arrow
返回

SCRIPT-BASED INFERENCE AND MEMORY RETRIEVAL IN SUBSYMBOLIC STORY PROCESSING

delete1995-04-01
delete6
PRE
AI
R
Risto Miikkulainen *
DOI:10.1007/BF00877229delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
DISCERN is an integrated natural language processing system built entirely from distributed neural networks. It reads short narratives about stereotypical event sequences, stores them in episodic memory, generates fully expanded paraphrases of the narratives, and answers questions about them. Processing in DISCERN is based on hierarchically-organized backpropagation modules, communicating through a central lexicon of word representations. The lexicon is a double feature map system that transforms each orthographic word symbol into its semantic representation and vice versa. The episodic memory is a hierarchy of feature maps, where memories are stored ''one-shot'' at different locations. Several high-level phenomena emerge automatically from the special properties of distributed neural networks in this model. DISCERN learns to infer unmentioned events and unspecified role fillers, generates expectations and defaults, and exhibits plausible lexical access errors and memory interference behavior. Word semantics, memory organization, and appropriate script inferences are automatically extracted from examples. DISCERN shows that high-level natural language processing is feasible through integrated subsymbolic systems. Subsymbolic control of high-level behavior and representing and learning abstractions are the two main challenges in scaling up the approach to more open-ended tasks.
Keyword:
NEURAL NETWORK ARCHITECTURES
NATURAL LANGUAGE PROCESSING
REASONING
COGNITIVE MODELING

期刊

Applied Intelligence 封面图
Applied Intelligence
IF:
3.5
论文数:
7.6K
被引数:
1.7W

机构

暂无机构信息
引用论文

引用论文

err分享
err收藏
African Breast Cancer—Disparities in Outcomes (ABC-DO): protocol of a multicountry mobile health prospective study of breast cancer survival in sub-Saharan Africa
err2016-08-23
err0
errOAAI
errFiona McKenzie; Annelle Zietsman; Moses Galukande; Angelica Anele; Charles Adisa; Herbert Cubasch; Groesbeck Parham; Benjamin O Anderson; Behnoush Abedi-Ardekani; Joachim Schuz; Isabel dos Santos Silva; Valerie McCormack
err分享
err收藏
err分享
err收藏
err分享
err收藏
Monitoring breastfeeding indicators in high‐income countries: Levels, trends and challenges
err2021-01-06
err0
errOAAI
errJuliana S. Vaz; Maria Fatima S. Maia; Paulo A. R. Neves; Thiago M. Santos; Luís Paulo Vidaletti; Cesar Victora
err分享
err收藏
学者 查看更多内容