1. Rapid Prototyping of a Transfer-based Hebrew-to-English Machine Translation System Alon Lavie Language Technologies Institute Carnegie Mellon University Joint work with: Shuly Wintner, Danny Shacham, Nurit Melnik, Yuval Krymolowski - University of Haifa Erik Peterson – Carnegie Mellon University

2. June 20, 2007ISCOL/BISFAI-20072 Outline Context of this Work CMU Statistical Transfer MT Framework Hebrew and its Challenges for MT Hebrew-to-English System Morphological Analysis and Generation MT Resources: lexicon and grammar Translation Examples Performance Evaluation Conclusions, Current and Future Work

3. June 20, 2007ISCOL/BISFAI-20073 Current State-of-the-art in Machine Translation MT underwent a major paradigm shift over the past 15 years: –From manually crafted rule-based systems with manually designed knowledge resources –To search-based approaches founded on automatic extraction of translation models/units from large sentence- parallel corpora Current Dominant Approach: Phrase-based Statistical MT: –Extract and statistically model large volumes of phrase-to- phrase correspondences from automatically word-aligned parallel corpora –“Decode” new input by searching for the most likely sequence of phrase matches, using a statistical Language Model for the target language

4. June 20, 2007ISCOL/BISFAI-20074 Current State-of-the-art in Machine Translation Phrase-based MT State-of-the-art: –Requires minimally several million words of parallel text for adequate training –Limited to language-pairs for which such data exists: major European languages, Chinese, Japanese, a few others… –Linguistically shallow and highly lexicalized models result in weak generalization –Best performance levels (BLEU=~0.6) on Arabic-to- English provide understandable but often still somewhat disfluent translations –Ill suited for Hebrew and most of the world’s minor languages

5. June 20, 2007ISCOL/BISFAI-20075 CMU’s Statistical-Transfer (XFER) Approach Framework: Statistical search-based approach with syntactic translation transfer rules that can be acquired from data but also developed and extended by experts Elicitation: use bilingual native informants to produce a small high-quality word-aligned bilingual corpus of translated phrases and sentences Transfer-rule Learning: apply ML-based methods to automatically acquire syntactic transfer rules for translation between the two languages XFER + Decoder: –XFER engine produces a lattice of possible transferred structures at all levels –Decoder searches and selects the best scoring combination Rule Refinement: refine the acquired rules via a process of interaction with bilingual informants Word and Phrase bilingual lexicon acquisition

6. Transfer Engine English Language Model Transfer Rules {NP1,3} NP1::NP1 [NP1 "H" ADJ] -> [ADJ NP1] ((X3::Y1) (X1::Y2) ((X1 def) = +) ((X1 status) =c absolute) ((X1 num) = (X3 num)) ((X1 gen) = (X3 gen)) (X0 = X1)) Translation Lexicon N::N |: ["$WR"] -> ["BULL"] ((X1::Y1) ((X0 NUM) = s) ((Y0 lex) = "BULL")) N::N |: ["$WRH"] -> ["LINE"] ((X1::Y1) ((X0 NUM) = s) ((Y0 lex) = "LINE")) Hebrew Input בשורה הבאה Decoder English Output in the next line Translation Output Lattice (0 1 "IN" @PREP) (1 1 "THE" @DET) (2 2 "LINE" @N) (1 2 "THE LINE" @NP) (0 2 "IN LINE" @PP) (0 4 "IN THE NEXT LINE" @PP) Preprocessing Morphology

7. June 20, 2007ISCOL/BISFAI-20077 Transfer Rule Formalism Type information Part-of-speech/constituent information Alignments x-side constraints y-side constraints xy-constraints, e.g. ((Y1 AGR) = (X1 AGR)) ; SL: the old man, TL: ha-ish ha-zaqen NP::NP [DET ADJ N] -> [DET N DET ADJ] ( (X1::Y1) (X1::Y3) (X2::Y4) (X3::Y2) ((X1 AGR) = *3-SING) ((X1 DEF = *DEF) ((X3 AGR) = *3-SING) ((X3 COUNT) = +) ((Y1 DEF) = *DEF) ((Y3 DEF) = *DEF) ((Y2 AGR) = *3-SING) ((Y2 GENDER) = (Y4 GENDER)) )

8. June 20, 2007ISCOL/BISFAI-20078 The Transfer Engine Main algorithm: chart-style bottom-up integrated parsing+transfer with beam pruning –Seeded by word-to-word translations –Driven by transfer rules –Generates a lattice of transferred translation segments at all levels Some Unique Features: –Works with either learned or manually-developed transfer grammars –Handles rules with or without unification constraints –Supports interfacing with servers for morphological analysis and generation –Can handle ambiguous source-word analyses and/or SL segmentations represented in the form of lattice structures

9. June 20, 2007ISCOL/BISFAI-20079 XFER Output Lattice (28 28 "AND" -5.6988 "W" "(CONJ,0 'AND')") (29 29 "SINCE" -8.20817 "MAZ " "(ADVP,0 (ADV,5 'SINCE')) ") (29 29 "SINCE THEN" -12.0165 "MAZ " "(ADVP,0 (ADV,6 'SINCE THEN')) ") (29 29 "EVER SINCE" -12.5564 "MAZ " "(ADVP,0 (ADV,4 'EVER SINCE')) ") (30 30 "WORKED" -10.9913 "&BD " "(VERB,0 (V,11 'WORKED')) ") (30 30 "FUNCTIONED" -16.0023 "&BD " "(VERB,0 (V,10 'FUNCTIONED')) ") (30 30 "WORSHIPPED" -17.3393 "&BD " "(VERB,0 (V,12 'WORSHIPPED')) ") (30 30 "SERVED" -11.5161 "&BD " "(VERB,0 (V,14 'SERVED')) ") (30 30 "SLAVE" -13.9523 "&BD " "(NP0,0 (N,34 'SLAVE')) ") (30 30 "BONDSMAN" -18.0325 "&BD " "(NP0,0 (N,36 'BONDSMAN')) ") (30 30 "A SLAVE" -16.8671 "&BD " "(NP,1 (LITERAL 'A') (NP2,0 (NP1,0 (NP0,0 (N,34 'SLAVE')) ) ) ) ") (30 30 "A BONDSMAN" -21.0649 "&BD " "(NP,1 (LITERAL 'A') (NP2,0 (NP1,0 (NP0,0 (N,36 'BONDSMAN')) ) ) ) ")

10. June 20, 2007ISCOL/BISFAI-200710 The Lattice Decoder Simple Stack Decoder, similar in principle to simple Statistical MT decoders Searches for best-scoring path of non-overlapping lattice arcs No reordering during decoding Scoring based on log-linear combination of scoring components, with weights trained using MERT Scoring components: –Statistical Language Model –Fragmentation: how many arcs to cover the entire translation? –Length Penalty –Rule Scores –Lexical Probabilities (not fully integrated)

11. June 20, 2007ISCOL/BISFAI-200711 XFER Lattice Decoder 0 0 ON THE FOURTH DAY THE LION ATE THE RABBIT TO A MORNING MEAL Overall: -8.18323, Prob: -94.382, Rules: 0, Frag: 0.153846, Length: 0, Words: 13,13 235 < 0 8 -19.7602: B H IWM RBI&I (PP,0 (PREP,3 'ON')(NP,2 (LITERAL 'THE') (NP2,0 (NP1,1 (ADJ,2 (QUANT,0 'FOURTH'))(NP1,0 (NP0,1 (N,6 'DAY')))))))> 918 < 8 14 -46.2973: H ARIH AKL AT H $PN (S,2 (NP,2 (LITERAL 'THE') (NP2,0 (NP1,0 (NP0,1 (N,17 'LION')))))(VERB,0 (V,0 'ATE'))(NP,100 (NP,2 (LITERAL 'THE') (NP2,0 (NP1,0 (NP0,1 (N,24 'RABBIT')))))))> 584 < 14 17 -30.6607: L ARWXH BWQR (PP,0 (PREP,6 'TO')(NP,1 (LITERAL 'A') (NP2,0 (NP1,0 (NNP,3 (NP0,0 (N,32 'MORNING'))(NP0,0 (N,27 'MEAL')))))))>

12. June 20, 2007ISCOL/BISFAI-200712 XFER MT Prototypes General XFER framework under development for past five years Prototype systems so far: –German-to-English –Dutch-to-English –Chinese-to-English –Hindi-to-English –Hebrew-to-English In progress or planned: –Mapudungun-to-Spanish –Quechua-to-Spanish –Brazilian Portuguese-to-English –Native-Brazilian languages to Brazilian Portuguese –Hebrew-to-Arabic

13. June 20, 2007ISCOL/BISFAI-200713 Challenges for Hebrew MT Puacity in existing language resources for Hebrew –No publicly available broad coverage morphological analyzer –No publicly available bilingual lexicons or dictionaries –No POS-tagged corpus or parse tree-bank corpus for Hebrew –No large Hebrew/English parallel corpus Scenario well suited for CMU transfer-based MT framework for languages with limited resources

14. June 20, 2007ISCOL/BISFAI-200714 Modern Hebrew Spelling Two main spelling variants –“KTIV XASER” (difficient): spelling with the vowel diacritics, and consonant words when the diacritics are removed –“KTIV MALEH” (full): words with I/O/U vowels are written with long vowels which include a letter KTIV MALEH is predominant, but not strictly adhered to even in newspapers and official publications  inconsistent spelling Example: –niqud (spelling): NIQWD, NQWD, NQD –When written as NQD, could also be niqed, naqed, nuqad

15. June 20, 2007ISCOL/BISFAI-200715 Morphological Analyzer We use a publicly available morphological analyzer distributed by the Technion’s Knowledge Center, adapted for our system Coverage is reasonable (for nouns, verbs and adjectives) Produces all analyses or a disambiguated analysis for each word Output format includes lexeme (base form), POS, morphological features Output was adapted to our representation needs (POS and feature mappings)

16. June 20, 2007ISCOL/BISFAI-200716 Morphology Example Input word: B$WRH 0 1 2 3 4 |--------B$WRH--------| |-----B-----|$WR|--H--| |--B--|-H--|--$WRH---|

17. June 20, 2007ISCOL/BISFAI-200717 Morphology Example Y0: ((SPANSTART 0) Y1: ((SPANSTART 0) Y2: ((SPANSTART 1) (SPANEND 4) (SPANEND 2) (SPANEND 3) (LEX B$WRH) (LEX B) (LEX $WR) (POS N) (POS PREP)) (POS N) (GEN F) (GEN M) (NUM S) (NUM S) (STATUS ABSOLUTE)) (STATUS ABSOLUTE)) Y3: ((SPANSTART 3) Y4: ((SPANSTART 0) Y5: ((SPANSTART 1) (SPANEND 4) (SPANEND 1) (SPANEND 2) (LEX $LH) (LEX B) (LEX H) (POS POSS)) (POS PREP)) (POS DET)) Y6: ((SPANSTART 2) Y7: ((SPANSTART 0) (SPANEND 4) (SPANEND 4) (LEX $WRH) (LEX B$WRH) (POS N) (POS LEX)) (GEN F) (NUM S) (STATUS ABSOLUTE))

18. June 20, 2007ISCOL/BISFAI-200718 Translation Lexicon Constructed our own Hebrew-to-English lexicon, based primarily on existing “Dahan” H-to-E and E-to-H dictionary made available to us, augmented by other public sources Coverage is not great but not bad as a start –Dahan H-to-E is about 15K translation pairs –Dahan E-to-H is about 7K translation pairs Base forms, POS information on both sides Converted Dahan into our representation, added entries for missing closed-class entries (pronouns, prepositions, etc.) Had to deal with spelling conventions Recently augmented with ~50K translation pairs extracted from Wikipedia (mostly proper names and named entities)

19. June 20, 2007ISCOL/BISFAI-200719 Manual Transfer Grammar (human-developed) Initially developed by Alon in a couple of days, extended and revised by Nurit over time Current grammar has 36 rules: –21 NP rules –one PP rule –6 verb complexes and VP rules –8 higher-phrase and sentence-level rules Captures the most common (mostly local) structural differences between Hebrew and English

20. June 20, 2007ISCOL/BISFAI-200720 Transfer Grammar Example Rules {NP1,2} ;;SL: $MLH ADWMH ;;TL: A RED DRESS NP1::NP1 [NP1 ADJ] -> [ADJ NP1] ( (X2::Y1) (X1::Y2) ((X1 def) = -) ((X1 status) =c absolute) ((X1 num) = (X2 num)) ((X1 gen) = (X2 gen)) (X0 = X1) ) {NP1,3} ;;SL: H $MLWT H ADWMWT ;;TL: THE RED DRESSES NP1::NP1 [NP1 "H" ADJ] -> [ADJ NP1] ( (X3::Y1) (X1::Y2) ((X1 def) = +) ((X1 status) =c absolute) ((X1 num) = (X3 num)) ((X1 gen) = (X3 gen)) (X0 = X1) )

21. June 20, 2007ISCOL/BISFAI-200721 Hebrew-to-English MT Prototype Initial prototype developed within a two month intensive effort Accomplished: –Adapted available morphological analyzer –Constructed a preliminary translation lexicon –Translated and aligned Elicitation Corpus –Learned XFER rules –Developed (small) manual XFER grammar –System debugging and development –Evaluated performance on unseen test data using automatic evaluation metrics

22. June 20, 2007ISCOL/BISFAI-200722 Example Translation Input: – לאחר דיונים רבים החליטה הממשלה לערוך משאל עם בנושא הנסיגה –After debates many decided the government to hold referendum in issue the withdrawal Output: –AFTER MANY DEBATES THE GOVERNMENT DECIDED TO HOLD A REFERENDUM ON THE ISSUE OF THE WITHDRAWAL

23. June 20, 2007ISCOL/BISFAI-200723 Noun Phrases – Construct State HXL@T[HNSIAHRA$WN] decision.3SF-CSthe-president.3SMthe-first.3SM החלטת הנשיא הראשון החלטת הנשיא הראשונה [HXL@THNSIA]HRA$WNH decision.3SF-CSthe-president.3SMthe-first.3SF THE DECISION OF THE FIRST PRESIDENT THE FIRST DECISION OF THE PRESIDENT

24. June 20, 2007ISCOL/BISFAI-200724 Noun Phrases - Possessives HNSIAHKRIZ$HM$IMHHRA$WNH$LWTHIH the-presidentannouncedthat-the-task.3SFthe-first.3SFof-himwill.3SF LMCWA PTRWNLSKSWKBAZWRNW to-findsolutionto-the-conflictin-region-POSS.1P הנשיא הכריז שהמשימה הראשונה שלו תהיה למצוא פתרון לסכסוך באזורנו Without transfer grammar: THE PRESIDENT ANNOUNCED THAT THE TASK THE BEST OF HIM WILL BE TO FIND SOLUTION TO THE CONFLICT IN REGION OUR With transfer grammar: THE PRESIDENT ANNOUNCED THAT HIS FIRST TASK WILL BE TO FIND A SOLUTION TO THE CONFLICT IN OUR REGION

25. June 20, 2007ISCOL/BISFAI-200725 Subject-Verb Inversion ATMWLHWDI&HHMM$LH yesterdayannounced.3SFthe-government.3SF אתמול הודיעה הממשלה שתערכנה בחירות בחודש הבא $T&RKNHBXIRWTBXWD$HBA that-will-be-held.3PFelections.3PFin-the-monththe-next Without transfer grammar: YESTERDAY ANNOUNCED THE GOVERNMENT THAT WILL RESPECT OF THE FREEDOM OF THE MONTH THE NEXT With transfer grammar: YESTERDAY THE GOVERNMENT ANNOUNCED THAT ELECTIONS WILL ASSUME IN THE NEXT MONTH

26. June 20, 2007ISCOL/BISFAI-200726 Subject-Verb Inversion LPNIKMH$BW&WTHWDI&HHNHLTHMLWN beforeseveralweeksannounced.3SFmanagement.3SF.CSthe-hotel לפני כמה שבועות הודיעה הנהלת המלון שהמלון יסגר בסוף השנה $HMLWNISGRBSWFH$NH that-the-hotel.3SMwill-be-closed.3SMat-end.3SM.CSthe-year Without transfer grammar: IN FRONT OF A FEW WEEKS ANNOUNCED ADMINISTRATION THE HOTEL THAT THE HOTEL WILL CLOSE AT THE END THIS YEAR With transfer grammar: SEVERAL WEEKS AGO THE MANAGEMENT OF THE HOTEL ANNOUNCED THAT THE HOTEL WILL CLOSE AT THE END OF THE YEAR

27. June 20, 2007ISCOL/BISFAI-200727 Evaluation Results Test set of 62 sentences from Haaretz newspaper, 2 reference translations SystemBLEUNISTPRMETEOR No Gram0.06163.41090.40900.44270.3298 Learned0.07743.54510.41890.44880.3478 Manual0.10263.77890.43340.44740.3617

28. June 20, 2007ISCOL/BISFAI-200728 Current and Future Work Issues specific to the Hebrew-to-English system: –Coverage: further improvements in the translation lexicon and morphological analyzer –Manual Grammar development –Acquiring/training of word-to-word translation probabilities –Acquiring/training of a Hebrew language model at a post- morphology level that can help with disambiguation General Issues related to XFER framework: –Discriminative Language Modeling for MT –Effective models for assigning scores to transfer rules –Improved grammar learning –Merging/integration of manual and acquired grammars

29. June 20, 2007ISCOL/BISFAI-200729 Conclusions Test case for the CMU XFER framework for rapid MT prototyping Preliminary system was a two-month, three person effort – we were quite happy with the outcome Core concept of XFER + Decoding is very powerful and promising for MT We experienced the main bottlenecks of knowledge acquisition for MT: morphology, translation lexicons, grammar...

30. June 20, 2007ISCOL/BISFAI-200730 Questions?