WMT的英德翻译

1. The University of Cambridge’s Machine Translation Systems for WMT18

1. basic Architecture

Combine the three most commonly used architectures: recurrent, convolutional, and self-attention-based models like the Transformer

2. system combination

If we want to combine q models , we first divide the models into two groups by selecting a p with 1 p q.

Then, we refer to the first group as full posterior scores and the second group as MBR-based scores.

Full-posterior models scores compute as follows：

在这里插入图片描述

Combined scores compute as follows：

在这里插入图片描述

3. Data

1. language detection (Nakatani, 2010) on all available monolingual and parallel data

2. additionally filtered on ParaCrawl

• No words contain more than 40 characters.
• Sentences must not contain HTML tags.
• The minimum sentence length is 4 words.
• The character ratio between source and targetmust not exceed 1:3 or 3:1
• Source and target sentences must be equal af-ter stripping out non-numerical characters.
• Sentences must end with punctuation marks.

---

2. NTT’s Neural Machine Translation Systems for WMT 2018

1. basic Architecture

Transformer Big

2. Data

• Noisy Data Filtering

1. use language model (such as KenLM) to evaluate a sentences naturalness
2. use a word alignment model (such as fast_align) to check whether the sentence pair has the same meaning

• Synthetic Corpus

3. translating monolingual sentences with Transformer -> seudo-parallel corpora
4. Back-translate & evaluate -> selected the high-scoring sentence pair

• Right-to-Left Re-ranking

5. R2L model re-ranks an n-best hypothesis generated by the Left-to-Right (L2R) model (n=10)

---

3. Microsoft’s Submission to the WMT2018 News Translation Task:How I Learned to Stop Worrying and Love the Data

1. basic Architecture

Transformer Big + Ensemble-decoding + R2L Reranking

2. Data

• Dual conditional cross-entropy filtering

  For a sentence pair(x, y), cross-entropy compute as follows:

  where A and B are translation models trained on the same data but in inverse directions.(We setting and )

  is the probability distribution for a model M

• Data weighting

  sentence instance weighting is a feature available in Marian(Junczys-Dowmunt et al., 2018) .

  sentence score = Data weighting * cross-entropy -> sort and select by sentence score