中文
相关论文

相关论文: Capture Salient Historical Information: A Fast and…

200 篇论文

Spoken Language Understanding (SLU), a core component of the task-oriented dialogue system, expects a shorter inference latency due to the impatience of humans. Non-autoregressive SLU models clearly increase the inference speed but suffer…

计算与语言 · 计算机科学 2021-08-17 Lizhi Cheng , Weijia Jia , Wenmian Yang

We propose two methods to capture relevant history information in a multi-turn dialogue by modeling inter-speaker relationship for spoken language understanding (SLU). Our methods are tailored for and therefore compatible with XLNet, which…

计算与语言 · 计算机科学 2019-10-29 Jonggu Kim , Jong-Hyeok Lee

Multi-Intent Spoken Language Understanding (SLU), a novel and more complex scenario of SLU, is attracting increasing attention. Unlike traditional SLU, each intent in this scenario has its specific scope. Semantic information outside the…

计算与语言 · 计算机科学 2022-11-23 Lizhi Cheng , Wenmian Yang , Weijia Jia

Spoken language understanding (SLU), which is a core component of the task-oriented dialogue system, has made substantial progress in the research of single-turn dialogue. However, the performance in multi-turn dialogue is still not…

计算与语言 · 计算机科学 2021-03-11 Lizhi Cheng , Weijia Jia , Wenmian Yang

Spoken language understanding (SLU) is a key component of task-oriented dialogue systems. SLU parses natural language user utterances into semantic frames. Previous work has shown that incorporating context information significantly…

计算与语言 · 计算机科学 2020-03-04 Qian Chen , Zhu Zhuo , Wen Wang , Qiuyun Xu

Spoken language understanding (SLU) is an essential component in conversational systems. Most SLU component treats each utterance independently, and then the following components aggregate the multi-turn information in the separate phases.…

计算与语言 · 计算机科学 2017-12-12 Po-Chun Chen , Ta-Chung Chi , Shang-Yu Su , Yun-Nung Chen

End-to-end spoken language understanding (SLU) systems that process human-human or human-computer interactions are often context independent and process each turn of a conversation independently. Spoken conversations on the other hand, are…

计算与语言 · 计算机科学 2021-08-20 Jatin Ganhotra , Samuel Thomas , Hong-Kwang J. Kuo , Sachindra Joshi , George Saon , Zoltán Tüske , Brian Kingsbury

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…

计算与语言 · 计算机科学 2025-06-05 Zichuan Fu , Wentao Song , Yejing Wang , Xian Wu , Yefeng Zheng , Yingying Zhang , Derong Xu , Xuetao Wei , Tong Xu , Xiangyu Zhao

Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consistency and scalability. As conversations lengthen, essential information becomes sparse and…

计算与语言 · 计算机科学 2026-05-15 Renning Pang , Tian Lan , Leyuan Liu , Xiaoming Huang , Piao Tong , Xiaosong Zhang

Modern spoken language understanding (SLU) systems rely on sophisticated semantic notions revealed in single utterances to detect intents and slots. However, they lack the capability of modeling multi-turn dynamics within a dialogue…

计算与语言 · 计算机科学 2022-05-31 Ting-Wei Wu , Biing-Hwang Juang

Most human interactions occur in the form of spoken conversations where the semantic meaning of a given utterance depends on the context. Each utterance in spoken conversation can be represented by many semantic and speaker attributes, and…

计算与语言 · 计算机科学 2023-05-02 Siddhant Arora , Hayato Futami , Emiru Tsunoo , Brian Yan , Shinji Watanabe

Spoken Language Understanding (SLU) is a key component of goal oriented dialogue systems that would parse user utterances into semantic frame representations. Traditionally SLU does not utilize the dialogue history beyond the previous…

计算与语言 · 计算机科学 2017-07-11 Ankur Bapna , Gokhan Tur , Dilek Hakkani-Tur , Larry Heck

Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…

音频与语音处理 · 电气工程与系统科学 2022-06-28 Yingying Gao , Junlan Feng , Chao Deng , Shilei Zhang

Language Models (LMs) have been ubiquitously leveraged in various tasks including spoken language understanding (SLU). Spoken language requires careful understanding of speaker interactions, dialog states and speech induced multimodal…

计算与语言 · 计算机科学 2021-09-22 Ayush Kumar , Mukuntha Narayanan Sundararaman , Jithendra Vepa

Spoken language understanding (SLU) refers to the process of inferring the semantic information from audio signals. While the neural transformers consistently deliver the best performance among the state-of-the-art neural architectures in…

计算与语言 · 计算机科学 2020-08-26 Martin Radfar , Athanasios Mouchtaris , Siegfried Kunzmann

End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a…

音频与语音处理 · 电气工程与系统科学 2020-08-14 Xueli Jia , Jianzong Wang , Zhiyong Zhang , Ning Cheng , Jing Xiao

Spoken Language Understanding (SLU) is one essential step in building a dialogue system. Due to the expensive cost of obtaining the labeled data, SLU suffers from the data scarcity problem. Therefore, in this paper, we focus on data…

计算与语言 · 计算机科学 2021-09-03 Haitao Lin , Lu Xiang , Yu Zhou , Jiajun Zhang , Chengqing Zong

Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While…

计算与语言 · 计算机科学 2025-10-06 Neeraj Agrawal , Sriram Ganapathy

To capture salient contextual information for spoken language understanding (SLU) of a dialogue, we propose time-aware models that automatically learn the latent time-decay function of the history without a manual time-decay function. We…

计算与语言 · 计算机科学 2019-06-19 Jonggu Kim , Jong-Hyeok Lee

Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialogue history has been exploited to improve conventional…

‹ 上一页 1 2 3 10 下一页 ›