handle the lengthy question with multiple noisy sentences•To solve the limited training data, we propose using a sequential transfer learning•The HCA-model does not require any external resources and task-specific features•The HCA-model achieves the best results in the both public-domain SemEval datasets and the domain-specific AskUbuntu dataset

论文关键词：Community question answering,Question retrieval,Hierarchical compare-aggregate model,Transfer learning,Deep learning

论文评审过程：Received 10 September 2019, Revised 26 April 2020, Accepted 31 May 2020, Available online 18 June 2020, Version of Record 18 June 2020.

论文官网地址：https://doi.org/10.1016/j.ipm.2020.102318