Online Semantic Parsing for Latency Reduction in Task-Oriented Dialogue
Standard conversational semantic parsing maps a complete user utterance into an executable program, after which the program is executed to respond to the user. This could be slow when the program contains expensive function calls. We investigate the opportunity to reduce latency by predicting and executing function calls while the user is still speaking. We introduce the task of online semantic parsing for this purpose, with a formal latency reduction metric inspired by simultaneous machine translation. We propose a general framework with first a learned prefix-to-program prediction module, and then a simple yet effective thresholding heuristic for subprogram selection for early execution. Experiments on the SMCalFlow and TreeDST datasets show our approach achieves large latency reduction with good parsing quality, with a 30%–65% latency reduction depending on function execution time and allowed cost.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationSemantic ParsingTranslationSimilar Papers 제목 키워드 기반
Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog
Semantic parsing using sequence-to-sequence models allows parsing of deeper representations compared to traditional word tagging based models. In spite of these advantages, widespread adoption of these models for real-ti…
Semantic ParsingSpan Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing
An effective recipe for building seq2seq, non-autoregressive, task-oriented parsers to map utterances to semantic frames proceeds in three steps: encoding an utterance $x$, predicting a frame's length |y|, and decoding a…
Cross-Lingual TransferDecoderPredictionQuantization+2SCOPE: Tree-based Self-Correcting Online Log Parsing via Syntactic-Semantic Collaboration
Log parsing is a critical step for automated log analysis in complex systems. Traditional heuristic-based methods offer high efficiency but are limited in accuracy due to overlooking semantic context. In contrast, recent…
Federated Learning for Semantic Parsing: Task Formulation, Evaluation Setup, New Algorithms
This paper studies a new task of federated learning (FL) for semantic parsing, where multiple clients collaboratively train one global model without sharing their semantic parsing data. By leveraging data from multiple c…
Federated LearningSemantic ParsingText to SQLText-To-SQLQUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning
This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) tasks. Our investigation reveals that conven…
Language ModelingLanguage ModellingVision-Language-Action