Generating Persona Consistent Dialogues by Exploiting Natural Language Inference

By Haoyu Song, Weinan Zhang, Jingwen Hu, Ting-Wei Liu. 2019

85 citations recorded by the source corpus.

Consistency is one of the major challenges faced by dialogue agents. A human-like dialogue agent should not only respond naturally, but also maintain a consistent persona. In this paper, we exploit the advantages of natural language inference (NLI) technique to address the issue of generating persona consistent dialogues. Different from existing work that re-ranks the retrieved responses through an NLI model, we cast the task as a reinforcement learning problem and propose to exploit the NLI signals from response-persona pairs as rewards for the process of dialogue generation. Specifically, our generator employs an attention-based encoder-decoder to generate persona-based responses. Our evaluator consists of two components: an adversarially trained naturalness module and an NLI based consistency module. Moreover, we use another well-performed NLI model in the evaluation of persona-consistency. Experimental results on both human and automatic metrics, including the model-based consistency evaluation, demonstrate that the proposed approach outperforms strong generative baselines, especially in the persona-consistency of generated responses.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Pascale Fung
2. Andrea Madotto
3. Wenliang Dai
4. Nayeon Lee
5. Etsuko Ishii
6. Yan Xu
7. Dan Su
8. Ziwei Ji

In Computer Vision and Pattern Recognition

1. Pascale Fung
2. Wenliang Dai
3. Ziwei Ji
4. Dan Su
5. Iryna Gurevych
6. Edwin Simpson
7. Haolan Zhan
8. Tiezheng Yu

In Natural Language Processing

1. Pascale Fung
2. Andrea Madotto
3. Nayeon Lee
4. Etsuko Ishii
5. Yejin Bang
6. Iryna Gurevych
7. Yan Xu
8. Delong Chen

Citations in the corpus

• Survey of Hallucination in Natural Language Generation (2022, methodology): “Lately, the application of NLI methods [88, 144] or reinforcement learning frameworks [107] have been investigated.”
• Large Language Models: A Survey (2024, unknown): “• Advanced metrics such as PARENT [149], PARENT-T [150], and Knowledge F1 [151] are utilized when structured knowledge sources are available.”
• Improving Factual Consistency Between a Response and Persona Facts (2021, background): “Song et al. (2020) propose an NLI-based reward for persona consistency that calculates a score us-ing only the persona facts with the highest entailment and contradiction probabilities, rather than the whole persona.”
• Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization (2021, methodology): “Besides, it has been used in dialogue systems to measure the logic consistency [32, 48, 53].”