Presentation is loading. Please wait.

Presentation is loading. Please wait.

Machine Translation Introduction to MT. Dan Jurafsky Machine Translation Fully automatic Helping human translators Enter Source Text: Translation from.

Similar presentations


Presentation on theme: "Machine Translation Introduction to MT. Dan Jurafsky Machine Translation Fully automatic Helping human translators Enter Source Text: Translation from."— Presentation transcript:

1 Machine Translation Introduction to MT

2 Dan Jurafsky Machine Translation Fully automatic Helping human translators Enter Source Text: Translation from Stanford’s Phrasal: 这 不过 是 一 个 时间 的 问题. This is only a matter of time.

3 Dan Jurafsky Google Translate Fried ripe plantains: os-maduros-fritos/ os-maduros-fritos/

4 Dan Jurafsky Machine Translation The Story of the Stone (“The Dream of the Red Chamber”) Cao Xueqin 1792 Chinese gloss: Dai-yu alone at bed on think-of-with-gratitude Bao-chai… again listen to window outside bamboo tip plantain leaf of on, rain sound sigh drop, clear cold penetrate curtain, not feeling again fall down tears come. Hawkes translation: As she lay there alone, Dai-yu’s thoughts turned to Bao-chai… Then she listened to the insistent rustle of the rain on the bamboos and plantains outside her window. The coldness penetrated the curtains of her bed. Almost without noticing it she had begun to cry.

5 Dan Jurafsky Difficulties in Chinese to English translation Long Chinese sentences: 4 English sentences to 1 Chinese Chinese no pronouns or articles (English the, a) Chinese has locative post-positions, English prepositions Chinese bed on, window outside, English on the bed, outside the window Chinese rarely marks tense: English as, turned to, had begun, Chinese tou, ‘penetrate’ -> English penetrated Chinese relative clauses are before the noun, English after Chinese: [window outside bamboo on] rain English: rain [on the bamboo outside the window] Stylistic and cultural differences Chinese bamboo tip plaintain leaf -> bamboos and plantains Chinese rain sound sigh drop -> insistent rustle of the rain Chinese ma ‘curtain’ -> curtains of her bed

6 Dan Jurafsky Alignment in Machine Translation

7 Dan Jurafsky Early MT History 1946 Booth and Weaver discuss MT in New York idea of dictionary-based direct translation 1947 Warren Weaver suggests translation by computer 1949 Weaver memorandumWeaver memorandum 1952 all 18 MT researchers in world meet at MIT 1954 IBM/Georgetown Demo Russian-English MT lots of labs take up MT

8 Dan Jurafsky 1949 Weaver memorandum “There are certain invariant properties which are… common to all languages” ‘When I look at an article in Russian, I say "This is really written in English, but it has been coded in some strange symbols. I will now proceed to decode.”’ “[If] one can see… N words on either side, then, if N is large enough, one can unambiguously decide the meaning of the central word.” 8

9 Dan Jurafsky The History of MT: Pessimism 1959/1960 Yehoshua Bar-Hillel “Report on the state of MT in US and GB” FAHQ MT too hard because we would have to encode all of human knowledge Instead we should work on computer tools for human translators

10 Dan Jurafsky The claim that fully automatic high quality MT is impossible Yehoshua Bar-Hillel A Demonstration of the Nonfeasibility of Fully Automatic High Quality Translation. Little John was looking for his toy box. Finally he found it. The box was in the pen. John was very happy. Pen 1 : Enclosure for small children Pen 2 : Writing utensil Pen 1 : Enclosure for small children

11 Dan Jurafsky The box was in the pen.

12 Dan Jurafsky The claim that fully automatic high quality MT is impossible Yehoshua Bar-Hillel, 1960 “I now claim that no existing or imaginable program will enable an electronic computer to determine…”

13 Dan Jurafsky The state of the art in MT

14 Dan Jurafsky The state of the art in MT

15 Dan Jurafsky History of MT: Further Pessimism The ALPAC report Headed by John R. Pierce of Bell Labs Conclusions: MT doesn’t work MT a failure: all current MT work had to be post-edited Intelligibility and informativeness worse than human We don’t need MT anyhow Already too many human translators from Russian Results: MT research suffered Funding loss Number of research labs declined Association for Machine Translation and Computational Linguistics dropped MT from its name

16 Dan Jurafsky MT in the modern age Resurgence of MT in Europe and Japan Domain-specific rule-based systems 1990-present Rise of Statistical Machine Translation

17 Machine Translation Introduction to MT

18 Machine Translation Language Divergences

19 Dan Jurafsky Language Similarities and Divergences Typology: the study of systematic cross-linguistic similarities and differences What are the dimensions along which human languages vary?

20 Dan Jurafsky Syntactic Variation: Basic Word Orders SVO (Subject-Verb-Object) languages English, German, French, Mandarin I baked a pizza SOV Languages Japanese, Hindi English: He adores listening to music Japanese: kare ha ongaku wo kiku no ga daisuki desu he music to listening adores VSO languages Irish, Classical Arabic, Tagalog In many languages one word order is more basic

21 Dan Jurafsky Morphology Morpheme: “ Minimal meaningful unit of language” Word = Morpheme + Morpheme + Morpheme +… Stems: (base form, root) hope+ing  hopinghop  hopping Affixes Prefixes: Antidisestablishmentarianism Suffixes: Antidisestablishmentarianism Infixes: hingi (borrow) – humingi (borrower) in Tagalog Circumfixes: sagen (say) – gesagt (said) in German

22 Dan Jurafsky Morphemes per Word isolating synthetic Vietnamese Joseph Greenberg A Quantitative Approach to the Morphological Typology of Language. IJAL 26: Yakut (Turkic) 2.17 English 1.68 West Greenlandic (Eskimo- Inuit) Swahili

23 Dan Jurafsky Few morphemes per word: Cantonese “He said this was the biggest building in the whole country” Each word in this sentence has one morpheme (and one syllable): keui wa chyuhn gwok jeui daaih gaan nguk haih li gaan he say entire country most big bldg house is this bldg

24 Dan Jurafsky Many Morphemes per word: Turkish uygarlaştıramadıklarımızdanmışsınızcasına uygar+laş+tır+ama+dık+lar+ımız+dan+mış+sınız+casına Behaving as if you are among those whom we could not cause to become civilized

25 Dan Jurafsky Word Segmentation Are word boundaries marked in writing? Some writing systems: boundaries between words not marked Chinese, Japanese, Thai Word segmentation becomes an important part of text normalization for MT Some languages tend to have sentences that are quite long, closer to English paragraphs than sentences: Modern Standard Arabic, Chinese Sentence segmentation may be necessary for MT between these languages and languages like English

26 Dan Jurafsky Inferential Load: cold vs. hot languages Hot languages: Who did what to whom is marked explicitly English Cold languages: The hearer has more “figuring out” of who the various actors in the various events are Japanese, Chinese Balthasar Bickel Referential density in discourse and syntactic typology. Language 79:2,

27 Dan Jurafsky Inferential Load: The blue noun phrases are not in the Chinese original 飓风丽塔已经减弱为第三级飓风, Rita weakened and was downgraded to a Category 3 storm; ø 迫近美国德课萨斯州和路易斯安那州, [Rita/it/the storm] is moving close to Texas and Louisiana; 当局表示, the authorities announced; 虽然 ø 在登陆前可能再稍微减弱, although [Rita/it/the storm] might weaken again before landing, 但 ø 仍然会非常危险, [Rita/it/the storm] is still very dangerous; ø 预料 ø 会在当地时间星期六凌晨在德州和路易斯安那州之间登陆, [the authorities] predict [Rita/it/the storm] will arrive at the Texas- Louisiana border on Saturday morning local time; ø 直接吹袭休斯敦市东面的主要炼油设施。 [Rita/it/the storm] will directly hit the oil-refining industry east of Houston.

28 Dan Jurafsky Lexical Divergences Word to phrases: English computer science French informatique Part of Speech divergences English She likes to sing German Sie singt gerne [She sings likefully] English I’m hungry Spanish Tengo hambre [I have hunger]

29 Dan Jurafsky Lexical Specificity Divergences Grammatical specificity Spanish: plural pronouns have gender ( ellos/ellas ) English: plural pronouns no gender ( they ) So translating “they” from English to Spanish, need to figure out gender of the referent!

30 Dan Jurafsky Lexical Divergences: Semantic Specificity English brother Mandarin gege (older brother), didi (younger brother) English wall German Wand (inside) Mauer (outside) English fish Spanish pez (the creature) pescado (fish as food) Cantonese ngau English cow beef

31 Dan Jurafsky Predicate Argument divergences English Spanish The bottle floated out.La botella salió flotando. The bottle exited floating Satellite-framed languages: direction of motion is marked on the satellite Crawl out, float off, jump down, walk over to, run after Most of Indo-European, Hungarian, Finnish, Chinese Verb-framed languages: direction of motion is marked on the verb Spanish, French, Arabic, Hebrew, Japanese, Tamil, Polynesian, Mayan, Bantu families L. Talmy Lexicalization patterns: Semantic Structure in Lexical Form.

32 Dan Jurafsky Predicate Argument divergences: Heads and Argument swapping Heads: English: X swim across Y Spanish: X crucar Y nadando English: I like to eat German: Ich esse gern English: I’d prefer vanilla German: Mir wäre Vanille lieber Arguments: Spanish: Y me gusta English: I like Y German: Der Termin fällt mir ein English: I forget the date Dorr, Bonnie J., "Machine Translation Divergences: A Formal Description and Proposed Solution," Computational Linguistics, 20:4,

33 Dan Jurafsky Predicate-Argument Divergence Counts Found divergences in 32% of sentences in UN Spanish/English Corpus Part of Speech X tener hambre Y have hunger 98% Phrase/Light verb X dar puñaladas a Z X stab Z 83% Structural X entrar en Y X enter Y 35% Heads swap X cruzar Y nadando X swim across Y 8% Arguments swap X gustar a Y Y likes X 6% B.Dorr et al DUSTer: A Method for Unraveling Cross-Language Divergences for Statistical Word-Level Alignment

34 Machine Translation Language Divergences

35 Machine Translation Three classical methods for MT

36 Dan Jurafsky 3 Classical methods for MT Direct Transfer Interlingua

37 Dan Jurafsky Three MT Approaches: Direct, Transfer, Interlingual

38 Dan Jurafsky Direct Translation Proceed word-by-word through text Translating each word No intermediate structures except morphology Knowledge is in the form of Huge bilingual dictionary word-to-word translation information After word translation, can do simple reordering Adjective ordering English -> French/Spanish

39 Dan Jurafsky Direct MT Dictionary entry

40 Dan Jurafsky Direct MT

41 Dan Jurafsky Problems with direct MT German Chinese

42 Dan Jurafsky The Transfer Model Idea: apply contrastive knowledge, i.e., knowledge about the difference between two languages Steps: Analysis: Syntactically parse source language Transfer: Rules to turn this parse into parse for target language Generation: Generate target sentence from parse tree

43 Dan Jurafsky English to French English: Adjective Noun French: Noun Adjective This is not always true Route mauvaise ‘bad road, badly-paved road’ Mauvaise route ‘wrong road’ But is a reasonable first approximation Rule:

44 Dan Jurafsky Transfer rules

45 Dan Jurafsky Transferring the green witch…. 45

46 Dan Jurafsky Interlingua Instead of N 2 sets of transfer rules Use meaning as a representation language 1.Parse source sentence into meaning representation 2.Generate target sentence from meaning. Intuition: Use other NLP applications to do MT work English book to Spanish: libro or reservar Disambiguate book into concepts BOOKVOLUME and RESERVE Need 2N systems (a parser and generator for each language)

47 Dan Jurafsky Interlingua for Mary did not slap the green witch

48 Machine Translation Three classical methods for MT


Download ppt "Machine Translation Introduction to MT. Dan Jurafsky Machine Translation Fully automatic Helping human translators Enter Source Text: Translation from."

Similar presentations


Ads by Google