Cross-Lingual Knowledge Projection and Knowledge Enhancement for Zero-Shot Question Answering in Low-Resource Languages

Ralethe, Sello and Buys, Jan (2025) Cross-Lingual Knowledge Projection and Knowledge Enhancement for Zero-Shot Question Answering in Low-Resource Languages, Proceedings of International Conference on Computational Linguistics (COLING 2025), 19-24 January 2025, bu Dhabi, UAE.

Text (camera-ready version of the conference paper) COLING_2025_Proceedings_LeNS_Align.pdf - Accepted Version Download (264kB)

Abstract

Cross-lingual knowledge projection and knowledge-enhanced language models aim to overcome the limitations of incomplete knowledge bases (KBs) and small-sized corpora in low-resource languages (LRLs). We introduce LeNS-Align, a technique that improves cross-lingual KB triple projection by combining lexical alignment, named-entity recognition, and semantic alignment. We apply LeNS-Align to project KB triples from English to four low-resource South African languages, creating more comprehensive KBs. To enhance question answering capabilities in these languages, we augment multilingual language models with Graph Neural Networks that embed the projected KB knowledge. Evaluations on three translated test sets show that our approach improves zero-shot question answering accuracy by up to 17\% compared to baselines without KB access. The results highlight how our integrated approach expands knowledge coverage and question answering capabilities in low-resource languages, addressing the challenge of scarce native KBs. This work contributes to bridging the knowledge gap for low-resource languages and demonstrates a method for enhancing NLP capabilities in resource-constrained settings.

Item Type:	Conference paper
Subjects:	Computing methodologies > Artificial intelligence > Natural language processing Computing methodologies > Artificial intelligence > Natural language processing > Language resources
Date Deposited:	10 Dec 2024 07:27
Last Modified:	10 Dec 2024 07:27
URI:	https://pubs.cs.uct.ac.za/id/eprint/1709

Actions (login required)

View Item