%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:13:12 PM

@INPROCEEDINGS{Parida_EMNLP2019_2019,
         author = {Parida, Shantipriya and Motlicek, Petr},
       projects = {Innosuisse-SM2, Idiap},
          month = nov,
          title = {Abstract Text Summarization: A Low Resource Challenge},
      booktitle = {In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2019)},
           year = {2019},
          pages = {5},
      publisher = {Association for Computational Linguistics (ACL)},
       location = {HongKong, China},
       abstract = {Text summarization is considered as a challenging task in the NLP community. The availability of datasets for the task of multilingual text summarization is rare, and such datasets are difficult to construct. In this work, we
build an abstract text summarizer for the German language text using the state-of-the-art “Transformer” model. We propose an iterative data augmentation approach which uses synthetic data along with the real summarization data for the German language. To generate synthetic data, the Common Crawl (German) dataset is exploited, which covers different domains. The synthetic data is effective for the low resource condition and is particularly helpful for our multilingual scenario where availability of summarizing data is still
a challenging issue. The data are also useful in deep learning scenarios where the neural models require a large amount of training data for utilization of its capacity. The obtained summarization performance is measured in terms of ROUGE and BLEU score. We achieve an absolute improvement of +1.5 and +16.0 in
ROUGE1 F1 (R1 F1) on the development and test sets, respectively, compared to the system which does not rely on data augmentation.},
            pdf = {https://publications.idiap.ch/attachments/papers/2019/Parida_EMNLP2019_2019.pdf}
}