arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08124cs.CLcs.AI
收藏

意义的结构:NLP系统的系统语料分析

Architectures of Meaning, A Systematic Corpus Analysis of NLP Systems

The University of Manchester(曼彻斯特大学);University of Manchester(曼彻斯特大学);CRUK Manchester Institute(英国癌症研究院曼彻斯特研究所);Idiap Research Institute(Idiap研究所)

Oskar Wysocki, Malina Florea, Donal Landers, Andre Freitas

摘要:

本文提出了一种新的统计语料库分析框架,旨在解释自然语言处理(NLP)的架构模式的规模。该方法结合基于饱和度的词典构建、统计语料库分析方法和图形搭配,从语料库中归纳出自然语言处理架构模式的综合表示。该框架在Semeval任务的完整语料库中进行了验证,并展示了连贯的架构模式,可用于以数据驱动的方式回答架构问题,提供了一种系统的机制来解释一个动态和指数增长的领域。

英文摘要:

This paper proposes a novel statistical corpus analysis framework targeted towards the interpretation of Natural Language Processing (NLP) architectural patterns at scale. The proposed approach combines saturation-based lexicon construction, statistical corpus analysis methods and graph collocations to induce a synthesis representation of NLP architectural patterns from corpora. The framework is validated in the full corpus of Semeval tasks and demonstrated coherent architectural patterns which can be used to answer architectural questions on a data-driven fashion, providing a systematic mechanism to interpret a largely dynamic and exponentially growing field.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑