Coherent Dialogue with Attention-Based Language Models

Mei, Hongyuan; Bansal, Mohit; Walter, Matthew R.

doi:10.1609/aaai.v31i1.10961

Cited by 33 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent developments in deep learning have led to end-to-end approaches to dialogue using supervised learning, such as sequence-to-sequence models (Dušek and Jurcicek, 2016;Eric and Manning, 2017), hierarchical models (Serban et al, 2017), attention (Mei et al, 2017;Chen et al, 2019), andTransformer-based models (Wu et al, 2021;Hosseini-Asl et al, 2020;Peng et al, 2020;Adiwardana et al, 2020). However, supervised learning only allows an agent to imitate behaviors, requires optimal data, and does not allow agents to exceed human performance.…”

Section: Related Workmentioning

confidence: 99%

CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning

Verma¹,

Fu²,

Yang³

et al. 2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Conventionally, generation of natural language for dialogue agents may be viewed as a statistical learning problem: determine the patterns in human-provided data and generate appropriate responses with similar statistical properties. However, dialogue can also be regarded as a goal directed process, where speakers attempt to accomplish a specific task. Reinforcement learning (RL) algorithms are designed specifically for solving such goal-directed problems, but the most direct way to apply RLthrough trial-and-error learning in human conversations, -is costly. In this paper, we study how offline reinforcement learning can instead be used to train dialogue agents entirely using static datasets collected from human speakers. Our experiments show that recently developed offline RL methods can be combined with language models to yield realistic dialogue agents that better accomplish task goals.

show abstract

Section: Related Workmentioning

confidence: 99%

CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning

Verma¹,

Fu²,

Yang³

et al. 2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…Constrained recurrent models are also used to generate online product reviews of certain topic, sentiment, style and length [28], affective dialogue responses [40], or for modeling participant roles and topics in conversational systems [102].…”

Section: E Adapting Existing Models and Architectures To Accommodate ...mentioning

confidence: 99%

Why is constrained neural language generation particularly challenging?

Gârbacea¹,

Mei²

2022

Preprint

View full text Add to dashboard Cite

Recent advances in deep neural language models combined with the capacity of large scale datasets have accelerated the development of natural language generation systems that produce fluent and coherent texts (to various degrees of success) in a multitude of tasks and application contexts. However, controlling the output of these models for desired user and task needs is still an open challenge. This is crucial not only to customizing the content and style of the generated language, but also to their safe and reliable deployment in the real world. We present an extensive survey on the emerging topic of constrained neural language generation in which we formally define and categorize the problems of natural language generation by distinguishing between conditions and constraints (the latter being testable conditions on the output text instead of the input), present constrained text generation tasks, and review existing methods and evaluation metrics for constrained text generation. Our aim is to highlight recent progress and trends in this emerging field, informing on the most promising directions and limitations towards advancing the state-of-the-art of constrained neural language generation research.

show abstract

“…Recently, short text conversation has been popular. The system receives a short dialog context and generates a response using statistical machine translation or seq-to-seq networks (Ritter, Cherry, and Dolan 2011;Vinyals and Le 2015;Shang, Lu, and Li 2015;Serban et al 2016;Li et al 2016;Mei, Bansal, and Walter 2017). In contrast to response generation, the retrieval-based approach uses a ranking model to select the highest scoring response from candidates (Lu and Li 2013;Hu et al 2014;Ji, Lu, and Li 2014;Wang et al 2015).…”

Section: Related Workmentioning

confidence: 99%

Addressee and Response Selection in Multi-Party Conversations With Speaker Interaction RNNs

Zhang

Lee

Polymenakos³

et al. 2018

AAAI

View full text Add to dashboard Cite

In this paper, we study the problem of addressee and response selection in multi-party conversations. Understanding multi-party conversations is challenging because of complex speaker interactions: multiple speakers exchange messages with each other, playing different roles (sender, addressee, observer), and these roles vary across turns. To tackle this challenge, we propose the Speaker Interaction Recurrent Neural Network (SI-RNN). Whereas the previous state-of-the-art system updated speaker embeddings only for the sender, SI-RNN uses a novel dialog encoder to update speaker embeddings in a role-sensitive way. Additionally, unlike the previous work that selected the addressee and response separately, SI-RNN selects them jointly by viewing the task as a sequence prediction problem. Experimental results show that SI-RNN significantly improves the accuracy of addressee and response selection, particularly in complex conversations with many speakers and responses to distant messages many turns in the past.

show abstract

Coherent Dialogue with Attention-Based Language Models

Cited by 33 publications

References 25 publications

CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning

CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning

Why is constrained neural language generation particularly challenging?

Addressee and Response Selection in Multi-Party Conversations With Speaker Interaction RNNs

Contact Info

Product

Resources

About