End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Management
Not on the map. Why?
Abstract (arXiv)
Current task-oriented dialog (TOD) systems mostly manage structured knowledge (e.g. databases and tables) to guide the goal-oriented conversations. However, they fall short of handling dialogs which also involve unstructured knowledge (e.g. reviews and documents). In this paper, we formulate a task of modeling TOD grounded on a fusion of structured and unstructured knowledge. To address this task, we propose a TOD system with semi-structured knowledge management, SeKnow, which extends the belief state to manage knowledge with both structured and unstructured contents. Furthermore, we introduce two implementations of SeKnow based on a non-pretrained sequence-to-sequence model and a pretrained language model, respectively. Both implementations use the end-to-end manner to jointly optimize dialog modeling grounded on structured and unstructured knowledge. We conduct experiments on a modified version of MultiWOZ 2.1 dataset, Mod-MultiWOZ 2.1, where dialogs are processed to involve semi-structured knowledge. Experimental results show that SeKnow has strong performances in both end-to-end dialog and intermediate knowledge management, compared to existing TOD systems and their extensions with pipeline knowledge management schemes.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 46 of its 65 references that are in the map. First posted on arXiv 22 Jun 2021.
Builds on
46 of 65 references.
References · 46
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
- 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
- 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
- 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
34 more
- 2018Universal Transformerscited by 613
- 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
- 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
- 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
- 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
- 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
- 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
- 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
- 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 139
- 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
- 2020TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Trackingcited by 130
- 2020MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systemscited by 103
- 2019Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Contextcited by 99
- 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
- 2017Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systemscited by 84
- 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
- 2020CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Datasetcited by 66
- 2020Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Accesscited by 58
- 2018Towards Exploiting Background Knowledge for Building Conversation Systemscited by 57
- 2020A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learningcited by 47
- 2019Structured Fusion Networks for Dialogcited by 40
- 2021Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialogcited by 33
- 2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
- 2020GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systemscited by 29
- 2019MOSS: End-to-End Dialog System Framework with Modular Supervisioncited by 19
- 2020UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialoguescited by 19
- 2019Deep Conversational Recommender in Travelcited by 16
- 2021Learning to Select External Knowledge with Multi-Scale Negative Samplingcited by 16
- 2017Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capabilitycited by 14
- 2021Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9cited by 10
- 2017Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systemscited by 8
- 2017Learning Conversational Systems that Interleave Task and Non-Task Contentcited by 7
- 2021HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Managementcited by 6
- 2020Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systemscited by 5
Built on by
Citing papers per year: 2022: 2; 2023: 1.
3 papers.