@article{severEvaluating2020,
    title = {Evaluating cross-lingual textual similarity on dictionary alignment problem},
    copyright = {All rights reserved},
    issn = {1574-0218},
    url = {https://doi.org/10.1007/s10579-020-09498-1},
    doi = {10.1007/s10579-020-09498-1},
    abstract = {Bilingual or even polylingual word embeddings created many possibilities for tasks involving multiple languages. While some tasks like cross-lingual information retrieval aim to satisfy users’ multilingual information needs, some enable transferring valuable information from resource-rich languages to resource-poor ones. In any case, it is important to build and evaluate methods that operate in a cross-lingual setting. In this paper, Wordnet definitions in 7 different languages are used to create a semantic textual similarity testbed to evaluate cross-lingual textual semantic similarity methods. A document alignment task is created to be used between Wordnet glosses of synsets in 7 different languages. Unsupervised textual similarity methods—Wasserstein distance, Sinkhorn distance and cosine similarity—are compared with a supervised Siamese deep learning model. The task is modeled both as a retrieval task and an alignment task to investigate the hubness of the semantic similarity functions. Our findings indicate that considering the problem as a retrieval and alignment problem has a detrimental effect on the results. Furthermore, we show that cross-lingual textual semantic similarity can be used as an automated Wordnet construction method.},
    language = {en},
    urldate = {2020-07-01},
    journal = {Language Resources and Evaluation},
    author = {Sever, Yiğit and Ercan, Gönenç},
    month = jun,
    year = {2020},
}