# mT5-small-sum-de-en-v1

This is a bilingual summarization model for English and German. It is based on the multilingual T5 model google/mt5-small.

This model is provided by the One Conversation team of Deutsche Telekom AG.

## Training

The training was conducted with the following hyperparameters:

• source_prefix: "summarize: "
• batch size: 3
• max_source_length: 800
• max_target_length: 96
• warmup_ratio: 0.3
• number of train epochs: 10
• learning rate: 5e-5

## Datasets and Preprocessing

The datasets were preprocessed as follows:

The summary was tokenized with the google/mt5-small tokenizer. Then only the records with no more than 94 summary tokens were selected.

The MLSUM dataset has a special characteristic. In the text, the summary is often included completely as one or more sentences. These have been removed from the texts. The reason is that we do not want to train a model that ultimately extracts only sentences as a summary.

This model is trained on the following datasets:

CNN Daily - Train en 218,223 The license is unclear. The data comes from CNN and Daily Mail. We assume that it may only be used for research purposes and not commercially.
Extreme Summarization (XSum) - Train en 204,005 The license is unclear. The data comes from BBC. We assume that it may only be used for research purposes and not commercially.
wiki_lingua English en 130,331 Creative Commons CC BY-NC-SA 3.0 License
wiki_lingua German de 48,390 Creative Commons CC BY-NC-SA 3.0 License
MLSUM German - Train de 218,043 Usage of dataset is restricted to non-commercial research purposes only. Copyright belongs to the original copyright holders (see here).
SwissText 2019 - Train de 84,564 The license is unclear. The data was published in the German Text Summarization Challenge. We assume that they may be used for research purposes and not commercially.
Language Size
German 350,997
English 552,559
Total 903,556

## Evaluation on MLSUM German Test Set (no beams)

Model rouge1 rouge2 rougeL rougeLsum
ml6team/mt5-small-german-finetune-mlsum 18.3607 5.3604 14.5456 16.1946
deutsche-telekom/mT5-small-sum-de-en-01 (this) 21.7336 7.2614 17.1323 19.3977

## Evaluation on CNN Daily English Test Set (no beams)

Model rouge1 rouge2 rougeL rougeLsum
sshleifer/distilbart-xsum-12-6 26.7664 8.8243 18.3703 23.2614
mrm8488/t5-base-finetuned-summarize-news 37.576 14.7389 24.0254 34.4634
deutsche-telekom/mT5-small-sum-de-en-01 (this) 37.6339 16.5317 27.1418 34.9951

## Evaluation on Extreme Summarization (XSum) English Test Set (no beams)

Model rouge1 rouge2 rougeL rougeLsum
mrm8488/t5-base-finetuned-summarize-news 18.6204 3.535 12.3997 15.2111
deutsche-telekom/mT5-small-sum-de-en-01 (this) 32.3416 10.6191 25.3799 25.3908
sshleifer/distilbart-xsum-12-6 44.2553 ♣ 21.4289 ♣ 36.2639 ♣ 36.2696 ♣

♣: These values seem to be unusually high. It could be that the test set was used in the training data.