State-Machine-Based Dialogue Agents with Few-Shot Contextual Semantic Parsers

09/16/2020
by   Giovanni Campagna, et al.
0

This paper presents a methodology and toolkit for creating a rule-based multi-domain conversational agent for transactions from (1) language annotations of the domains' database schemas and APIs and (2) a couple of hundreds of annotated human dialogues. There is no need for a large annotated training set, which is expensive to acquire. The toolkit uses a pre-defined abstract dialogue state machine to synthesize millions of dialogues based on the domains' information. The annotated and synthesized data are used to train a contextual semantic parser that interprets the user's latest utterance in the context of a formal representation of the conversation up to that point. Developers can refine the state machine to achieve higher accuracy. On the MultiWOZ benchmark, we achieve over 71 cleaned, reannotated test set, without using any of the original training data. Our state machine can model 96 improves by 9 showing the benefit of synthesizing data using the state machine.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/04/2021

Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues

Robust state tracking for task-oriented dialogue systems currently remai...
research
04/01/2021

MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation

The MultiWOZ 2.0 dataset was released in 2018. It consists of more than ...
research
10/03/2019

Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks

Goal-oriented dialogue systems are now being widely adopted in industry ...
research
04/18/2019

Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands

To understand diverse natural language commands, virtual assistants toda...
research
05/28/2020

ConCET: Entity-Aware Topic Classification for Open-Domain Conversational Agents

Identifying the topic (domain) of each user's utterance in open-domain c...
research
09/12/2023

Widely Interpretable Semantic Representation: Frameless Meaning Representation for Broader Applicability

This paper presents a novel semantic representation, WISeR, that overcom...
research
09/01/2021

Building a Legal Dialogue System: Development Process, Challenges and Opportunities

This paper presents key principles and solutions to the challenges faced...

Please sign up or login with your details

Forgot password? Click here to reset