@inproceedings{L16-1721,
 abstract = {This paper discusses the role that statistical machine translation (SMT) can play in the development of cross-border EU e-commerce,by highlighting extant obstacles and identifying relevant technologies to overcome them. In this sense, it firstly proposes a typology of e-commerce static and dynamic textual genres and it identifies those that may be more successfully targeted by SMT. The specific challenges concerning the automatic translation of user-generated content are discussed in detail. Secondly, the paper highlights the risk of data sparsity inherent to e-commerce and it explores the state-of-the-art strategies to achieve domain adequacy via adaptation. Thirdly, it proposes a robust workflow for the development of SMT systems adapted to the e-commerce domain by relying on inexpensive methods. Given the scarcity of user-generated language corpora for most language pairs, the paper proposes to obtain monolingual target-language data to train language models and aligned parallel corpora to tune and evaluate MT systems by means of crowdsourcing.
},
 address = {Portorož, Slovenia},
 author = {Meritxell Fernández Barrera and Vladimir Popescu and Antonio Toral and Federico Gaspari and Khalid Choukri},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {4550--4556},
 publisher = {European Language Resources Association (ELRA)},
 title = {Enhancing Cross-border EU E-commerce through Machine Translation: Needed Language Resources, Challenges and Opportunities},
 url = {https://www.aclweb.org/anthology/L16-1721},
 year = {2016}
}