paper-with-me

홈 › Papers

Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking

2017-07-18 · WS 2017 9 · Glorianna Jagfeld, Ngoc Thang Vu

This paper presents our novel method to encode word confusion networks, which can represent a rich hypothesis space of automatic speech recognition systems, via recurrent neural networks. We demonstrate the utility of our approach for the task of dialog state tracking in spoken dialog systems that relies on automatic speech recognition output. Encoding confusion networks outperforms encoding the best hypothesis of the automatic speech recognition in a neural system for dialog state tracking on the well-known second Dialog State Tracking Challenge dataset.

📄 PDF Abstract BibTeX arXiv:1707.05853

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)dialog state trackingspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding

2020-05-24 · Chen Liu, Su Zhu, Zijian Zhao, Ruisheng Cao 외

Spoken Language Understanding (SLU) converts hypotheses from automatic speech recognizer (ASR) into structured semantic representations. ASR recognition errors can severely degenerate the performance of the subsequent SL…

Spoken Language Understanding

Modeling ASR Ambiguity for Dialogue State Tracking Using Word Confusion Networks

2020-02-03 · Vaishali Pal, Fabien Guillot, Manish Shrivastava, Jean-Michel Renders 외

Spoken dialogue systems typically use a list of top-N ASR hypotheses for inferring the semantic meaning and tracking the state of the dialogue. However ASR graphs, such as confusion networks (confnets), provide a compact…

Dialogue State TrackingSpoken Dialogue Systems

Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge

2018-09-10 · CONLL 2018 10 · Debanjan Chaudhuri, Agustinus Kristiadi, Jens Lehmann, Asja Fischer

Building systems that can communicate with humans is a core problem in Artificial Intelligence. This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dia…

Watch It Twice: Video Captioning with a Refocused Video Encoder

2019-07-21 · Xiangxi Shi, Jianfei Cai, Shafiq Joty, Jiuxiang Gu

With the rapid growth of video data and the increasing demands of various applications such as intelligent video search and assistance toward visually-impaired people, video captioning task has received a lot of attentio…

Video Captioning

Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings

2018-05-21 · ACL 2018 7 · Bernd Bohnet, Ryan Mcdonald, Goncalo Simoes, Daniel Andor 외

The rise of neural networks, and particularly recurrent neural networks, has produced significant advances in part-of-speech tagging accuracy. One characteristic common among these models is the presence of rich initial …

Morphological TaggingPart-Of-Speech TaggingSentenceWord Embeddings