TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Task-Oriented Dialogue Systems	KVRET	DSR	Entity F1	51.9	# 7
Task-Oriented Dialogue Systems	KVRET	DSR	BLEU	12.7	# 8

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/sequence-to-sequence-learning-for-task/task-oriented-dialogue-systems-on-kvret)](https://paperswithcode.com/sota/task-oriented-dialogue-systems-on-kvret?p=sequence-to-sequence-learning-for-task)`

Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation

COLING 2018 · Haoyang Wen, Yijia Liu, Wanxiang Che, Libo Qin, Ting Liu ·

Classic pipeline models for task-oriented dialogue system require explicit modeling the dialogue states and hand-crafted action spaces to query a domain-specific knowledge base. Conversely, sequence-to-sequence models learn to map dialogue history to the response in current turn without explicit knowledge base querying. In this work, we propose a novel framework that leverages the advantages of classic pipeline and sequence-to-sequence models. Our framework models a dialogue state as a fixed-size distributed representation and use this representation to query a knowledge base via an attention mechanism. Experiment on Stanford Multi-turn Multi-domain Task-oriented Dialogue Dataset shows that our framework significantly outperforms other sequence-to-sequence based baseline models on both automatic and human evaluation.