8. qun liu (dcu) hybrid solutions for translation

97
Hybrid Solutions for Translation: Going hybrid Qun Liu (DCU) Dr. Manuel Herranz (Pangeanic) 12 November 2013, Birmingham, UK

Upload: riilp

Post on 10-May-2015

575 views

Category:

Technology


1 download

TRANSCRIPT

Page 1: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Hybrid Solutions for Translation: Going hybrid

Qun Liu (DCU)Dr. Manuel Herranz (Pangeanic)

12 November 2013, Birmingham, UK

Page 2: 8. Qun Liu (DCU) Hybrid Solutions for Translation

PART A

Qun Liu (DCU)[email protected]

Page 3: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Outline

Why Hybrid MT? An overview of Hybrid MT Typical Hybrid MT Approaches Conclusion

Page 4: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

MT Approaches

RBMT: Rule-based Machine Translation

EBMT: Example-based Machine Translation

TM: Translation Memory

SMT: Statistical Machine Translation

Page 5: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

RBMT: Vauquois’ Triangle

Syntactic Transfer

Semantic Transfer

Interlingua

DirectSource Language Target Language

Analysis Generation

Page 6: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

RBMT: Rules for Components

Analysis

Morphological Analysis Source Morphological Rules

Syntactic Analysis (Parsing) Source Grammar

Semantic Analysis Source Semantic Rules

Transfer

Lexical Transfer Bilingual Lexicon

Syntactic Transfer Syntactic Mapping Rules

Semantic Transfer Semantic Mapping Rules

Generation

Semantic Generation Target Semantic Rules

Syntactic Generation Target Grammar

Morphological Generation Target Morphological Rules

Page 7: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

RBMT: an Example

Page 8: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

RBMT: an Example

Page 9: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

RBMT: an Example

Page 10: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

RBMT: an Example

Page 11: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

RBMT: an Example

Page 12: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

RBMT

RBMT makes use of human encoded linguistic rules for translation

Development of a RBMT system is very expensive because it needs plenty of human labour and takes a long time (years)

Page 13: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

RBMT

RBMT systems can reach good translation quality after years of development in the given domain.

Well developed RBMT systems tend to better capture large size sentence structures but perform worse on small size expressions compared with SMT systems.

Page 14: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

EBMT

An EBMT system translate sentences by analog of existing translation examples

EBMT does not need deep analysis of source text and may generate high quality translation when similar examples are found

Page 15: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

EBMT

Page 16: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

EBMT

Quality of EBMT increases while we get more examples.

A problem of EBMT is the coverage of the examples, especially for long sentences.

Page 17: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

TM

Translation Memory directly output existing target sentence when a very similar source sentence is found in the memory, or it outputs nothing.

Page 18: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

SMT

SMT builds statistical models to predict the probability of a target sentence being the translation of a given source sentence.

To translate a given source sentence is just to search for a target sentence with the highest translation probability.

Page 19: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

SMT

A large number of translation pairs (parallel corpus) is needed to estimate the model parameters.

To predict the translation, sentence pairs are broken into smaller translation equivalence, either in word level, or in phrase level or syntax rule level.

Page 20: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Word-based SMT

Page 21: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Word-based SMTSource Target Probability

Bushi (布什) Bush 0.7

President 0.2

US 0.1

yu (与) and 0.6

with 0.4

juxing (举行) hold 0.7

had 0.3

le (了) hold 0.01

... ...

Page 22: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Phrase-based SMT

Page 23: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Phrase-based SMTSource Target Probability

Bushi (布什) Bush 0.5

president Bush 0.3

the US president 0.2

Bushi yu (布什与) Bush and 0.8

the president and 0.2

yu Shalong (与沙龙) and Shalong 0.6

with Shalong 0.4

juxing le huiang (举行了会谈) hold a meeting 0.7

had a meeting 0.3

Page 24: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Hierarchical Phrased-based SMT

Page 25: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Hierarchical Phrased-based SMTSource Target Probability

juxing le huiang (举行了会谈) hold a meeting 0.6

had a meeting 0.3

X huitang (X会谈) X a meeting 0.8

X a talk 0.2

juxing le X (举行了X) hold a X 0.5

had a X 0.5

Bushi yu Shalong (布什与沙龙) Bush and Sharon 0.8

Bushi X (布什X) Bush X 0.7

X yu Y (X与Y) X and Y 0.9

Page 26: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Syntax-based SMT

Page 27: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Syntax-based SMT

Source Target Probability

VPB(VS(juxing) AS(le) NPB(huiang)) (举行了会谈)

hold a meeting 0.6

have a meeting 0.3

have a talk 0.1

VPB(VS(juxing) AS(le) x1:NPB) (举行了x1)

hold a x1 0.5

have a x1 0.5

VP(PP(P(yu) x1:NPB) x2:VPB) (与 x1 x2) x2 with x1 0.9

IP(x1:NPB VP(x2:PP x3:VPB)) x1 x3 x2 0.7

Page 28: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

SMT

SMT is cheap SMT systems can be developed in a

short time SMT needs a large number of parallel

corpus

Page 29: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

SMT

SMT gets good quality translations if we have plenty of in-domain data

SMT quality drops dramatically for out-of-domain data

SMT results is fluent in short phrases but not good at large size sentence structures (esp. for distant languages)

Page 30: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Why Hybrid MT?

Each MT approach has its pros and cons.

We want to take advantage of different MT approaches

We do not want to waste our investments on existing MT systems

Page 31: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Outline

Why Hybrid MT? An overview of Hybrid MT Typical Hybrid MT Approaches Conclusion

Page 32: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

An overview of Hybrid MT

Selective MT: loose coupling Pipelined MT: medium coupling Mixture MT: close coupling

Page 33: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Selective MT

Given translations generated by different approaches, Selective MT tries to select a best one, or select best parts from different translations and combine them to a new one.

Page 34: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Selective MT

MT1

MT3

SelectMT2

Source

Target

Target

Page 35: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Selective MT

MT1

MT3

SelectMT2

Source

Target

Target

Page 36: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Selective MT

Typical Selective MT:System RecommendationSystem Combination Sentence-level combination word-level combination

Page 37: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Pipelined MT

Pipelined MT adopts one approach as the main approach and use another approach for monolingual pre-processing or post-processing.

Page 38: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Pipelined MT

Main ApproachPre-Processing Post-Processing

Page 39: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Pipelined MT

Typical Pipelined MT:Statistical Post-Editing for RBMTRule-based Pre-reordering for SMT

Page 40: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Mixture MT

Mixture MT adopts one approach as the main approach but utilizes one or more different approaches in some components.

Page 41: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Mixture MT

Page 42: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Mixture MT

Typical Mixture MT:Statistical Parsing in RBMTRule-based Named Entity Translation

in SMTHuman-Encoded Rules in SMTSMT Decoding with TM Phrases

Page 43: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Outline

Why Hybrid MT? An overview of Hybrid MT Typical Hybrid MT Approaches Conclusion

Page 44: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Typical Hybrid MT Approaches

Selective MTSystem RecommendationSystem Combination

Pipelined MT Mixture MT

Page 45: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Recommendation

Yifan He, Yanjun Ma, Josef van Genabith and Andy

Way, Bridging SMT and TM with System

Recommendation, Proceedings of the 48th Annual

Meeting of the Association for Computational

Linguistics (ACL2010), pages 622–630, Uppsala,

Sweden, 11-16 July 2010.

Page 46: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Recommendation

Intuition: In some cases when we have enough big

translation memory, the trained SMT system is comparable with TM output in translation quality. Here comes the problem of selection.

System recommendation recommends SMT outputs to a TM user when it predicts that SMT outputs are more suitable for post-editing than the hits provided by the TM

Page 47: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Recommendation

TM

SMT

SystemRecommendation

Parallel Corpus

Page 48: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Recommendation

A SVM binary classifier is adopted The classifier is trained on human-

annotated data A confidence score is given for the

recommendation

Page 49: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Recommendation

SMT System Features: features used in the SMT system

TM Feature: Fuzzy Match Cost

System Independent Features: Source-Side Language Model Score and Perplexity

Target-Side Language Model Perplexity

The Pseudo-Source Fuzzy Match Score

The IBM Model 1 Score.

Page 50: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Recommendation

Evaluation Metrics:

Where A is the set of recommended MT outputs, and B is the set of MT outputs that have lower TER than TM hits.

Page 51: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Recommendation

Page 52: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Recommendation

Page 53: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Typical Hybrid MT Approaches

Selective MTSystem RecommendationSystem Combination

Pipelined MT Mixture MT

Page 54: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Combination

Rosti, A. V. I., Ayan, N. F., Xiang, B., Matsoukas, S., Schwartz, R. M., & Dorr, B. J. (2007, April). Combining Outputs from Multiple Machine Translation Systems. In HLT-NAACL (pp. 228-235).

Page 55: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Combination

Rosti, A. V. I., Matsoukas, S., & Schwartz, R. (2007, June). Improved word-level system combination for machine translation. In ANNUAL MEETING-ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (Vol. 45, No. 1, p. 312).

Page 56: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Combination

He, X., Yang, M., Gao, J., Nguyen, P., & Moore, R. 2008. Indirect-HMM-based hypothesis alignment for combining outputs from machine translation systems. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (pp. 98-107). Association for Computational Linguistics.

Page 57: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

System Combination

Feng, Y., Liu, Y., Mi, H., Liu, Q., & Lü, Y. 2009. Lattice-based system combination for statistical machine translation. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3-Volume 3 (pp. 1105-1113). Association for Computational Linguistics.

Page 58: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Sentence-Level System Combination

Kumar, S., & Byrne, W. J. (2004, May). Minimum Bayes-Risk Decoding for Statistical Machine Translation. In HLT-NAACL (pp. 169-176).

Page 59: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Sentence-Level System Combination

Consider we have several MT systems For a given source text F, each MT system

output a n-best target text If possible, MT system gives each target

text a probability P(E|F), or we may consider the n-best target text with equal probabilities.

Page 60: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Sentence-Level System Combination

Minimum Bayes-Risk (MBR):

Page 61: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Word-LevelSystem Combination

Select a translation candidate as a skeleton (backbone) with Minimal Bayes Risk

Construct a confusion network by aligning all the words in other translation candidates to the words in the skeleton

Select the best path from the confusion network and generate a new translation

Page 62: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Translation Candidate

Skeleton

Page 63: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Word Alignment against the Skeleton

Skeleton

Page 64: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Confusion Network

Final output: Please show me on the map.

Page 65: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Word-LevelSystem Combination

System combination is proved to be very effective

In NIST Open MT Evaluation Chinese-English task, MSR-NRC-SRI ranked no.1 by using system combination technologies

In later NIST evaluations, different tracks are defined participants using or not using system combination technologies.

Page 66: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Typical Hybrid MT Approaches

Selective MT Pipelined MTStatistical Post-Editing for RBMTRule-based Pre-reordering for SMT

Mixture MT

Page 67: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Statistical Post-Editing for RBMT

Dugast, L., Senellart, J., & Koehn, P. (2007, June). Statistical post-editing on SYSTRAN's rule-based translation system. In Proceedings of the Second Workshop on Statistical Machine Translation (pp. 220-223). Association for Computational Linguistics.

Page 68: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Statistical Post-Editing for RBMT

Simard, M., Ueffing, N., Isabelle, P., & Kuhn, R. (2007). Rule-based Translation With Statistical Phrase-based Post-editing. Second Workshop on Statistical Machine Translation. Prague, Czech Republic. June 23, 2007. pp. 203–206.

Page 69: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Statistical Post-Editing

When we have: A very good RBMT system Large number of parallel corpus which can be

used for SMT training Both RBMT and SMT have advantages and

disadvantages Can we make benefits from both methods?

Page 70: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Statistical Post-Editing

SourceText RBMT RBMT

Result SPE SPEResult

A Statistical Post-Editing (SPE) system is a monolingual SMT system which takes the result of a RBMT system as input and generate a improved target output.

Page 71: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Statistical Post Edit: Training

Source

Target

RBMT RBMTTarget

Target

SPETraining SPE

Page 72: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Statistical Post Edit: Training

RBMT usually generates a better word order while SMT can make better lexical selection.

RBMT+SPE outperforms the original RBMT and SMT systems.

Page 73: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Typical Hybrid MT Approaches

Selective MT Pipelined MTStatistical Post-Editing for RBMTRule-based Pre-reordering for SMT

Mixture MT

Page 74: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Rule-based Pre-reordering for SMT

Elia Yuste, Manuel Herranz, Alexandra Helle and Hirokazu Suzuki, Go Hybrid: Pangeanic's and Toshiba's First Steps Towards ENJP MT Hybridization, AAMT Journal, No.50, December 2011 (Part B for this tutorial)

Page 75: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Rule-based Pre-reordering for SMT

Xia, F., & McCord, M. (2004, August). Improving a statistical MT system with automatically learned rewrite patterns. In Proceedings of the 20th international conference on Computational Linguistics (p. 508). Association for Computational Linguistics.

Page 76: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Rule-based Pre-reordering for SMT

A phrase-based SMT (PBSMT) system performs good lexical choices but is not good at long distance reordering without linguistics knowledge

A rule-based word-reordering on the source side is conducted to make the word order of the source text much more similar with the word order in the target side.

Page 77: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Rule-based Pre-reordering for SMT

SourceText

Pre-Reordering

ReorderedSource Text PBSMT Target

Text

Page 78: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

PBSMT: Training

Source

Target

Pre-reordering

ReorderedSource

Target

PBSMTTraining PBSMT

Page 79: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Pre-reordering: Training

The rule for pre-ordering can be automatic acquired from the parallel corpus with automatic word alignment and parsing trees in both side.

Page 80: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Pre-reordering: Training

Parsing the source sentence Parsing the target sentence Align the words and the phrases in

both sides Extract the rewrite rules

Page 81: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Parsing Trees and Alignments

Page 82: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Rule Extraction

Page 83: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Rule Organization and Filtering

Page 84: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Applying Rewrite Rules

Page 85: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Rule-based Pre-reordering for SMT

Page 86: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Typical Hybrid MT Approaches

Selective MT Pipelined MTMixture MTStatistical Parsing in RBMTRule-based Named Entity Translation in SMTHuman-Acquired Rules in SMTSMT Decoding with TM Phrases

Page 87: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Statistical Parsing in RBMT

Statistical parsing outperforms rule-based parsing if we have large scale treebank.

It is reasonable to use statistical algorithm in the parsing component in a RBMT system.

Page 88: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Rule-based Named Entity Translation in SMT

Ney, H. (2013). Statistical MT Systems Revisited: How much Hybridity do they have? Proceedings of the Second Workshop on Hybrid Approaches to Translation, page 7, Sofia, Bulgaria, August 8, 2013.

Page 89: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Numerical Expression Translation

3501749

3,501,749

350,1749

3 million 501 thousand and 749

350 wan 1749

English:

Chinese:

Page 90: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Human-Acquired Rules in SMT

Li, X., Lü, Y., Meng, Y., Liu, Q., & Yu, H. Feedback Selecting of Manually Acquired Rules Using Automatic Evaluation. Proceedings of the 4th Workshop on Patent Translation, pages 52-59, MT Summit XIII, Xiamen, China, September 2011

Page 91: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Human-Acquired Rules in SMT

These rules are used in the decoding process together with the Hierarchical Phrases in a SMT system

Page 92: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

SMT Decoding with TM Phrases

Philipp Koehn and Jean Senellart. 2010. Convergence of translation memory and statistical machine translation. In AMTA Workshop on MT Research and the Translation Industry, pages 21–31.

Wang, K., Zong, C., & Su, K. Y. Integrating Translation Memory into Phrase-Based Machine Translation during Decoding. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 11–21, Sofia, Bulgaria, August 4-9 2013

Page 93: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

SMT Decoding with TM Phrases

Yanjun Ma, Yifan He, Andy Way and Josef van Genabith. 2011. Consistent translation using discriminative learning: a translation memory-inspired approach. In Proceedings of the 49th Annual Meeting of the Association for Computational Lingui stics, pages 1239–1248, Portland, Oregon.

Yifan He, Yanjun Ma, Andy Way and Josef van Genabith. 2011. Rich linguistic features for translation memory-inspired consistent translation. In Proceedings of the Thirteenth Machine Translation Summit, pages 456–463.

Page 94: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

SMT Decoding with TM Phrases

Extract TM phrases from similar sentences in the translation memory and use them in the decoding process in the runtime.

Page 95: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Outline

Why Hybrid MT? An overview of Hybrid MT Typical Hybrid MT Approaches Conclusion

Page 96: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Conclusion

Different MT approaches have advantages and disadvantages, which are usually complementary.

Hybrid MT can take benefit from different MT approaches

Three categories of Hybrid MT is introduced: Selective, Pipelined and Mixture.

Actually almost all the real MT systems are hybrid system.

Page 97: 8. Qun Liu (DCU) Hybrid Solutions for Translation

Winter School 2013, Birmingham

Thank you!Q&A