SOTAVerified

Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots

2020-04-07Code Available1· sign in to hype

Jia-Chen Gu, Tianda Li, Quan Liu, Zhen-Hua Ling, Zhiming Su, Si Wei, Xiaodan Zhu

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots. A new model, named Speaker-Aware BERT (SA-BERT), is proposed in order to make the model aware of the speaker change information, which is an important and intrinsic property of multi-turn dialogues. Furthermore, a speaker-aware disentanglement strategy is proposed to tackle the entangled dialogues. This strategy selects a small number of most important utterances as the filtered context according to the speakers' information in them. Finally, domain adaptation is performed to incorporate the in-domain knowledge into pre-trained language models. Experiments on five public datasets show that our proposed model outperforms the present models on all metrics by large margins and achieves new state-of-the-art performances for multi-turn response selection.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
DoubanSA-BERTMAP0.62Unverified
E-commerceSA-BERTR10@10.7Unverified
RRSSA-BERT+BERT-FPMAP0.7Unverified
RRS Ranking TestSA-BERT+BERT-FPNDCG@30.67Unverified
Ubuntu Dialogue (v1, Ranking)SA-BERTR10@10.86Unverified
Ubuntu IRCSA-BERTAccuracy60.42Unverified

Reproductions