Digital Assistant Reference Resolution for Ambiguous User Utterances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Digital assistants struggle to accurately interpret user utterances containing ambiguous references, leading to inefficiencies and increased power consumption due to the need for clarification.
Innovation Solution
A digital assistant system that utilizes a reference resolution service to determine a set of possible entities, analyze user utterances for ambiguous references, and perform tasks based on candidate interpretations, thereby clarifying user intent without additional input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the digital assistant requests clarification for ambiguous references, then the accuracy of task execution is improved, but the number of interactions increases and power consumption rises
Solution Approach 1:
The system performs preliminary resolution of ambiguous references by analyzing the user utterance against a knowledge base of entities and relationships before task execution. This preliminary action identifies the most likely intended entity, allowing the system to proceed with task execution without requiring additional clarification interactions, thereby reducing interaction count while maintaining execution accuracy
2Measurement precision
If the digital assistant requests clarification for ambiguous references, then the accuracy of task execution is improved, but power consumption increases
Solution Approach 1:
The system performs preliminary resolution of ambiguous references by analyzing the user utterance against a knowledge base of entities and relationships before task execution. This preliminary action identifies the most likely intended entity, allowing the system to proceed with task execution without requiring additional clarification interactions, thereby reducing interaction count and associated power consumption
3Measurement precision
If the digital assistant uses reference resolution service to analyze user utterance, then the accuracy of understanding user intent is improved, but the processing complexity increases
Solution Approach 1:
The reference resolution process is segmented into distinct stages: extracting entities from the utterance, querying the knowledge base for candidate entities, resolving ambiguities based on contextual relationships, and selecting the most likely intended entity. This segmentation allows the complex processing to be managed in manageable steps, improving accuracy while controlling processing complexity
Data Source
AI summary
Systems and processes for operating a digital assistant are provided. An example method includes, at an electronic device having one or more processors and memory, detecting invocation of a digital assistant; determining, using a reference resolution service, a set of possible entities; receiving a user utterance including an ambiguous reference; determining based on the user utterance and the list of possible entities, a candidate interpretation including a preliminary set of entities corresponding to the ambiguous reference; determining, with the reference resolution service and based on the candidate interpretation including the preliminary set of entities corresponding to the ambiguous reference, an entity corresponding to the ambiguous reference; and performing, based on the candidate interpretation and the entity corresponding to the ambiguous reference, a task associated with the user utterance.