基於語法剖析樹片段的遞迴自動聯結記憶體做具語義線索的語法剖析

Fragment-based Recursive Auto-associative Memory Parsing with Semantic Clues

周聰衍(Cong-Yan Zhou)

指導教授 ： 蘇豐文

國立清華大學/電機資訊學院/資訊工程學系/碩士(2015年)

摘要

在傳統的語法剖析中雖然基於幾率的前後文無關文法雖然在語法剖析中亦能取得較好表現，但卻無法處理需前後文語境才能解決的介系詞片語的二義性問題。本文提出了一種基於語法剖析樹片段與遞迴自動聯結記憶體的方法，同時考慮語法與語義線索，解決候選語法剖析樹中存在的二義性問題。

關鍵字

自然語言解析 ； 語法剖析樹片段 ； 遞迴自動聯結記憶體

並列摘要

Traditional syntactic parsing such as using Probabilistic context free grammar (PCFG) parser, Stanford parser, etc. can achieve good performance on parsing natural language sentences. However, they usually suffer ambiguous problems in dealing with situations such as PP attachment that need semantic information to resolve. We propose a novel data-oriented fragment-based adaptive parsing method that combines both syntactic and semantic information with the help of parsing fragments and a recursive auto-associative memory (RAAM) that can disambiguate by selecting the most semantic plausible parse tree from ambiguous candidates.

並列關鍵字

natural language parsing ； fragment ； recursive auto-associative memory

參考文獻

[5] Pollack, Jordan B. "Recursive distributed representations." Artificial Intelligence 46.1: 77-105. 1990

[8] Harris, Zellig S. "Distributional structure." Word , 1954.

[9] Deerwester, Scott C., et al. "Indexing by latent semantic analysis." JAsIs 41.6: 391-407. 1990

[10] Salton, Gerard, Anita Wong, and Chung-Shu Yang. "A vector space model for automatic indexing." Communications of the ACM 18.11 : 613-620. 1975

[1] Socher, Richard, et al. "Parsing with compositional vector grammars." In Proceedings of the ACL conference. 2013.