mlsanityData to 7 Oct 2026

Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?

arXiv 2212.10504 ↗First posted 20 Dec 2022cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Task-oriented dialogue (TOD) systems are mainly based on the slot-filling-based TOD (SF-TOD) framework, in which dialogues are broken down into smaller, controllable units (i.e., slots) to fulfill a specific task. A series of approaches based on this framework achieved remarkable success on various TOD benchmarks. However, we argue that the current TOD benchmarks are limited to surrogate real-world scenarios and that the current TOD models are still a long way to cover the scenarios. In this position paper, we first identify current status and limitations of SF-TOD systems. After that, we explore the WebTOD framework, the alternative direction for building a scalable TOD system when a web/mobile interface is available. In WebTOD, the dialogue system learns how to understand the web/mobile interface that the human agent interacts with, powered by a large-scale language model.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 57 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

35 of 57 references.

References · 35

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  7. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  8. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  9. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 481
  10. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  11. 2021OCR-free Document Understanding Transformercited by 400
  12. 2022Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understandingcited by 360
23 more
  1. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  2. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  3. 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
  4. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 202
  5. 2020Mapping Natural Language Instructions to Mobile UI Action Sequencescited by 180
  6. 2022CM3: A Causal Masked Multimodal Model of the Internetcited by 142
  7. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
  8. 2019Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overviewcited by 137
  9. 2020Task-Oriented Dialogue as Dataflow Synthesiscited by 122
  10. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  11. 2017Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systemscited by 84
  12. 2020Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Biascited by 82
  13. 2022META-GUI: Towards Multi-modal Conversational Agents on Mobile GUIcited by 81
  14. 2019Efficient Dialogue State Tracking by Selectively Overwriting Memorycited by 76
  15. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
  16. 2021Grounding Open-Domain Instructions to Automate Web Support Taskscited by 43
  17. 2021Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Maskingcited by 22
  18. 2019Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generationcited by 21
  19. 2019Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commandscited by 19
  20. 2022Toward Self-learning End-to-End Task-Oriented Dialog Systemscited by 9
  21. 2020A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk Representationcited by 8
  22. 2022ThingTalk: An Extensible, Executable Representation Language for Task-Oriented Dialoguescited by 6
  23. 2022Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257