-
摘要: 描述了一种新的计算问题与支持答案句相似度的方法, 即基于依赖关系三元组匹配的方法. 该方法引入了问题中的疑问性和非疑问性部分的信息, 采用了启发式规则扩展问题的依赖关系三元组, 从而匹配变形的答案句. 同时把问题与支持答案句的相似度作为新的特征, 应用于开放领域的问题回答(Question answering, QA)任务中的答案排序. 实验结果表明, 引入新特征的答案排序方法与通常的基于密度的方法相比, 在相对精度指标上提高了8.2%, 在平均排序倒数(Mean reciprocal rank, MRR)评价上提高了8%.Abstract: This paper presents a new method to compute the similarity between question and answer sentences, namely dependency relation triples matching. This method considers the information of question's interrogative part and non-interrogative part, and heuristic rules are used to expand question's relation triples to match metamorphosing answer sentences. Then, this similarity score is used as a new feature for answer ranking in open domain question answering (QA) track. The experiments show the new answer ranking method outperforms the common density-based approach by up to 8.2% in relative precision and 8% in mean reciprocal rank (MRR) evaluation.
-
Key words:
- Question answering /
- answering ranking /
- dependency relation triple
点击查看大图
计量
- 文章访问数: 2220
- HTML全文浏览量: 32
- PDF下载量: 1289
- 被引次数: 0