Syntax-based Machine Translation using Multi Bottom-up Tree - PowerPoint PPT Presentation

Syntax-based Machine Translation using Multi Bottom-up Tree Transducers Andreas Maletti Fabienne Braune, Daniel Quernheim, Nina Seemann Institute for Natural Language Processing Universität Stuttgart, Germany maletti@ims.uni-stuttgart.de Uppsala — November 8, 2012 Syntax-based MT using MBOT A. Maletti 1 ·

Overview Motivation 1 Extended Multi Bottom-up Tree Transducers 2 The Theory 3 The Application 4 Syntax-based MT using MBOT A. Maletti 2 ·

Motivation Machine translation Translation Input: Official forecasts predicted just 3 percent, Bloomberg said. Reference: Offizielle Prognosen sind von nur 3 Prozent ausgegangen, meldete Bloomberg. [official] [forecasts] [are] [of] [only] [3 percent] [assumed] [reported] [Bloomberg] Our MBOT translator (untuned): offiziellen prognosen vorausgesagt nur 3 % bloomberg habe. [official] [forecasts] [*predicted] [only] [3 %] [Bloomberg] [*has] Google Translate ( translate.google.com ): Offizielle Prognosen vorausgesagt nur 3 Prozent, sagte Bloomberg. [official] [forecasts] [*predicted] [only] [3 percent] [said] [Bloomberg] Syntax-based MT using MBOT A. Maletti 3 ·

Motivation Machine translation Translation Input: The ECB wants to hold inflation to under two percent, or somewhere in that vicinity. Reference: Die EZB ist bestrebt, die Inflationsrate unter zwei Prozent, [the] [ECB] [is] [desire] [the] [inflation rate] [below] [two percent] oder zumindest knapp an der Zwei-Prozent-Marke zu halten. [or] [at least] [close] [at] [the] [two percent mark] [to keep] Google Translate ( translate.google.com ): Die EZB will die Inflation zu halten unter zwei Prozent, [the] [ECB] [wants] [the] [inflation] [*to keep] [below] [two percent] oder irgendwo in der Nähe. [or] [somewhere] [in] [the] [vicinity] Syntax-based MT using MBOT A. Maletti 4 ·

Motivation Syntax-based machine translation Remark There is no universally accepted definition Syntax-based systems Language Machine model Input − → Parser − → translation − → − → Output system Syntax-based MT using MBOT A. Maletti 5 ·

Motivation What do we have? Input Parallel text (English and German) E URO P ARL Parsers B IT P AR , C HARNIAK , B ERKELEY Example “We must bear in mind the Community as a whole.” “Wir müssen uns davor hüten, alles vergemeinschaften zu wollen.” Syntax-based MT using MBOT A. Maletti 6 ·

Motivation What do we have? Input Parallel text (English and German) E URO P ARL Parsers B IT P AR , C HARNIAK , B ERKELEY Example “We must bear in mind the Community as a whole.” “Wir müssen uns davor hüten, alles vergemeinschaften zu wollen.” E URO P ARL German-English parallel data: 1 , 920 , 209 parallel sentences 44 , 548 , 491 words in German 47 , 818 , 827 words in English Syntax-based MT using MBOT A. Maletti 6 ·

Motivation First step: Word Alignment Alignments by G IZA ++ [O CH , N EY ’03]: We must bear in mind the Community as a whole . Wir müssen uns davor hüten , alles vergemeinschaften zu wollen . Syntax-based MT using MBOT A. Maletti 7 ·

Motivation First step: Word Alignment Alignments by G IZA ++ [O CH , N EY ’03]: We must bear in mind the Community as a whole . Wir müssen uns davor hüten , alles vergemeinschaften zu wollen . We can help countries catch up , but not by putting their neighbours on hold . Wir können Ländern beim Aufholen helfen , aber nicht , indem wir ihre Nachbarn in den Wartesaal schicken . Syntax-based MT using MBOT A. Maletti 7 ·

Motivation Second step: Parsing C HARNIAK parser: TOP [C HARNIAK , J OHNSON ’05] S . NP VP . PRP MD VP We must VB PP NP bear IN NP NP PP in NN DT NN IN NP Community as mind the DT NN a whole BitPar parser: TOP [S CHMID ’06] $. S-TOP . NP-SB/Pl VMFIN-HD-Pl VP-OC/inf PPER-HD-Nom.Pl müssen NP-DA PP-OP/V VVINF-HD $, VP-OC/zu , Wir PPER-HD-Dat.Pl PROAV-PH hüten VP-OC/inf VZ-HD uns davor NP-OA VVINF-HD PTKZU-PM VMINF-HD PIS-HD-Acc.Sg.Neut vergemeinschaften zu wollen alles Syntax-based MT using MBOT A. Maletti 8 ·

Motivation Second step: Parsing C HARNIAK parser: TOP S , . S CC FRAG , . NP VP but RB PP PRP MD VP not IN S We can VB S by VP help NP VP VBG NP PP putting NNS VB PRT PRP$ NNS IN NP countries catch RP their neighbours on NN up hold BitPar parser: TOP CS-TOP $. ... . S-TOP $, , ... NP-SB/Pl VMFIN-HD-Pl VP-OC/inf PPER-HD-Nom.Pl können NP-DA PP-MO/V VVINF-HD APPRART-AC-Dat.Sg.Neut NN-HD-Dat.Sg.Neut Wir NN-HD-Dat.Pl.Neut helfen Ländern beim Aufholen Syntax-based MT using MBOT A. Maletti 9 ·

Motivation Equalizing examples Input Yugoslav President Voislav signed for Serbia. � �� Transliteration: w twlY AltwqyE En SrbyA Alr}ys AlywgwslAfy fwyslAf. And then the matter was decided, and everything was put in place. � �� Transliteration: f kAn An tm AlHsm w wDEt Al > mwr fy nSAb hA. Below are the male and female winners in the different categories. �� Transliteration: w hnA Al > wA}l w Al > wlyAt fy mxtlf Alf}At. Syntax-based MT using MBOT A. Maletti 10 ·

Motivation Equalizing examples Alignment Yugoslav President Voislav signed for Serbia w twlY AltwqyE En SrbyA Alr}ys AlywgwslAfy fwyslAf Syntax-based MT using MBOT A. Maletti 11 ·

Motivation Rule extraction S NP-SBJ VP NML NNP VBD PP signed JJ NNP Voislav IN NP Yugoslav President for NNP Serbia SrbyA AltwqyE Alr}ys AlywgwslAfy fwyslAf En NN-PROP DET-NN PREP NP DET-NN DET-ADJ NN-PROP twlY NP PP NP NP w PV NP-OBJ NP-SBJ CONJ VP S Syntax-based MT using MBOT A. Maletti 12 ·

Syntax-based Machine Translation using Multi Bottom-up Tree - PowerPoint PPT Presentation

Syntax-based Machine Translation using Multi Bottom-up Tree Transducers Andreas Maletti Fabienne Braune, Daniel Quernheim, Nina Seemann Institute for Natural Language Processing Universitt Stuttgart, Germany maletti@ims.uni-stuttgart.de

Learning Non-Isomorphic Tree Mappings for Machine Translation Syntax-Based Machine Translation

Statistical Machine Translation Outline p Why Syntax? Lecture 5 Yamada and Knight:

Automatic Category Label Coarsening for Syntax-Based Machine Translation Greg Hanneman and Alon

Syntax-based Transla0on Part 2: Synchronous Grammars Machine Translation

Improving Trees and Alignments for Syntax- Based Machine Translation Kevin Knight

Parser Self-Training for Syntax-Based Machine Translation Nara Institute of Science and

Lexical Syntax for Dependency-based Language Models Statistical Machine Translation Incremental

Empirical Methods in Natural Language Processing Lecture 18 Machine translation (V): Syntax-Based

Syntax-Based Decoding 2 Philipp Koehn 14 November 2017 Philipp Koehn Machine Translation:

Syntax-Based Decoding Philipp Koehn 9 November 2017 Philipp Koehn Machine Translation:

Chapter 11 Tree-based models Statistical Machine Translation Tree-Based Models Traditional

Vector Space Models for Phrase-based Machine Translation Tamer Alkhouli, Andreas Guta, and

A General-Purpose Rule Extractor for SCFG-Based Machine Translation Greg Hanneman , Michelle

Syntax and Semantics Philipp Koehn 3 November 2020 Philipp Koehn Machine Translation: Syntax

Syntax-based Transla0on Part 1: Re-ordering for

Discontinuous Statistical Machine Translation with Target-Side Dependency Syntax Nina Seemann

Adaptive Multi-pass Decoder for Neural Machine Translation EMNLP 2018

Guy Dar Machine Translation Seminar Tel Aviv University 2014 } Pr Problems: lems: Poor

CSE 517 Natural Language Processing Winter 2013 Syntax-Based Translation Luke Zettlemoyer

Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder Huadong Chen ! ,

Semi-supervised Learning for Neural Machine Translation Yong Cheng joint work with Wei Xu,

Chapter 4 Word-based models Statistical Machine Translation Lexical Translation How to

Statistical Machine Translation Nadir Durrani 21-November-2014 Machine Translation

Neural Machine Translation Gongbo Tang 8 October 2018 Outline Neural Machine Translation 1