Spoken language understanding using weakly supervised learning

Weilin Wu

doi:10.1016/j.csl.2009.05.002

2010-04-01

PRE

DOI：10.1016/j.csl.2009.05.002

原文链接

原文求助

摘要

En 中文

In this paper, we present a weakly supervised learning approach for spoken language understanding in domain-specific dialogue systems. We model the task of spoken language understanding as a two-stage classification problem. Firstly, the topic classifier is used to identify the topic of an input utterance. Secondly, with the restriction of the recognized target topic, the slot classifiers are trained to extract the corresponding slot-value pairs. It is mainly data-driven and requires only minimally annotated corpus for training whilst retaining the understanding robustness and deepness for spoken language. More importantly, it allows that weakly supervised strategies are employed for training the two kinds of classifiers, which could significantly reduce the number of labeled sentences. We investigated active learning and naive self-training for the two kinds of classifiers. Also, we propose a practical method for bootstrapping topic-dependent slot classifiers from a small amount of labeled sentences. Experiments have been conducted in the context of the Chinese public transportation information inquiry domain and the English DARPA Communicator domain. The experimental results show the effectiveness of our proposed SLU framework and demonstrate the possibility to reduce human labeling efforts significantly. (C) 2009 Elsevier Ltd. All rights reserved.

Keyword:

Spoken language understanding

Spoken dialogue system

Topic classification

Active learning

Self-training

Bootstrapping

AI总结

对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Computer Speech and Language

IF:

3.4

论文数:

1.5K

被引数:

2.6K

机构

shanghai jiao tong university

学者数:

15.7W

论文数: 11.7W

被引数: 159

引用论文

Development and application of a computer vision system for the measurement of the colour of Iranian sweet bread

Quality Assurance and Safety of Crops & Foods

IF0

2014-03-01

OAAI

M. Hashemi Shahraki; M. Mashkour; A. Daraei Garmakhany

Estimating multivariate similarity between neuroimaging datasets with sparse canonical correlation analysis: an application to perfusion imaging

Frontiers in Neuroscience

IF0

2015-10-13

OAAI

Maria J. Rosa; Mitul A. Mehta; Emilio M. Pich; Celine Risterucci; Fernando Zelaya; Antje A. T. S. Reinders; Steve C. R. Williams; Paola Dazzan; Orla M. Doyle; Andre F. Marquand

The Calcium Binding Site in Cytochrome aa₃ from Paracoccus denitrificans

Biochemistry

IF0

1999-07-27

PREAI

Sirpa Riistama; Liisa Laakkonen; Mårten Wikström; Michael I. Verkhovsky; Anne Puustinen

Incorporation of the nicotinic acetylcholine receptor into planar multilamellar films: characterization by fluorescence and Fourier transform infrared difference spectroscopy

Biophysical Journal

IF0

1992-04-01

OAAI

J.E. Baenziger; K.W. Miller; K.J. Rothschild