End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

We propose a novel problem within end-to-end learning of task-oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e.g., car not starting). Such dialogs are grounded in domain-specific flowcharts, which the agent is supposed to follow during the conversation. Our task exposes novel technical challenges for neural TOD, such as grounding an utterance to the flowchart without explicit annotation, referring to additional manual pages when user asks a clarification question, and ability to follow unseen flowcharts at test time. We release a dataset (FloDial) consisting of 2,738 dialogs grounded on 12 different troubleshooting flowcharts. We also design a neural model, FloNet, which uses a retrieval-augmented generation architecture to train the dialog agent. Our experiments find that FloNet can do zero-shot transfer to unseen flowcharts, and sets a strong baseline for future research.

PDF Abstract EMNLP 2021 PDF EMNLP 2021 Abstract


Introduced in the Paper:

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Flowchart Grounded Dialog Response Generation FloDial FloNet BLEU-4 19.46 # 1
PPL 3.79 # 1
Success Rate 0.337 # 1
Zero-Shot Flowchart Grounded Dialog Response Generation FloDial FloNet BLEU-4 16.31 # 1
PPL 4.94 # 1
Success Rate 0.125 # 1


No methods listed for this paper. Add relevant methods here