OpenNMT-py models

This page lists pretrained models for OpenNMT-py.

• Translation
• Summarization
  • English
  • Chinese
• Dialog

Translation

	English-German - Transformer (download)
Configuration	Base Transformer configuration with standard training options
Data	WMT with shared SentencePiece model
BLEU	newstest2014 = 26.89 newstest2017 = 28.09

	German-English - 2-layer BiLSTM (download)
Configuration	2-layer BiLSTM with hidden size 500 trained for 20 epochs
Data	IWSLT ‘14 DE-EN
BLEU	30.33

Summarization

English

	2-layer LSTM (download)
Configuration	2-layer LSTM with hidden size 500 trained for 20 epochs
Data	Gigaword standard
Gigaword F-Score	R1 = 33.60 R2 = 16.29 RL = 31.45

	2-layer LSTM with copy attention (download)
Configuration	2-layer LSTM with hidden size 500 and copy attention trained for 20 epochs
Data	Gigaword standard
Gigaword F-Score	R1 = 35.51 R2 = 17.35 RL = 33.17

	Transformer (download)
Configuration	See OpenNMT-py summarization example
Data	CNN/Daily Mail

	1-layer BiLSTM (download)
Configuration	See OpenNMT-py summarization example
Data	CNN/Daily Mail
Gigaword F-Score	R1 = 39.12 R2 = 17.35 RL = 36.12

Chinese

	1-layer BiLSTM (download)
Author	playma
Configuration	Preprocessing options: src_vocab_size 8000, tgt_vocab_size 8000, src_seq_length 400, tgt_seq_length 30, src_seq_length_trunc 400, tgt_seq_length_trunc 100. Training options: 1 layer, LSTM 300, WE 500, encoder_type brnn, input feed, AdaGrad, adagrad_accumulator_init 0.1, learning_rate 0.15, 30 epochs
Data	LCSTS
Gigaword F-Score	R1 = 35.67 R2 = 23.06 RL = 33.14

Dialog

	2-layer LSTM (download)
Configuration	2 layers, LSTM 500, WE 500, input feed, dropout 0.2, global_attention mlp, start_decay_at 7, 13 epochs
Data	OpenSubtitles