SGER: Using Text Coherence and Verbal Valence in Long- Distance N-grams

SGER：在长距离 N 元语法中使用文本连贯性和语言效价

• 批准号: 9704046
• 负责人: Daniel Jurafsky
• 金额: $ 5万
• 依托单位: University of Colorado at Boulder
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1997
• 资助国家: 美国
• 起止时间: 1997-01-15 至 1997-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9704046&HistoricalAwards=false
• 关键词: SGER; Using; Text; Coherence; Verbal

*** Building better speech recognizers requires augmenting n-gram grammars with sophisticated yet probabilistic linguistic knowledge. This project is building probabilistic models of two important pieces of syntactic/semantic knowledge: verb-argument constraints and semantic text coherence.(1) Verbs place strong constraints on the syntax and semantics of their arguments. This project is computing probabilities for the different argument structures that can co-occur with different verbs, and using these probabilities to augment standard trigram language models.(2) Texts and discourses tend to be semantically coherent;in particular the words that occur in a text tend to be semantically related to each other. This project is applying a model of word meaning called Latent Semantic Analysis (LSA) to ASR LMs. In LSA, a word-similarity metric is defined by computing a large matrix of word co-occurrence probabilities, which are then smoothed via Singular Value Decomposition, resulting in a generalized measure of semantic word-similarity. Trigram models can then increase the probability that similar words will occur near each other. Building these two stochastic models of linguistic knowledge, besides possible application in speech recognition LMs, word-sense disambiguation, or parsing, also helps bridge the gap between the structural models used in linguistics and the statistical models of speech engineering.***

*** 构建更好的语音识别器需要使用复杂且概率性的语言知识来增强 n 元语法。 该项目正在构建两个重要的句法/语义知识的概率模型：动词参数约束和语义文本连贯性。（1）动词对其参数的语法和语义施加了严格的约束。 该项目正在计算可以与不同动词同时出现的不同参数结构的概率，并使用这些概率来增强标准三元组语言模型。（2）文本和话语往往在语义上是连贯的；特别是文本中出现的单词往往在语义上彼此相关。 该项目正在将一种称为潜在语义分析 (LSA) 的词义模型应用于 ASR LM。 在LSA中，单词相似度度量是通过计算单词共现概率的大矩阵来定义的，然后通过奇异值分解对其进行平滑，从而得到语义单词相似度的广义度量。 Trigram 模型可以增加相似单词彼此靠近出现的概率。 构建这两种语言知识的随机模型，除了可能应用于语音识别 LM、词义消歧或解析之外，还有助于弥合语言学中使用的结构模型和语音工程统计模型之间的差距。***