A Supervised Learning based Chunking in Thai using Categorial Grammar
Thepchai Supnithi, Chanon Onman, Peerachet Porkaew, Taneth Ruangrajitpakorn, Kanokorn Trakultaweekoon, Asanee Kawtrakul · 2010
One of the challenging problems in Thai NLP is to manage a problem on a syntactical analysis of a long sentence. This paper applies conditional random field and categorical grammar to develop a chunking method, which can group words into larger unit. Based on the experiment, we found the impressive results. We gain around 74.17% on sentence level chunking. Furthermore we got a more correct parsed tree based on our technique. Around 50% of tree can be added. Finally, we solved the problem on implicit sentential NP which is one of the difficult Thai language processing. 58.65% of sentential NP is correctly detected.