Lecture Natural language processing: Chapter 3 – Lê Ngọc Tấn

Trường Đại học Công nghiệp Tp. HCM<br /> Khoa Công nghệ thông tin<br /> (Faculty of Information Technology)<br /> <br /> N.L.P.<br /> NATURAL LANGUAGE PROCESSING<br /> Teacher: Lê Ngọc Tấn<br />  Email: letan.dhcn@gmail.com<br />  Blog: http://lengoctan.wordpress.com<br /> <br /> <br /> Chapter 3<br /> Basic principles for NLP<br /> <br /> NLP. p.2<br /> <br /> POS – part of speech tagging (1)<br /> <br /> <br /> Perhaps starting with Aristotle in the West<br /> (384-322 BCE), there was the idea of having<br /> parts of speech<br /> <br /> <br /> <br /> It comes from Dionysius Thrax of Alexandria<br /> (c. 100 BCE), the idea that is still with us that<br /> there are 8 traditional parts of speech:<br /> – Thrax: noun, verb, article, adverb, preposition,<br /> conjunction, participle, pronoun<br /> – School grammar: noun, verb, adjective, adverb,<br /> preposition, conjunction, interjection, pronoun<br /> <br /> NLP. p.3<br /> <br /> POS – part of speech examples for English<br /> <br /> <br /> N<br /> V<br />  ADJ<br />  ADV<br /> P<br />  PRO<br />  DET<br />  CONJ<br /> <br /> noun<br /> chair, bandwidth, pacing<br /> verb<br /> study, debate, munch<br /> adj<br /> purple, tall, ridiculous<br /> adverb<br /> unfortunately, slowly<br /> preposition<br /> of, by, to<br /> pronoun<br /> I, me, mine<br /> determiner the, a, that, those<br /> conjunction<br /> and, or<br /> NLP. p.4<br /> <br /> Open vs. Closed Classes<br />  Open<br /> <br /> vs. Closed classes<br /> <br /> – Closed:<br /> •<br /> •<br /> •<br /> •<br /> <br /> determiners: a, an, the<br /> pronouns: she, he, I<br /> prepositions: on, under, over, near, by, …<br /> Why “closed”?<br /> <br /> – Open:<br /> • Nouns, Verbs, Adjectives, Adverbs.<br /> <br /> NLP. p.5<br /> <br />