Unsupervised Learning of Morphology

形态学的无监督学习

• 批准号: 0415138
• 负责人: Mitchell Marcus
• 金额: --
• 依托单位: University of Pennsylvania
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2005
• 资助国家: 美国
• 起止时间: 2005-06-01 至 2010-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0415138&HistoricalAwards=false
• 关键词: Unsupervised; Learning; Morphology

This project is working to develop a new system that simultaneously discovers the patterns of word morphology and parts of speech for a wide range of the world's languages from unannotated text. Given a quantity of training text, such a system will yield a transducer, which segments the words in new texts into stems and affixes and determine the part of speech of each word as a whole. Through unsupervised learning, an iterative bootstrapping procedure will combine several different linguistic knowledge sources to gradually build up a representation of the language in the form of paradigms. From these paradigms, symbolic part of speech rules and morphophonological rewrite rules will be extracted, which will then be compiled into a probabilistic finite-state transducer, which can label new texts with morphology and part of speech.Despite the widespread application of machine learning techniques to natural language processing, developing morphological analyzers still involves much human effort. While the morphology of English is very simple, the automatic analysis by computer of texts or speech in the majority of the world's languages depend on the availability of appropriate morphological analyzers. It is also important for the important problem of automatic information extraction in the biomedical domain, where it is necessary to analyze the complex structure of technical terms, even in English. Such analyzers are useful in most applications in natural language processing, including parsing, information retrieval, machine translation, text summarization, correct pronunciation in speech synthesis, language models in speech recognition, language generation, and named entity recognition.

这个项目致力于开发一种新系统，可以同时发现世界上各种语言的词法和词性模式，这些模式来自于没有注释的文本。给定一定数量的训练文本，这样的系统将产生一个换能器，它将新文本中的单词分割成词干和词缀，并确定每个单词作为一个整体的词性。通过无监督学习，迭代的自举过程将几种不同的语言知识来源结合起来，以范式的形式逐渐建立语言的表征。从这些范式中提取符号词性规则和词性重写规则，然后将其编译成概率有限状态换能器，该换能器可以用词性和词性标记新文本。尽管机器学习技术在自然语言处理中得到了广泛的应用，但开发形态学分析仪仍然需要大量的人力。虽然英语的词法非常简单，但计算机对世界上大多数语言的文本或语音的自动分析依赖于适当的词法分析器。它对于生物医学领域的自动信息提取这一重要问题也很重要，因为在生物医学领域中，需要分析技术术语的复杂结构，甚至是英语术语。这种分析器在自然语言处理的大多数应用中都很有用，包括解析、信息检索、机器翻译、文本摘要、语音合成中的正确发音、语音识别中的语言模型、语言生成和命名实体识别。