A Comparison of Unsupervised Methods for Ad hoc Cross-Lingual Document Retrieval

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

Abstrakti

We address the problem of linking related documents across languages in a multilingual collection. We evaluate three diverse unsupervised methods to represent and compare documents: (1) multilingual topic model; (2) cross-lingual document embeddings; and (3) Wasserstein distance. We test the performance of these methods in retrieving news articles in Swedish that are known to be related to a given Finnish article. The results show that ensembles of the methods outperform the stand-alone methods, suggesting that they capture complementary characteristics of the documents.
Alkuperäiskielienglanti
OtsikkoProceedings of the LREC 2020 Workshop on Cross-Language Search and Summarization of Text and Speech
Julkaisupäivä16 toukokuuta 2020
TilaJulkaistu - 16 toukokuuta 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa

Siteeraa tätä

Zosa, E., Pivovarova, L., & Granroth-Wilding, M. (2020). A Comparison of Unsupervised Methods for Ad hoc Cross-Lingual Document Retrieval. teoksessa Proceedings of the LREC 2020 Workshop on Cross-Language Search and Summarization of Text and Speech