Presentation is loading. Please wait.

Presentation is loading. Please wait.

Modern MT Systems and the Myth of Human Translation: Real World Status Quo ● Intro ● MT & HT Definitions ● Comparison MT vs. HT ● Evaluation Methods ●

Similar presentations


Presentation on theme: "Modern MT Systems and the Myth of Human Translation: Real World Status Quo ● Intro ● MT & HT Definitions ● Comparison MT vs. HT ● Evaluation Methods ●"— Presentation transcript:

1

2 Modern MT Systems and the Myth of Human Translation: Real World Status Quo ● Intro ● MT & HT Definitions ● Comparison MT vs. HT ● Evaluation Methods ● FAE Framework ● Conclusion ● Discussion

3 Is This for Me? ● (Freelance) translators and agencies ● Developers and vendors of MT systems ● People concerned with MT evaluation ● People concerned with HT evaluation This talk may be of benefit for: Not for interpreters and speech/non-text based issues

4 Introduction ● What is Machine Translation (MT)? ● What is [Human] Translation (HT)? „MT is the automatic translation of human language by computers.“ „The process of transforming text from one language into another language.“ „A written communication in a second language having the same meaning as the written communication in a first language.“

5 Introduction II ● Is there such a thing as HT? „Pure Human Translation“ „Machine Aided Human Translation“ „Human Aided Machine Translation“ ● Is HT equal to HT? „Native Speaker“ „Speaks Language X“ „[Trained] Professional“ „Trained Prof. specialized in X“

6 HT/MT Examples & Quizshow Original: Einzigartiger Freizeitpark für Groß und Klein T1: Singular recreational park for large and small T2: Unique leisure time park for largely and small T3: Ein Fantastische DinoPark ferrcoitung T4: Unique Freizeitpark at big and little T5: Unique amusement park for great and Klein T6: Unique leisure park for big and little T1: Babelfish/SYSTRAN T2: SDL FreeTranslation.com T3: Human T4: InterTran T5: Linguatex eTranslation T6: PetaMem LangSuite MT

7

8

9

10

11

12 Summary HT Quality ● Not all HTs are equal ● Significant amount done by untrained people ● Better performance of good(!) MT systems on these examples suggests rising MT competitiveness

13 Issues with MT & HT Evaluation ● Evaluation vs. Similarity Ngram does work? Why? ● Reference Translations: Cost & Availability Multiples – which „Axiomatic Truth“ ● Judging Expensive Questionable results ● Using MT-eval methods: limitations just mentioned

14 Mission Impossible? ● Fully automatic evaluation method for both MT & HT – with no human Intervention? ● Purpose: Automatic QA of translations – at least safe rejection of bad results ● Part of an iterative process (with faith in the translator)

15 We need it – should we give up?

16 Let's Try Anyway! ● Text Metrics Length Word/Sentence/Paragraph count ● Statistics Character/Word occurrence Ngram Collocations ● Translator Parameters ● Monolingual Corpora for SL & TL Statistical reference ● Dictionaries & Thesauri Adequacy check Translation distance Sentence Alignment ● Parallel Corpora Translation Length Ratio Extract Information Reference Data

17 Workflow

18 Conclusion ● Translation results of the best contemporary MT systems can be considered on par with the average HT ● The presented evaluation framework is just the beginning of an automatic evaluation method for both MT & HT ● It is a robust and reliable validation method with safe rejection of invalid/bad translations ● In production Q1/2005

19 Thanks! Q & A


Download ppt "Modern MT Systems and the Myth of Human Translation: Real World Status Quo ● Intro ● MT & HT Definitions ● Comparison MT vs. HT ● Evaluation Methods ●"

Similar presentations


Ads by Google