中文知识库问答中的路径选择

路径选择是知识库问答任务的关键步骤,语义相似度常被用来计算路径对于问句的相似度得分。针对测试集中存在大量未见的关系,该文提出使用一种负例动态采样的语义相似度模型的训练方法,去丰富训练集中关系的多样性,模型性能得到显著提升。针对复杂问题候选路径数量组合爆炸问题,该文比较了两种路径剪枝方法,即基于分类的方法和基于集束搜索的方法。在包含简单问题和复杂问题的CCKS 2019-CKBQA评测数据集上,该方法能达到较优异的性能,测试集上单模型系统平均F₁值达到0.694,系统融合后达到0.731。

Path Selection for Chinese Knowledge Base Question Answering

Path selection, as a key step in the Knowledge Base Question Answering (KBQA) task, relies on the the semantic similarity between a question and candidate paths. To deal with massive unseen relations in the test set, a method based on dynamic sampling of negative examples is proposed to enrich the relations in the training set. In the prediction phase, two path pruning methods, i.e., the classification method and the beam search method, are compared to tackle the explosion of candidate paths. On the CCKS 2019-CKBQA evaluation data set containing simple and complex problems, the proposed method achieves an average F₁ value of 0.694 for the single-model system, and 0.731 for the ensemble system.