Semantic Representation for Dialogue Modeling

ACL 2021  ·  Xuefeng Bai, Yulong Chen, Linfeng Song, Yue Zhang ·

Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities. To this end, we exploit Abstract Meaning Representation (AMR) to help dialogue modeling. Compared with the textual input, AMR explicitly provides core semantic knowledge and reduces data sparsity. We develop an algorithm to construct dialogue-level AMR graphs from sentence-level AMRs and explore two ways to incorporate AMRs into dialogue systems. Experimental results on both dialogue understanding and response generation tasks show the superiority of our model. To our knowledge, we are the first to leverage a formal semantic representation into neural dialogue modeling.

PDF Abstract ACL 2021 PDF ACL 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Dialog Relation Extraction DialogRE Dual F1 (v1) 67.3 # 1
F1c (v1) 61.4 # 1
F1c (v2) 61.1 # 4
F1 (v2) 67.1 # 4

Methods


No methods listed for this paper. Add relevant methods here