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 M_1,...,M_q, we first divide the models into two groups by selecting a p with 1 \le p \le q.

Then, we refer to the first group M_1,...,M_p as full posterior scores and the second group M_p,...,M_q 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
  1. translating monolingual sentences with Transformer -> seudo-parallel corpora
  2. Back-translate & evaluate -> selected the high-scoring sentence pair
  • Right-to-Left Re-ranking
  1. 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:

    adq(x, y) = exp(-(|H_A(y|x) - H_B(y|x)|) + \frac{1}{2} (H_A(y|x) + H_B(y|x)))

    where A and B are translation models trained on the same data but in inverse directions.(We setting A = W_{de->en} and B = W_{en->de})

    H_M(y|x) = - \frac{1}{|y|} \sum\limits_{t=1}^{|y|} log P_M(y_t|y<t, x)

    P_M(x|y) 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

©著作权归作者所有,转载或内容合作请联系作者
  • 序言:七十年代末,一起剥皮案震惊了整个滨河市,随后出现的几起案子,更是在滨河造成了极大的恐慌,老刑警刘岩,带你破解...
    沈念sama阅读 203,271评论 5 476
  • 序言:滨河连续发生了三起死亡事件,死亡现场离奇诡异,居然都是意外死亡,警方通过查阅死者的电脑和手机,发现死者居然都...
    沈念sama阅读 85,275评论 2 380
  • 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
    开封第一讲书人阅读 150,151评论 0 336
  • 文/不坏的土叔 我叫张陵,是天一观的道长。 经常有香客问我,道长,这世上最难降的妖魔是什么? 我笑而不...
    开封第一讲书人阅读 54,550评论 1 273
  • 正文 为了忘掉前任,我火速办了婚礼,结果婚礼上,老公的妹妹穿的比我还像新娘。我一直安慰自己,他们只是感情好,可当我...
    茶点故事阅读 63,553评论 5 365
  • 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
    开封第一讲书人阅读 48,559评论 1 281
  • 那天,我揣着相机与录音,去河边找鬼。 笑死,一个胖子当着我的面吹牛,可吹牛的内容都是我干的。 我是一名探鬼主播,决...
    沈念sama阅读 37,924评论 3 395
  • 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
    开封第一讲书人阅读 36,580评论 0 257
  • 序言:老挝万荣一对情侣失踪,失踪者是张志新(化名)和其女友刘颖,没想到半个月后,有当地人在树林里发现了一具尸体,经...
    沈念sama阅读 40,826评论 1 297
  • 正文 独居荒郊野岭守林人离奇死亡,尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 35,578评论 2 320
  • 正文 我和宋清朗相恋三年,在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 37,661评论 1 329
  • 序言:一个原本活蹦乱跳的男人离奇死亡,死状恐怖,灵堂内的尸体忽然破棺而出,到底是诈尸还是另有隐情,我是刑警宁泽,带...
    沈念sama阅读 33,363评论 4 318
  • 正文 年R本政府宣布,位于F岛的核电站,受9级特大地震影响,放射性物质发生泄漏。R本人自食恶果不足惜,却给世界环境...
    茶点故事阅读 38,940评论 3 307
  • 文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹,春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 29,926评论 0 19
  • 文/苍兰香墨 我抬头看了看天上的太阳。三九已至,却和暖如春,着一层夹袄步出监牢的瞬间,已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 31,156评论 1 259
  • 我被黑心中介骗来泰国打工, 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留,地道东北人。 一个月前我还...
    沈念sama阅读 42,872评论 2 349
  • 正文 我出身青楼,却偏偏与公主长得像,于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子,可洞房花烛夜当晚...
    茶点故事阅读 42,391评论 2 342

推荐阅读更多精彩内容