SemanticZ at SemEval-2016 Task 3: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings
SemanticZ at SemEval-2016 Task 3: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings
复制标题
DOI：
10.18653/v1/s16-1136
复制
发表时间：
2016-06
期刊：
影响因子：
--
通讯作者：
Todor Mihaylov;Preslav Nakov
中科院分区：
文献类型：
--
作者：
Todor Mihaylov;Preslav Nakov
我们描述了在社区论坛中寻找良好答案的系统，如 SemEval-2016 中定义的，询问 3 社区问答。我们的方法依赖于基于微调词嵌入和主题相似性的几个语义相似性特征。在主要子任务 C 中，我们的初次提交排名第三，MAP 为 51.68，准确度为 69.94。在子任务 A 中，我们的初次提交也是第三名，MAP 为 77.58，准确度为 73.39。
We describe our system for finding good answers in a community forum, as defined in SemEval-2016, ask 3 on Community Question Answering. Our approach relies on several semantic similarity features based on fine-tuned word embeddings and topics similarities. In the main Subtask C, our primary submission was ranked third, with a MAP of 51.68 and accuracy of 69.94. In Subtask A, our primary submission was also third, with MAP of 77.58 and accuracy of 73.39.