TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Dialog Relation Extraction	DialogRE	Dual	F1 (v1)	67.3	# 3
Dialog Relation Extraction	DialogRE	Dual	F1c (v1)	61.4	# 3
Dialog Relation Extraction	DialogRE	Dual	F1c (v2)	61.1	# 8
Dialog Relation Extraction	DialogRE	Dual	F1 (v2)	67.1	# 8

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/semantic-representation-for-dialogue-modeling/dialog-relation-extraction-on-dialogre)](https://paperswithcode.com/sota/dialog-relation-extraction-on-dialogre?p=semantic-representation-for-dialogue-modeling)`

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.