Filters








22,764 Hits in 6.7 sec

A Joint and Domain-Adaptive Approach to Spoken Language Understanding [article]

Linhao Zhang, Yu Shi, Linjun Shou, Ming Gong, Houfeng Wang, Michael Zeng
2021 arXiv   pre-print
In this paper, we attempt to bridge these two lines of research and propose a joint and domain adaptive approach to SLU.  ...  Besides, results show that our joint model can be effectively adapted to a new domain.  ...  Introduction Spoken Language Understanding (SLU) is a critical component in spoken dialogue systems. It usually involves two subtasks: intent detection (ID) and slot filling (SF).  ... 
arXiv:2107.11768v1 fatcat:26e44tz5ozcn7byg4jmdnk55ry

A Survey on Spoken Language Understanding: Recent Advances and New Frontiers [article]

Libo Qin, Tianbao Xie, Wanxiang Che, Ting Liu
2021 arXiv   pre-print
Spoken Language Understanding (SLU) aims to extract the semantics frame of user queries, which is a core component in a task-oriented dialog system.  ...  However, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this article.  ...  Onenet: Joint domain, intent, slot prediction for turn spoken language understanding. In Interspeech, 2016. spoken language understanding. In ASRU, 2017.  ... 
arXiv:2103.03095v2 fatcat:krhrfeomafd6nds2m4o5djbzby

A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling [article]

Yu Wang, Yilin Shen, Hongxia Jin
2018 arXiv   pre-print
Intent detection and slot filling are two main tasks for building a spoken language understanding(SLU) system. Multiple deep learning based models have demonstrated good results on these tasks .  ...  The most effective algorithms are based on the structures of sequence to sequence models (or "encoder-decoder" models), and generate the intents and semantic tags either using separate models or a joint  ...  Comparing stochastic approaches Home Bi-model without a 689 97.8% 98.55% to spoken language understanding in multiple lan- decoder Bi-model with a decoder  ... 
arXiv:1812.10235v1 fatcat:ultvuaalmngn7hdplfbv45bjju

Robust dialog state tracking using delexicalised recurrent neural networks and unsupervised adaptation

Matthew Henderson, Blaise Thomson, Steve Young
2014 2014 IEEE Spoken Language Technology Workshop (SLT)  
Word-based dialog state tracking is attractive as it does not require engineering a spoken language understanding system for use in the new domain and it avoids the need for a general purpose intermediate  ...  Most existing spoken dialog systems are designed to work in a static, well-defined domain, and are not well suited to tasks in which the domain may change or be extended over time.  ...  Acknowledgements Matthew Henderson is a Google Research doctoral fellow.  ... 
doi:10.1109/slt.2014.7078601 dblp:conf/slt/HendersonTY14 fatcat:e5r7gkbhwjbv3mvz37de7n65z4

SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding [article]

Yu-An Chung, Chenguang Zhu, Michael Zeng
2021 arXiv   pre-print
Spoken language understanding (SLU) requires a model to analyze input acoustic signal to understand its linguistic content and make predictions.  ...  In this paper, we propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules.  ...  This optional step aims to adapt the language module to the speech domain to facilitate later alignment.  ... 
arXiv:2010.02295v3 fatcat:7bd3hk4qtbctbd5abzsl6ccy2a

Spoken language understanding using the Hidden Vector State Model

Yulan He, Steve Young
2006 Speech Communication  
In this paper, the practical application of the model in a spoken language understanding system (SLU) is described.  ...  indicate that the overall framework allows adaptation to related domains, and scaling to cover enlarged domains.  ...  Typical structure of a spoken language understanding system.  ... 
doi:10.1016/j.specom.2005.06.002 fatcat:3xbkx7fn6ff6bpkce4bxbtz2ry

Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding [article]

Chao-Wei Huang, Yun-Nung Chen
2020 arXiv   pre-print
Experiments on the benchmark ATIS dataset show that the proposed method significantly improves the performance of spoken language understanding when performing on ASR transcripts.  ...  We propose a novel confusion-aware fine-tuning method to mitigate the impact of ASR errors to pre-trained LMs.  ...  spoken utterances to adapt.  ... 
arXiv:1909.10861v2 fatcat:jfajw75iibgapkpgsgbhoil43q

Deep Learning for Dialogue Systems

Yun-Nung Chen, Asli Celikyilmaz, Dilek Hakkani-Tür
2017 Proceedings of ACL 2017, Tutorial Abstracts  
However, how to successfully apply deep learning based approaches to a dialogue system is still challenging.  ...  The classic dialogue systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently risen the applications of neural models to dialogue modeling.  ...  ] • Spoken/Natural language understanding (SLU/NLU) -Semantic frame representation -Domain classification -Slot tagging -Joint semantic frame parsing -Contextual language understanding -Structural  ... 
doi:10.18653/v1/p17-5004 dblp:conf/acl/ChenCH17 fatcat:eyltpy5guna6bfsczav3vji7x4

Semantic language models with deep neural networks

Ali Orkan Bayer, Giuseppe Riccardi
2016 Computer Speech and Language  
Spoken language systems (SLS) communicate with users in natural language through speech. There are two main problems related to processing the spoken input in SLS.  ...  The second one is spoken language understanding (SLU) which understands what the user means. We focus on the language model (LM) component of SLS.  ...  Spoken language understanding (SLU) is most often performed by using a semantic-frame approach [130] .  ... 
doi:10.1016/j.csl.2016.04.001 fatcat:2ybfzvyavngkfn2rbtrbotnhc4

Improving Speech Recognition and Understanding using Error-Corrective Reranking

Minwoo Jeong, Gary Geunbae Lee
2008 ACM Transactions on Asian Language Information Processing  
The proposed error corrective re-ranking approach exploits recognition environment characteristics and domainspecific semantic information to provide robustness and adaptability for a spoken language system  ...  To address this problem, we present a method to improve the accuracy of speech recognition and performance of spoken language applications.  ...  by the Ministry of Commerce, Industry and Energy of Korea.  ... 
doi:10.1145/1330291.1330293 fatcat:rtlpa7hjkva4zasy2nlgm66eky

Robust Zero-Shot Cross-Domain Slot Filling with Example Values

Darsh Shah, Raghav Gupta, Amir Fayazi, Dilek Hakkani-Tur
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
We propose utilizing both the slot description and a small number of examples of slot values, which may be easily available, to learn semantic representations of slots which are transferable across domains  ...  and robust to misaligned schemas.  ...  We would also like to thank the Deep Dialogue team at Google Research for their support.  ... 
doi:10.18653/v1/p19-1547 dblp:conf/acl/ShahGFH19 fatcat:qrdmwn45srbdneyourkyaa5nje

Multi-domain spoken language understanding with transfer learning

Minwoo Jeong, Gary Geunbae Lee
2009 Speech Communication  
This paper addresses the problem of multi-domain spoken language understanding (SLU) where domain detection and domaindependent semantic tagging problems are combined.  ...  We present a transfer learning approach to the multi-domain SLU problem in which multiple domain-specific data sources can be incorporated.  ...  We would also like to thank Donghyun Lee for his preparation of speech recognition results, and Derek Lactin for his proof-reading of the paper.  ... 
doi:10.1016/j.specom.2009.01.001 fatcat:u4yhnffhfbhwbeg2mgezszcz4u

ONENET: Joint domain, intent, slot prediction for spoken language understanding

Young-Bum Kim, Sungjin Lee, Karl Stratos
2017 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)  
In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames  ...  To address these issues, we present a unified neural network that jointly performs domain, intent, and slot predictions.  ...  A typical way to handle multiple domains for the spoken language understanding (SLU) task [1] is to perform domain prediction first and then carry out intent prediction [2, 3, 4] and slot tagging  ... 
doi:10.1109/asru.2017.8268984 dblp:conf/asru/KimLS17a fatcat:cn6kttdotndsfjfuv7thpuglxa

A Multi-Strategic Concept-Spotting Approach for Robust Understanding of Spoken Korean

Changki Lee, Jihyun Eun, Minwoo Jeong, Gary Geunbae Lee, YiGyu Hwang, Myung-Gil Jang
2007 ETRI Journal  
We propose a multi-strategic concept-spotting approach for robust spoken language understanding of conversational Korean in a hostile recognition environment such as in-car navigation and telebanking services  ...  spoken language inputs.  ...  To overcome these speech recognition limitations, we attempt to understand spoken languages by a concept-spotting approach which aims to extract only essential factors for Table 1 .  ... 
doi:10.4218/etrij.07.0106.0204 fatcat:qutw5nsa2fh7rikcamdhz6uzgq

OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding [article]

Young-Bum Kim, Sungjin Lee, Karl Stratos
2018 arXiv   pre-print
In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames  ...  To address these issues, we present a unified neural network that jointly performs domain, intent, and slot predictions.  ...  A typical way to handle multiple domains for the spoken language understanding (SLU) task [1] is to perform domain prediction first and then carry out intent prediction [2, 3, 4] and slot tagging  ... 
arXiv:1801.05149v1 fatcat:om3zdtpmffgqxixfhfijqo553u
« Previous Showing results 1 — 15 out of 22,764 results