早比晚好：融合主题与词嵌入的神经问题释义识别
Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification
摘要：
问题释义识别是社区问答（CQA）中的一项关键任务，用于确定传入的问题之前是否被询问过。许多当前的模型使用词嵌入来识别重复的问题，但在功能工程系统中使用主题模型表明，它们也可以帮助完成这项任务。因此，我们提出了两种方式合并主题与词嵌入（早期与晚期融合）在一个新的神经架构的问题释义识别。我们的研究结果表明，我们的系统在多个CQA数据集上的表现优于神经基线，而消融研究强调了主题的重要性，特别是在我们的架构中早期主题嵌入融合。
英文摘要：
Question paraphrase identification is a key task in Community Question Answering (CQA) to determine if an incoming question has been previously asked. Many current models use word embeddings to identify duplicate questions, but the use of topic models in feature-engineered systems suggests that they can be helpful for this task, too. We therefore propose two ways of merging topics with word embeddings (early vs. late fusion) in a new neural architecture for question paraphrase identification. Our results show that our system outperforms neural baselines on multiple CQA datasets, while an ablation study highlights the importance of topics and especially early topic-embedding fusion in our architecture.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
