Guiding Neural Machine Translation with Retrieved Translation Pieces
Opened this issue · 0 comments
kweonwooj commented
Abstract
- propose effective method to incorporate out-of-the-box sentence pairs during NMT decoding process
- use a search engine to retrieve similar sentence pairs
- collect n-gram translation pieces from target side where similarity and alignment score is high
- reward translation pieces during NMT decoding process
- +6.0 BLEU improvement in narrow domain translation task
- effective algorithm design enables accuracy, speed and simplicity of implementation
Details
- Problem
- NMT is weak at translating low-frequency words or phrases
- Retrieval-based Model
- an active research area where NMT retrieves sentence pairs from training corpus during translation
- it augments parametric NMT model with a non-parametric translation memory that allows for increased capacity
- Two main approaches
- Li et al 2016 and Farajian et al 2017 use the retrieved sentence pairs to fine tune the parameters of the NMT model
- Gu et al 2017 uses the retrieved sentence pairs as additional inputs to the NMT decoding
- Contribution
- existing methods perform well, but add significant complexity and computational/memory cost to the decoding process
- propose a simple and efficient method that collects n-gram in the retrieved target sentences (
translation pieces
), calculate a pseudo-probability to weight the translation pieces and reward NMT to output translation pieces during beam search decoding process
Guiding NMT with Translation Pieces
- use Lucene search engine to retrieve
M
source sentences that have n-gram similarity - among all n-grams in retrieved target sentences, collect translation pieces and score them according to the similarity between input sentence and retrieved source sentence:
- in beam search decoding process, translation pieces are given rewards
- reward process is implemented efficiently such that it does not traverse over all target vocabilary
V
, but only traverse target words that belong to translation pieces
Experiments
- corpus : JRC-Acquis corpus. 670k sentences with narrow domain
- result : +6.0 BLEU score over baseline NMT
Ablation Experiments
-
Effect of look-up corpus
- similarity between test set and look-up corpus is an important factor in performance of Guided NMT
- in WMT17 EnDe News Translation task, this method does not achieve significant improvements over the baseline due to difference in train and test data distribution, as shown in Table 8 where WMT's similarity distribution is focused on 0.2~0.4
-
Infrequent n-grams
-
vs Search Engine Guided NMT by Gu et al 2017
Personal Thoughts
- well written paper, well experimented, in-depth analysis
Algorithm 2
is an efficient method to reward/punish n-gram outputs in beam search- consideration on practical implementation was impressive
- hope infrequent n-grams can be dealt well for general purpose translation task (WMT News task)
Link : https://arxiv.org/pdf/1804.02559v1.pdf
Authors : Zhang et al. 2018