Mattia Antonino Di Gangi

Also published as: Mattia Antonino Di Gangi


pdf bib
Neural Speech Translation: From Neural Machine Translation to Direct Speech Translation
Mattia Antonino Di Gangi
Proceedings of the 23rd Annual Conference of the European Association for Machine Translation


pdf bib
Enhancing Transformer for End-to-end Speech-to-Text Translation
Mattia Antonino Di Gangi | Matteo Negri | Roldano Cattoni | Roberto Dessi | Marco Turchi
Proceedings of Machine Translation Summit XVII: Research Track


pdf bib
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018
Mattia Antonino Di Gangi | Roberto Dessì | Roldano Cattoni | Matteo Negri | Marco Turchi
Proceedings of the 15th International Conference on Spoken Language Translation

This paper describes FBK’s submission to the end-to-end English-German speech translation task at IWSLT 2018. Our system relies on a state-of-the-art model based on LSTMs and CNNs, where the CNNs are used to reduce the temporal dimension of the audio input, which is in general much higher than machine translation input. Our model was trained only on the audio-to-text parallel data released for the task, and fine-tuned on cleaned subsets of the original training corpus. The addition of weight normalization and label smoothing improved the baseline system by 1.0 BLEU point on our validation set. The final submission also featured checkpoint averaging within a training run and ensemble decoding of models trained during multiple runs. On test data, our best single model obtained a BLEU score of 9.7, while the ensemble obtained a BLEU score of 10.24.


pdf bib
Monolingual Embeddings for Low Resourced Neural Machine Translation
Mattia Antonino Di Gangi | Marcello Federico
Proceedings of the 14th International Conference on Spoken Language Translation

Neural machine translation (NMT) is the state of the art for machine translation, and it shows the best performance when there is a considerable amount of data available. When only little data exist for a language pair, the model cannot produce good representations for words, particularly for rare words. One common solution consists in reducing data sparsity by segmenting words into sub-words, in order to allow rare words to have shared representations with other words. Taking a different approach, in this paper we present a method to feed an NMT network with word embeddings trained on monolingual data, which are combined with the task-specific embeddings learned at training time. This method can leverage an embedding matrix with a huge number of words, which can therefore extend the word-level vocabulary. Our experiments on two language pairs show good results for the typical low-resourced data scenario (IWSLT in-domain dataset). Our consistent improvements over the baselines represent a positive proof about the possibility to leverage models pre-trained on monolingual data in NMT.

pdf bib
FBK’s Participation to the English-to-German News Translation Task of WMT 2017
Mattia Antonino Di Gangi | Nicola Bertoldi | Marcello Federico
Proceedings of the Second Conference on Machine Translation