Parsing in the absence of related languages: Evaluating low-resource dependency parsers on Tagalog
Year: 2020
Type: other
Abstract: Cross-lingual and multilingual methods have been widely suggested as options for dependency parsing of low-resource languages; however, these typically require the use of annotated data in related high-resource languages. In this paper, we evaluate the performance of these methods versus monolingual parsing of Tagalog, an Austronesian language which shares little typological similarity with any existing high-resource languages. We show that a monolingual model developed on minimal target language data consistently outperforms all cross-lingual and multilingual models when no closely-related sources exist for a low-resource language.
Source: Underline Science Inc.
DOI: 10.48448/0jhv-jk62
Authors: The 28th International Conference on Computational Linguistics 2020, Aquino, Angelina, de Leon, Franz
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6948378146