An Adversarial Learning Framework For A Persona-Based Multi-Turn Dialogue Model

Olabiyi, O.; Khazane, Anish; Salimov, Alan; Mueller, Erik T.

doi:10.18653/v1/w19-2301

Cited by 16 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, under the topic of dialogue personalizing, Zemlyanskiy and Sha (2018) proposed a post-processing method to re-rank candidates generated by beam search, while Olabiyi et al (2019) employed adversarial approaches to solve the consistency problem on interlocutors' names. Madotto et al (2019) applied meta-learning to quickly adapt to new speakers, and Tigunova et al (2019) extracted user attributes from daily dialogues.…”

Section: Related Workmentioning

confidence: 99%

You Impress Me: Dialogue Generation via Mutual Persona Perception

Liu¹,

Chen²,

Chen³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

111

View full text Add to dashboard Cite

Despite the continuing efforts to improve the engagingness and consistency of chitchat dialogue systems, the majority of current work simply focus on mimicking human-like responses, leaving understudied the aspects of modeling understanding between interlocutors. The research in cognitive science, instead, suggests that understanding is an essential signal for a high-quality chitchat conversation. Motivated by this, we propose P 2 BOT, a transmitter-receiver based framework with the aim of explicitly modeling understanding. Specifically, P 2 BOT incorporates mutual persona perception to enhance the quality of personalized dialogue generation. Experiments on a large public dataset, PERSONA-CHAT, demonstrate the effectiveness of our approach, with a considerable boost over the state-of-theart baselines across both automatic metrics and human evaluations.

show abstract

Section: Related Workmentioning

confidence: 99%

You Impress Me: Dialogue Generation via Mutual Persona Perception

Liu¹,

Chen²,

Chen³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

111

View full text Add to dashboard Cite

show abstract

“…There are various kinds of background knowledge that can be grounded in dialogue modeling, including commonsense items from knowledge graphs to strengthen reasoning ability [Zhang et al, 2021a], persona-based attributes such as speaker identity, dialogue topic, speaker sentiments, to enrich the dialogue context [Olabiyi et al, 2019], scenario information to provide the dialogue background [Ouyang et al, 2020], etc.…”

Section: Background Knowledge Groundingmentioning

confidence: 99%

Advances in Multi-turn Dialogue Comprehension: A Survey

Zhang,

Zhao

2021

Preprint

View full text Add to dashboard Cite

Training machines to understand natural language and interact with humans is an elusive and essential task in the field of artificial intelligence. In recent years, a diversity of dialogue systems has been designed with the rapid development of deep learning researches, especially the recent pre-trained language models. Among these studies, the fundamental yet challenging part is dialogue comprehension whose role is to teach the machines to read and comprehend the dialogue context before responding. In this paper, we review the previous methods from the perspective of dialogue modeling. We summarize the characteristics and challenges of dialogue comprehension in contrast to plaintext reading comprehension. Then, we discuss three typical patterns of dialogue modeling that are widely-used in dialogue comprehension tasks such as response selection and conversation questionanswering, as well as dialogue-related language modeling techniques to enhance PrLMs in dialogue scenarios. Finally, we highlight the technical advances in recent years and point out the lessons we can learn from the empirical analysis and the prospects towards a new frontier of researches.

show abstract

“…This attribute should be very beneficial to dialogue modeling, especially in multi-turn scenarios. Most of the existing neural dialogue response generation models are based on recurrent neural networks (Sutskever et al, 2014;Vinyals and Le, 2015;Li et al, 2016a;Serban et al, 2016;Xing et al, 2017;Serban et al, 2017b,a;Li et al, 2016b;Zhang et al, 2018a;Olabiyi et al, 2018Olabiyi et al, , 2019a). These models have yielded promising results by generating mostly coherent responses given the dialogue context.…”

Section: Introductionmentioning

confidence: 99%

DLGNet: A Transformer-based Model for Dialogue Response Generation

Oluwatobi¹,

Mueller²

2020

Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI

Self Cite

View full text Add to dashboard Cite

Neural dialogue models, despite their successes, still suffer from lack of relevance, diversity, and in many cases coherence in their generated responses. On the other hand, transformer-based models such as GPT-2 have demonstrated an excellent ability to capture long-range structures in language modeling tasks. In this paper, we present DLGNet, a transformer-based model for dialogue modeling. We specifically examine the use of DL-GNet for multi-turn dialogue response generation. In our experiments, we evaluate DLGNet on the open-domain Movie Triples dataset and the closed-domain Ubuntu Dialogue dataset. DLGNet models, although trained with only the maximum likelihood objective, achieve significant improvements over state-of-the-art multi-turn dialogue models. They also produce best performance to date on the two datasets based on several metrics, including BLEU, ROUGE, and distinct n-gram. Our analysis shows that the performance improvement is mostly due to the combination of (1) the long-range transformer architecture with (2) the injection of random informative paddings. Other contributing factors include the joint modeling of dialogue context and response, and the 100% tokenization coverage from the byte pair encoding (BPE).

show abstract

An Adversarial Learning Framework For A Persona-Based Multi-Turn Dialogue Model

Cited by 16 publications

References 11 publications

You Impress Me: Dialogue Generation via Mutual Persona Perception

You Impress Me: Dialogue Generation via Mutual Persona Perception

Advances in Multi-turn Dialogue Comprehension: A Survey

DLGNet: A Transformer-based Model for Dialogue Response Generation

Contact Info

Product

Resources

About