Towards Robust Online Dialogue Response Generation

03/07/2022
by   Leyang Cui, et al.
0

Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings. We argue that this can be caused by a discrepancy between training and real-world testing. At training time, chatbot generates the response with the golden context, while it has to generate based on the context consisting of both user utterances and the model predicted utterances during real-world testing. With the growth of the number of utterances, this discrepancy becomes more serious in the multi-turn settings. In this paper, we propose a hierarchical sampling-based method consisting of both utterance-level sampling and semi-utterance-level sampling, to alleviate the discrepancy, which implicitly increases the dialogue coherence. We further adopt reinforcement learning and re-ranking methods to explicitly optimize the dialogue coherence during training and inference, respectively. Empirical experiments show the effectiveness of the proposed methods for improving the robustness of chatbots in real practice.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/03/2020

DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances

Recent advances in pre-trained language models have significantly improv...
research
09/11/2018

Detecting egregious responses in neural sequence-to-sequence models

In this work, we attempt to answer a critical question: whether there ex...
research
06/12/2021

Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring

Dialogue topic segmentation is critical in several dialogue modeling pro...
research
06/01/2019

Multi-Turn Beam Search for Neural Dialogue Modeling

In neural dialogue modeling, a neural network is trained to predict the ...
research
05/06/2022

Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances

Each utterance in multi-turn empathetic dialogues has features such as e...
research
08/13/2020

Ranking Enhanced Dialogue Generation

How to effectively utilize the dialogue history is a crucial problem in ...
research
12/21/2020

A Graph Reasoning Network for Multi-turn Response Selection via Customized Pre-training

We investigate response selection for multi-turn conversation in retriev...

Please sign up or login with your details

Forgot password? Click here to reset