Premium 구글번역 샘플

홈home > Premium 구글번역 샘플

원문 병서문
제목 영-한-번역샘플-수학물리
내용

1. The Overall Plan

We want to automatically analyze existing human sentence translations, with an eye toward building general translation rules -- we will use these rules to translate new texts automatically. I know this looks like a thick workbook, but if you take a day to work through it, you will know almost as much about statistical machine translation as anybody!


The basic text that this tutorial relies on is Brown et al, “The Mathematics of Statistical Machine Translation”, Computational Linguistics, 1993. On top of this excellent presentation, I can only add some perspective and perhaps some sympathy for the poor reader, who has (after all) done nothing wrong. Important terms are underlined throughout!


2. Basic Probability

We're going to consider that an English sentence e may translate into any French sentence f. Some translations are just more likely than others. Here are the basic notations we'll use to formalize “more likely”: P(e) -- a priori probability. The chance that e happens. For example, if e is the English string “I like snakes,” then P(e) is the chance that a certain person at a certain time will say “I like snakes” as opposed to saying something else.

1. The Overall Plan

전체 계획


We want to automatically analyze existing human sentence translations, with an eye toward building general translation rules -- we will use these rules to translate new texts automatically.

일반적인 번역 규칙을 세우기 위해 기존의 인간 문장 번역을 자동으로 분석하려고합니다. 이러한 규칙을 사용하여 새 텍스트를 자동으로 번역합니다.


I know this looks like a thick workbook, but if you take a day to work through it, you will know almost as much about statistical machine translation as anybody!

나는 이것이 두꺼운 통합 문서처럼 보인다는 것을 알고 있지만, 하루 동안 작업을하면 통계 기계 번역에 대해 거의 누구나 알 수 있습니다!


The basic text that this tutorial relies on is Brown et al, “The Mathematics of Statistical Machine Translation”, Computational Linguistics, 1993.

이 학습서가 사용하는 기본 텍스트는 Brown et al, "통계 기계 번역의 수학", Computational Linguistics, 1993입니다.


 On top of this excellent presentation, I can only add some perspective and perhaps some sympathy for the poor reader, who has (after all) done nothing wrong.

이 훌륭한 발표와 더불어, 나는 아무 잘못도하지 않은 가난한 독자에게 약간의 관점과 동정심을 더할 수 있습니다.


Important terms are underlined throughout!

중요한 용어는 전체에 밑줄이 그어져 있습니다!


2. Basic Probability

기본 확률


We're going to consider that an English sentence e may translate into any French sentence f.

우리는 영어 문장 e가 프랑스어 문장으로 번역 될 수 있습니다고 생각할 것입니다. f.


 Some translations are just more likely than others.

일부 번역은 다른 번역보다 가능성이 높습니다.


 Here are the basic notations we'll use to formalize “more likely”:

다음은“더 가능성이 높은”공식화에 사용할 기본 표기법입니다.


P(e) -- a priori probability.

P(e)-선험적 확률.


 The chance that e happens.

e가 일어날 확률.


 For example, if e is the English string “I like snakes,” then P(e) is the chance that a certain person at a certain time will say “I like snakes” as opposed to saying something else.

예를 들어, e가 영어 문자열“뱀을 좋아합니다”인 경우 P(e)는 특정 시간에 특정 사람이 다른 말을하는 대신“뱀을 좋아합니다”라고 말할 가능성입니다.