arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.12866cs.CLcs.AI
收藏

基于分层自注意的语义条件对话响应生成

Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention

Tencent AI Lab(腾讯人工智能实验室);Beijing University of Posts and Telecommunications(北京邮电大学);University of California, Santa Barbara(加州大学圣巴巴拉分校)

Wenhu Chen, Jianshu Chen, Pengda Qin, Xifeng Yan, William Yang Wang

摘要:

有限域上的语义控制神经响应生成已经取得了很好的性能。然而,走向多领域的大规模的情况下,被证明是困难的,因为可能的组合的语义输入增长与域的数量呈指数级。为了缓解这种可扩展性问题,我们利用对话行为的结构来构建一个多层的层次图,其中每个行为表示为图上的根到叶路由。然后,我们将这样的图结构作为一个归纳偏见,建立一个层次化的解开自我注意力网络,在那里我们解开注意力头来模拟对话行为图上的指定节点。通过在每一层激活不同的(解开的)头,可以组合地对许多对话行为语义进行建模以控制神经响应生成。在大规模的多领域WOZ数据集上,我们的模型可以在各种自动和人工评估指标上产生比基线显著的改进。

英文摘要:

Semantically controlled neural response generation on limited-domain has achieved great performance. However, moving towards multi-domain large-scale scenarios are shown to be difficult because the possible combinations of semantic inputs grow exponentially with the number of domains. To alleviate such scalability issue, we exploit the structure of dialog acts to build a multi-layer hierarchical graph, where each act is represented as a root-to-leaf route on the graph. Then, we incorporate such graph structure prior as an inductive bias to build a hierarchical disentangled self-attention network, where we disentangle attention heads to model designated nodes on the dialog act graph. By activating different (disentangled) heads at each layer, combinatorially many dialog act semantics can be modeled to control the neural response generation. On the large-scale Multi-Domain-WOZ dataset, our model can yield a significant improvement over the baselines on various automatic and human evaluation metrics.

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。

↑