paper-with-me

홈 › Papers

Dialogue Response Prefetching Based on Semantic Similarity and Prediction Confidence of Language Model

2025-08-06 · Kiyotada Mori, Seiya Kawano, Angel Fernando Garcia Contreras, Koichiro Yoshino arxiv

Prefetching of dialogue responses has been investigated to reduce user-perceived latency (UPL), which refers to the user's waiting time before receiving the system's response, in spoken dialogue systems. To reduce the UPL, it is necessary to predict complete user utterances before the end of the user's speech, typically by language models, to prepare prefetched dialogue responses. In this study, we proposed a prediction confidence model (PCM) that determines whether prefetching is possible or not by estimating the semantic similarity between the predicted complete user utterance and the complete user utterance. We evaluated our PCM based on the differences between the predicted complete user utterance and the complete user utterance.

📄 PDF Abstract BibTeX arXiv:2508.04403

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Similarity

Similar Papers 제목 키워드 기반

Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual Information

2023-05-26 · Kun Zhao, Bohao Yang, Chenghua Lin, Wenge Rong 외

The long-standing one-to-many issue of the open-domain dialogues poses significant challenges for automatic evaluation methods, i.e., there may be multiple suitable responses which differ in semantics for a given convers…

Semantic SimilaritySemantic Textual SimilaritySentence

Personalized Predictive ASR for Latency Reduction in Voice Assistants

2023-05-23 · Andreas Schwarz, Di He, Maarten Van Segbroeck, Mohammed Hethnawi 외

Streaming Automatic Speech Recognition (ASR) in voice assistants can utilize prefetching to partially hide the latency of response generation. Prefetching involves passing a preliminary ASR hypothesis to downstream syste…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Response Generationspeech-recognition+1

ConvoCache: Smart Re-Use of Chatbot Responses

2024-06-26 · Conor Atkins, Ian Wood, Mohamed Ali Kaafar, Hassan Asghar 외

We present ConvoCache, a conversational caching system that solves the problem of slow and expensive generative AI models in spoken chatbots. ConvoCache finds a semantically similar prompt in the past and reuses the resp…

Chatbot

Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation

2021-06-10 · Findings (ACL) 2021 8 · Prakhar Gupta, Yulia Tsvetkov, Jeffrey P. Bigham

Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models gener…

Binary ClassificationDialogue Evaluation

MALA: Cross-Domain Dialogue Generation with Action Learning

2019-12-18 · Xinting Huang, Jianzhong Qi, Yu Sun, Rui Zhang

Response generation for task-oriented dialogues involves two basic components: dialogue planning and surface realization. These two components, however, have a discrepancy in their objectives, i.e., task completion and l…

Dialogue GenerationResponse GenerationSemantic SimilaritySemantic Textual Similarity+1