A language-independent and fully unsupervised approach to lexicon induction and part-of-speech tagging for closely related languages

• Main Authors: Scherrer, Yves, Sagot, Benoît
• Other Authors: LATL-CUI, Laboratoire d'Analyse et de Technologie du Langage (LATL), Université de Genève = University of Geneva (UNIGE)-Université de Genève = University of Geneva (UNIGE), Analyse Linguistique Profonde à Grande Echelle, Large-scale deep linguistic processing (ALPAGE), Inria Paris-Rocquencourt, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université Paris Diderot - Paris 7 (UPD7), European Language Resources Association, ANR-11-IDEX-0005,USPC,Université Sorbonne Paris Cité(2011)
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2014
• Subjects: ACM: J.: Computer Applications/J.5: ARTS AND HUMANITIES/J.5.4: Linguistics; ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE/I.2.7: Natural Language Processing; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; Iceland
• Online Access: https://inria.hal.science/hal-01022298; https://inria.hal.science/hal-01022298/document; https://inria.hal.science/hal-01022298/file/lrec14cll.pdf

International audience In this paper, we describe our generic approach for transferring part-of-speech annotations from a resourced language towards an etymologically closely related non-resourced language, without using any bilingual (i.e., parallel) data. We first induce a translation lexicon from monolingual corpora, based on cognate detection followed by cross-lingual contextual similarity. Second, POS information is transferred from the resourced language along translation pairs to the non-resourced language and used for tagging the corpus. We evaluate our methods on three language families, consisting of five Romance languages, three Germanic languages and five Slavic languages. We obtain tagging accuracies of up to 91.6%.