End-to-End Task-Oriented Dialog System Through Template Slot Value Generation

End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task. While in non-collaborative settings, for example, negotiation and persuasion, users and systems do not share a common goal. As a result, compared to collaborate tasks, people use social content to build rapport and trust in these non-collaborative settings in order to advance their goals. To handle social content, we introduce a hierarchical intent annotation scheme, which can be generalized to different non-collaborative dialog tasks. Building upon TransferTransfo (Wolf et al. 2019), we propose an end-to-end neural network model to generate diverse coherent responses. Our model utilizes intent and semantic slots as the intermediate sentence representation to guide the generation process. In addition, we design a filter to select appropriate responses based on whether these intermediate representations fit the designed task and conversation constraints. Our non-collaborative dialog model guides users to complete the task while simultaneously keeps them engaged. We test our approach on our newly proposed AntiScam dataset and an existing PersuasionForGood dataset. Both automatic and human evaluations suggest that our model outperforms multiple baselines in these two non-collaborative tasks.

Download Full-text

MOSS: End-to-End Dialog System Framework with Modular Supervision

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6349 ◽

2020 ◽

Vol 34 (05) ◽

pp. 8327-8335

Author(s):

Weixin Liang ◽

Youzhi Tian ◽

Chengcai Chen ◽

Zhou Yu

Keyword(s):

Natural Language ◽

Customer Service ◽

State Of The Art ◽

Training Data ◽

Language Understanding ◽

Language Generation ◽

Dialog System ◽

Major Bottleneck ◽

End To End ◽

Task Oriented

A major bottleneck in training end-to-end task-oriented dialog system is the lack of data. To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an encoder-decoder training framework that could incorporate supervision from various intermediate dialog system modules including natural language understanding, dialog state tracking, dialog policy learning and natural language generation. With only 60% of the training data, MOSS-all (i.e., MOSS with supervision from all four dialog modules) outperforms state-of-the-art models on CamRest676. Moreover, introducing modular supervision has even bigger benefits when the dialog task has a more complex dialog state and action space. With only 40% of the training data, MOSS-all outperforms the state-of-the-art model on a complex laptop network trouble shooting dataset, LaptopNetwork, that we introduced. LaptopNetwork consists of conversations between real customers and customer service agents in Chinese. Moreover, MOSS framework can accommodate dialogs that have supervision from different dialog modules at both framework level and model level. Therefore, MOSS is extremely flexible to update in real-world deployment.

Download Full-text

Learning Personalized End-to-End Task-Oriented Dialogue Generation

Natural Language Processing and Chinese Computing - Lecture Notes in Computer Science ◽

10.1007/978-3-030-32233-5_5 ◽

2019 ◽

pp. 55-66

Author(s):

Bowen Zhang ◽

Xiaofei Xu ◽

Xutao Li ◽

Yunming Ye ◽

Xiaojun Chen ◽

...

Keyword(s):

End To End ◽

Task Oriented

Download Full-text

HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management

10.18653/v1/2021.findings-acl.139 ◽

2021 ◽

Author(s):

Silin Gao ◽

Ryuichi Takanobu ◽

Wei Peng ◽

Qun Liu ◽

Minlie Huang

Keyword(s):

Knowledge Management ◽

Hybrid Knowledge ◽

End To End ◽

Task Oriented

Download Full-text

End-to-end optimization of goal-driven and visually grounded dialogue systems

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2017/385 ◽

2017 ◽

Cited By ~ 16

Author(s):

Florian Strub ◽

Harm de Vries ◽

Jérémie Mary ◽

Bilal Piot ◽

Aaron Courville ◽

...

Keyword(s):

Gradient Algorithm ◽

Planning Problem ◽

Dialogue Systems ◽

Generation Task ◽

Policy Gradient ◽

Specific Object ◽

Complex Picture ◽

History Of ◽

End To End ◽

Task Oriented

End-to-end design of dialogue systems has recently become a popular research topic thanks to powerful tools such as encoder-decoder architectures for sequence-to-sequence learning. Yet, most current approaches cast human-machine dialogue management as a supervised learning problem, aiming at predicting the next utterance of a participant given the full history of the dialogue. This vision may fail to correctly render the planning problem inherent to dialogue as well as its contextual and grounded nature. In this paper, we introduce a Deep Reinforcement Learning method to optimize visually grounded task-oriented dialogues, based on the policy gradient algorithm. This approach is tested on the question generation task from the dataset GuessWhat?! containing 120k dialogues and provides encouraging results at solving both the problem of generating natural dialogues and the task of discovering a specific object in a complex picture.

Download Full-text