OwenZhu's Blog

WSTA 22 - MACHINE TRANSLATION

2018/05/29 Share

WORD-BASED AND PHRASE-BASED MT

Word based model: overly simplistic formulation — only used for _alignment_, not actual _translation_.

Phrase based MT: treats N-grams as translation units, referred to as ‘phrases’.

  • Phrase-pairs memorise:

    • common translation fragments

    • common reordering patterns

  • FINDING & SCORING PHRASE PAIRS

    • Extract” phrase pairs; then produce ‘probabilities’ by count
  • The phrase-table:
    • (massive list with many millions of pairs )
  • Decoding: segmentation of F into phrases; re-ordering of their translations to produce E
  • score function is product of the:

    • Translation “probability” $P(F|E)$, split into phrase-pairs
    • Languate model probability $P(E)$
    • distortion cost $d(start_i, end_{i-1})$, measuring amount of reordering between adjacent phrase-pairs
  • Search problem: find optimal translation $E^*$

TRANSLATION PROCESS:

  1. segment
  2. translate
  3. Reordering (Dynamic Programming solution)
  • PHRASE-BASED DECODING

NEURAL MACHINE TRANSLATION

Phrase-based approach is rather complicated

We want to know what is the probability of a sequence $y|x$?

sequence2sequence model

  • encoder-decoder models

    • _Encoder_: represents the source sentence as a vector or matrix of real values.
    • _Decoder_: predicts the word sequence in the target.
  • RNN attention model

Evaluation

Fluency; adequacy

BLEU: measures closeness of translation to one or more references

weighted average of 1,2,3&4-gram precisions and a brevity penalty to hedge against short outputs

CATALOG
  1. 1. WORD-BASED AND PHRASE-BASED MT
  2. 2. NEURAL MACHINE TRANSLATION
  3. 3. Evaluation