1 / 69

Lecture 40 of 42

Lecture 40 of 42. NLP and Philosophical Issues Discussion: Machine Translation (MT). Friday, 01 December 2006 William H. Hsu Department of Computing and Information Sciences, KSU KSOL course page: http://snipurl.com/v9v3 Course web site: http://www.kddresearch.org/Courses/Fall-2006/CIS730

maude
Download Presentation

Lecture 40 of 42

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Lecture 40 of 42 NLP and Philosophical Issues Discussion: Machine Translation (MT) Friday, 01 December 2006 William H. Hsu Department of Computing and Information Sciences, KSU KSOL course page: http://snipurl.com/v9v3 Course web site: http://www.kddresearch.org/Courses/Fall-2006/CIS730 Instructor home page: http://www.cis.ksu.edu/~bhsu Reading for Next Class: Sections 22.1, 22.6-7, Russell & Norvig 2nd edition CIS 490 / 730: Artificial Intelligence

  2. A 0.4 B 0.6 E 0.1 F 0.9 A 0.5 G 0.3 H 0.2 0.4 0.5 0.8 C 0.8 D 0.2 0.6 0.5 E 0.3 F 0.7 1 2 3 0.2 A 0.1 G 0.9 (Hidden) Markov Models:Review • Definition of Hidden Markov Models (HMMs) • Stochastic state transition diagram (HMMs: states, akanodes, are hidden) • Compare: probabilistic finite state automaton (Mealy/Moore model) • Annotated transitions (akaarcs, edges, links) • Output alphabet (the observable part) • Probability distribution over outputs • Forward Problem: One Step in ML Estimation • Given: modelh, observations (data) D • Estimate: P(D | h) • Backward Problem: Prediction Step • Given: model h, observations D • Maximize: P(h(X) = x | h, D) for a new X • Forward-Backward (Learning) Problem • Given: model space H, data D • Find: hH such that P(h | D) is maximized (i.e., MAP hypothesis) • HMMs Also A Case of LSQ (f Values in [Roth, 1999]) CIS 490 / 730: Artificial Intelligence

  3. Speech Acts Discourse Labeling Parsing / POS Tagging Lexical Analysis NLP Hierarchy:Review • Problem Definition • Given: m sentences containing untagged words • Example: “The can will rust.” • Label (one per word, out of ~30-150): vj s  (art, n, aux, vi) • Representation: labeled examples <(w1, w2, …, wn), s> • Return: classifier f: XV that tagsx (w1, w2, …, wn) • Applications: WSD, dialogue acts (e.g., “That sounds OK to me.”  ACCEPT) • Solution Approaches: Use Transformation-Based Learning (TBL) • [Brill, 1995]: TBL - mistake-driven algorithm that produces sequences of rules • Each rule of the form (ti, v): a test condition (constructed attribute) and a tag • ti: “w occurs within k words of wi” (context words); collocations (windows) • For more info: see [Roth, 1998], [Samuel, Carberry, Vijay-Shankar, 1998] • Recent Research • E. Brill’s page: http://www.cs.jhu.edu/~brill/ • K. Samuel’s page: http://www.eecis.udel.edu/~samuel/work/research.html Natural Language CIS 490 / 730: Artificial Intelligence

  4. Statistical Machine Translation USC/Information Sciences Institute USC/Computer Science Department Kevin Knight CIS 490 / 730: Artificial Intelligence

  5. 1a. Garcia and associates . 1b. Garcia y asociados . 7a. the clients and the associates are enemies . 7b. los clients y los asociados son enemigos . 2a. Carlos Garcia has three associates . 2b. Carlos Garcia tiene tres asociados . 8a. the company has three groups . 8b. la empresa tiene tres grupos . 3a. his associates are not strong . 3b. sus asociados no son fuertes . 9a. its groups are in Europe . 9b. sus grupos estan en Europa . 4a. Garcia has a company also . 4b. Garcia tambien tiene una empresa . 10a. the modern groups sell strong pharmaceuticals . 10b. los grupos modernos venden medicinas fuertes . 5a. its clients are angry . 5b. sus clientes estan enfadados . 11a. the groups do not sell zenzanine . 11b. los grupos no venden zanzanina . 6a. the associates are also angry . 6b. los asociados tambien estan enfadados . 12a. the small groups are not modern . 12b. los grupos pequenos no son modernos . Spanish/English Parallel Corpora:Review Clients do not sell pharmaceuticals in Europe => Clientes no venden medicinas en Europa CIS 490 / 730: Artificial Intelligence

  6. Data for Statistical MT and data preparation CIS 490 / 730: Artificial Intelligence

  7. Ready-to-Use Online Bilingual Data Millions of words (English side) (Data stripped of formatting, in sentence-pair format, available from the Linguistic Data Consortium at UPenn). CIS 490 / 730: Artificial Intelligence

  8. Ready-to-Use Online Bilingual Data Millions of words (English side) + 1m-20m words for many language pairs (Data stripped of formatting, in sentence-pair format, available from the Linguistic Data Consortium at UPenn). CIS 490 / 730: Artificial Intelligence

  9. Ready-to-Use Online Bilingual Data ??? Millions of words (English side) One Billion? CIS 490 / 730: Artificial Intelligence

  10. From No Data to Sentence Pairs • Easy way: Linguistic Data Consortium (LDC) • Really hard way: pay $$$ • Suppose one billion words of parallel data were sufficient • At 20 cents/word, that’s $200 million • Pretty hard way: Find it, and then earn it! • De-formatting • Remove strange characters • Character code conversion • Document alignment • Sentence alignment • Tokenization (also called Segmentation) CIS 490 / 730: Artificial Intelligence

  11. Sentence Alignment The old man is happy. He has fished many times. His wife talks to him. The fish are jumping. The sharks await. El viejo está feliz porque ha pescado muchos veces. Su mujer habla con él. Los tiburones esperan. CIS 490 / 730: Artificial Intelligence

  12. Sentence Alignment • The old man is happy. • He has fished many times. • His wife talks to him. • The fish are jumping. • The sharks await. • El viejo está feliz porque ha pescado muchos veces. • Su mujer habla con él. • Los tiburones esperan. CIS 490 / 730: Artificial Intelligence

  13. Sentence Alignment • The old man is happy. • He has fished many times. • His wife talks to him. • The fish are jumping. • The sharks await. • El viejo está feliz porque ha pescado muchos veces. • Su mujer habla con él. • Los tiburones esperan. CIS 490 / 730: Artificial Intelligence

  14. Sentence Alignment • The old man is happy. He has fished many times. • His wife talks to him. • The sharks await. • El viejo está feliz porque ha pescado muchos veces. • Su mujer habla con él. • Los tiburones esperan. Note that unaligned sentences are thrown out, and sentences are merged in n-to-m alignments (n, m > 0). CIS 490 / 730: Artificial Intelligence

  15. Tokenization (or Segmentation) • English • Input (some byte stream): "There," said Bob. • Output (7 “tokens” or “words”): " There , " said Bob . • Chinese • Input (byte stream): • Output: 美国关岛国际机场及其办公室均接获一名自称沙地阿拉伯富商拉登等发出的电子邮件。 美国 关岛国 际机 场 及其 办公 室均接获 一名 自称 沙地 阿拉 伯富 商拉登 等发 出 的 电子邮件。 CIS 490 / 730: Artificial Intelligence

  16. MT Evaluation CIS 490 / 730: Artificial Intelligence

  17. MT Evaluation • Manual: • SSER (subjective sentence error rate) • Correct/Incorrect • Error categorization • Testing in an application that uses MT as one sub-component • Question answering from foreign language documents • Automatic: • WER (word error rate) • BLEU (Bilingual Evaluation Understudy) CIS 490 / 730: Artificial Intelligence

  18. BLEU Evaluation Metric (Papineni et al, ACL-2002) Reference (human) translation:The U.S. island of Guam is maintaining a high state of alertafter theGuamairport and itsoffices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such asthe airport . • N-gram precision (score is between 0 & 1) • What percentage of machine n-grams can be found in the reference translation? • An n-gram is an sequence of n words • Not allowed to use same portion of reference translation twice (can’t cheat by typing out “the the the the the”) • Brevity penalty • Can’t just type out single word “the” (precision 1.0!) • *** Amazingly hard to “game” the system (i.e., find a way to change machine output so that BLEU goes up, but quality doesn’t) Machine translation:The American [?] international airport and its the office all receives one calls self the sand Arab rich business [?] and so on electronic mail , which sends out ; The threat will be able after public place and so on the airport to start the biochemistry attack , [?] highly alerts after the maintenance. CIS 490 / 730: Artificial Intelligence

  19. BLEU Evaluation Metric (Papineni et al, ACL-2002) Reference (human) translation:The U.S. island of Guam is maintaining a high state of alertafter theGuamairport and itsoffices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such asthe airport . • BLEU4 formula • (counts n-grams up to length 4) • exp (1.0 * log p1 + • 0.5 * log p2 + • 0.25 * log p3 + • 0.125 * log p4 – • max(words-in-reference / words-in-machine – 1, • 0) • p1 = 1-gram precision • P2 = 2-gram precision • P3 = 3-gram precision • P4 = 4-gram precision Machine translation:The American [?] international airport and its the office all receives one calls self the sand Arab rich business [?] and so on electronic mail , which sends out ; The threat will be able after public place and so on the airport to start the biochemistry attack , [?] highly alerts after the maintenance. CIS 490 / 730: Artificial Intelligence

  20. Multiple Reference Translations Reference translation 1:The U.S. island of Guam is maintaining a high state of alert after the Guam airport and its offices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such as the airport . Reference translation 1:The U.S. island of Guam is maintaining a high state of alert after the Guam airport and its offices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such as the airport . Reference translation 2:Guam International Airport and its offices are maintaining a high state of alert after receiving an e-mail that was from a person claiming to be the wealthy Saudi Arabian businessman Bin Laden and that threatened to launch a biological and chemical attack on the airport and other public places . Reference translation 2:Guam International Airport and its offices are maintaining a high state of alert after receiving an e-mail that was from a person claiming to be the wealthy Saudi Arabian businessman Bin Laden and that threatened to launch a biological and chemical attack on the airport and other public places . Machine translation:The American [?] international airport and its the office all receives one calls self the sand Arab rich business [?] and so on electronic mail , which sends out ; The threat will be able after public place and so on the airport to start the biochemistry attack , [?] highly alerts after the maintenance. Machine translation:The American [?] international airport and itsthe office all receives one calls self the sand Arab rich business [?] and so on electronic mail ,which sends out ; The threat will be able afterpublic place and so on theairportto start the biochemistryattack , [?] highly alerts after the maintenance. Reference translation 3:The US International Airport of Guam and its office has received an email from a self-claimed Arabian millionaire named Laden , which threatens to launch a biochemical attack on such public places as airport . Guam authority has been on alert . Reference translation 3:The US International Airport of Guam and its office has received an email from a self-claimed Arabian millionaire named Laden ,which threatens to launch a biochemical attack on such public places as airport . Guam authority has been on alert . Reference translation 4:US Guam International Airport and its office received an email from Mr. Bin Laden and other rich businessman from Saudi Arabia . They said there would be biochemistry air raid to Guam Airport and other public places . Guam needs to be in high precaution about this matter . Reference translation 4:US Guam International Airport and its office received an email from Mr. Bin Laden and other rich businessman from Saudi Arabia . They said there would be biochemistry air raid to Guam Airport and other public places . Guam needs to be in high precaution about this matter . CIS 490 / 730: Artificial Intelligence

  21. BLEU Tends to Predict Human Judgments (variant of BLEU) slide from G. Doddington (NIST) CIS 490 / 730: Artificial Intelligence

  22. Word-Based Statistical MT CIS 490 / 730: Artificial Intelligence

  23. Statistical MT Systems Spanish/English Bilingual Text English Text Statistical Analysis Statistical Analysis Broken English Spanish English What hunger have I, Hungry I am so, I am so hungry, Have I that hunger … Que hambre tengo yo I am so hungry CIS 490 / 730: Artificial Intelligence

  24. Statistical MT Systems Spanish/English Bilingual Text English Text Statistical Analysis Statistical Analysis Broken English Spanish English Translation Model P(s|e) Language Model P(e) Que hambre tengo yo I am so hungry Decoding algorithm argmax P(e) * P(s|e) e CIS 490 / 730: Artificial Intelligence

  25. Three Problems for Statistical MT • Language model • Given an English string e, assigns P(e) by formula • good English string -> high P(e) • random word sequence -> low P(e) • Translation model • Given a pair of strings <f,e>, assigns P(f | e) by formula • <f,e> look like translations -> high P(f | e) • <f,e> don’t look like translations -> low P(f | e) • Decoding algorithm • Given a language model, a translation model, and a new sentence f … find translation e maximizing P(e) * P(f | e) CIS 490 / 730: Artificial Intelligence

  26. The Classic Language ModelWord N-Grams Goal of the language model -- choose among: He is on the soccer field He is in the soccer field Is table the on cup the The cup is on the table Rice shrine American shrine Rice company American company CIS 490 / 730: Artificial Intelligence

  27. The Classic Language ModelWord N-Grams Generative approach: w1 = START repeat until END is generated: produce word w2 according to a big table P(w2 | w1) w1 := w2 P(I saw water on the table) = P(I | START) * P(saw | I) * P(water | saw) * P(on | water) * P(the | on) * P(table | the) * P(END | table) Probabilities can be learned from online English text. CIS 490 / 730: Artificial Intelligence

  28. Translation Model? Generative approach: Mary did not slap the green witch Source-language morphological analysis Source parse tree Semantic representation Generate target structure Maria no dió una botefada a la bruja verde CIS 490 / 730: Artificial Intelligence

  29. Translation Model? Generative story: Mary did not slap the green witch Source-language morphological analysis Source parse tree Semantic representation Generate target structure What are all the possible moves and their associated probability tables? Maria no dió una botefada a la bruja verde CIS 490 / 730: Artificial Intelligence

  30. The Classic Translation ModelWord Substitution/Permutation [IBM Model 3, Brown et al., 1993] Generative approach: Mary did not slap the green witch n(3|slap) Mary not slap slap slap the green witch P-Null Mary not slap slap slap NULL the green witch t(la|the) Maria no dió una botefada a la verde bruja d(j|i) Maria no dió una botefada a la bruja verde Probabilities can be learned from raw bilingual text. CIS 490 / 730: Artificial Intelligence

  31. Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … All word alignments equally likely All P(french-word | english-word) equally likely CIS 490 / 730: Artificial Intelligence

  32. Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … “la” and “the” observed to co-occur frequently, so P(la | the) is increased. CIS 490 / 730: Artificial Intelligence

  33. Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … “house” co-occurs with both “la” and “maison”, but P(maison | house) can be raised without limit, to 1.0, while P(la | house) is limited because of “the” (pigeonhole principle) CIS 490 / 730: Artificial Intelligence

  34. Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … settling down after another iteration CIS 490 / 730: Artificial Intelligence

  35. Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … • Inherent hidden structure revealed by EM training! • For details, see: • “A Statistical MT Tutorial Workbook” (Knight, 1999). • “The Mathematics of Statistical Machine Translation” (Brown et al, 1993) • Software: GIZA++ CIS 490 / 730: Artificial Intelligence

  36. Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … P(juste | fair) = 0.411 P(juste | correct) = 0.027 P(juste | right) = 0.020 … Possible English translations, to be rescored by language model new French sentence CIS 490 / 730: Artificial Intelligence

  37. Decoding for “Classic” Models • Of all conceivable English word strings, find the one maximizing P(e) x P(f | e) • Decoding is an NP-complete challenge • (Knight, 1999) • Several search strategies are available • Each potential English output is called a hypothesis. CIS 490 / 730: Artificial Intelligence

  38. The Classic Results • la politique de la haine . (Foreign Original) • politics of hate . (Reference Translation) • the policy of the hatred . (IBM4+N-grams+Stack) • nous avons signé le protocole . (Foreign Original) • we did sign the memorandum of agreement . (Reference Translation) • we have signed the protocol . (IBM4+N-grams+Stack) • où était le plan solide ? (Foreign Original) • but where was the solid plan ? (Reference Translation) • where was the economic base ? (IBM4+N-grams+Stack) the Ministry of Foreign Trade and Economic Cooperation, including foreign direct investment 40.007 billion US dollars today provide data include that year to November china actually using foreign 46.959 billion US dollars and CIS 490 / 730: Artificial Intelligence

  39. Flaws of Word-Based MT • Multiple English words for one French word • IBM models can do one-to-many (fertility) but not many-to-one • Phrasal Translation • “real estate”, “note that”, “interest in” • Syntactic Transformations • Verb at the beginning in Arabic • Translation model penalizes any proposed re-ordering • Language model not strong enough to force the verb to move to the right place CIS 490 / 730: Artificial Intelligence

  40. Phrase-Based Statistical MT CIS 490 / 730: Artificial Intelligence

  41. Phrase-Based Statistical MT Morgen fliege ich nach Kanada zur Konferenz Tomorrow I will fly to the conference In Canada • Foreign input segmented in to phrases • “phrase” is any sequence of words • Each phrase is probabilistically translated into English • P(to the conference | zur Konferenz) • P(into the meeting | zur Konferenz) • Phrases are probabilistically re-ordered See [Koehn et al, 2003] for an intro. This is state-of-the-art! CIS 490 / 730: Artificial Intelligence

  42. Advantages of Phrase-Based • Many-to-many mappings can handle non-compositional phrases • Local context is very useful for disambiguating • “Interest rate”  … • “Interest in”  … • The more data, the longer the learned phrases • Sometimes whole sentences CIS 490 / 730: Artificial Intelligence

  43. How to Learn the Phrase Translation Table? • One method: “alignment templates” (Och et al, 1999) • Start with word alignment, build phrases from that. Maria no dió una bofetada a la bruja verde This word-to-word alignment is a by-product of training a translation model like IBM-Model-3. This is the best (or “Viterbi”) alignment. Mary did not slap the green witch CIS 490 / 730: Artificial Intelligence

  44. How to Learn the Phrase Translation Table? • One method: “alignment templates” (Och et al, 1999) • Start with word alignment, build phrases from that. Maria no dió una bofetada a la bruja verde This word-to-word alignment is a by-product of training a translation model like IBM-Model-3. This is the best (or “Viterbi”) alignment. Mary did not slap the green witch CIS 490 / 730: Artificial Intelligence

  45. IBM Models are 1-to-Many • Run IBM-style aligner both directions, then merge: EF best alignment MERGE FE best alignment Union or Intersection CIS 490 / 730: Artificial Intelligence

  46. How to Learn the Phrase Translation Table? • Collect all phrase pairs that are consistent with the word alignment Maria no dió una bofetada a la bruja verde Mary did not slap the green witch one example phrase pair CIS 490 / 730: Artificial Intelligence

  47. Consistent with Word Alignment Maria no dió Maria no dió Maria no dió Mary did not slap Mary did not slap Mary did not slap consistent inconsistent inconsistent Phrase alignment must contain all alignment points for all the words in both phrases! CIS 490 / 730: Artificial Intelligence

  48. Word Alignment Induced Phrases Maria no dió una bofetada a la bruja verde Mary did not slap the green witch (Maria, Mary) (no, did not) (slap, dió una bofetada) (la, the) (bruja, witch) (verde, green) CIS 490 / 730: Artificial Intelligence

  49. Word Alignment Induced Phrases Maria no dió una bofetada a la bruja verde Mary did not slap the green witch (Maria, Mary) (no, did not) (slap, dió una bofetada) (la, the) (bruja, witch) (verde, green) (a la, the) (dió una bofetada a, slap the) CIS 490 / 730: Artificial Intelligence

  50. Word Alignment Induced Phrases Maria no dió una bofetada a la bruja verde Mary did not slap the green witch (Maria, Mary) (no, did not) (slap, dió una bofetada) (la, the) (bruja, witch) (verde, green) (a la, the) (dió una bofetada a, slap the) (Maria no, Mary did not) (no dió una bofetada, did not slap), (dió una bofetada a la, slap the) (bruja verde, green witch) CIS 490 / 730: Artificial Intelligence

More Related