TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Conversation Disentanglement	irc-disentanglement	BERT + BiLSTM	VI	93.3	# 1
Conversation Disentanglement	irc-disentanglement	BERT + BiLSTM	P	44.3	# 2
Conversation Disentanglement	irc-disentanglement	BERT + BiLSTM	R	49.6	# 1
Conversation Disentanglement	irc-disentanglement	BERT + BiLSTM	F	46.8	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/pre-trained-and-attention-based-neural/conversation-disentanglement-on-irc)](https://paperswithcode.com/sota/conversation-disentanglement-on-irc?p=pre-trained-and-attention-based-neural)`

Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems

4 Apr 2020 · Jia-Chen Gu, Tianda Li, Quan Liu, Xiaodan Zhu, Zhen-Hua Ling, Yu-Ping Ruan ·

The NOESIS II challenge, as the Track 2 of the 8th Dialogue System Technology Challenges (DSTC 8), is the extension of DSTC 7. This track incorporates new elements that are vital for the creation of a deployed task-oriented dialogue system. This paper describes our systems that are evaluated on all subtasks under this challenge. We study the problem of employing pre-trained attention-based network for multi-turn dialogue systems. Meanwhile, several adaptation methods are proposed to adapt the pre-trained language models for multi-turn dialogue systems, in order to keep the intrinsic property of dialogue systems. In the released evaluation results of Track 2 of DSTC 8, our proposed models ranked fourth in subtask 1, third in subtask 2, and first in subtask 3 and subtask 4 respectively.

PDF Abstract