Abstract
Accurate alignment between languages is fundamental for improving cross-lingual pre-trained language models (XLMs). Motivated by the natural phenomenon of code-switching (CS) in multilingual speakers, CS has been used as an effective data augmentation method that offers language alignment at word- or phrase-level, in contrast to sentence-level via parallel instances. Existing approaches either use dictionaries or parallel sentences with word-alignment to generate CS data by randomly switching words in a sentence. However, such methods can be suboptimal as dictionaries disregard semantics, and syntax might become invalid after random word switching. In this work, we propose EntityCS, a method that focuses on Entity-level Code-Switching to capture fine-grained cross-lingual semantics without corrupting syntax. We use Wikidata and the English Wikipedia to construct an entity-centric CS corpus by switching entities to their counterparts in other languages. We further propose entity-oriented masking strategies during intermediate model training on the EntityCS corpus for improving entity prediction. Evaluation of the trained models on four entity-centric downstream tasks shows consistent improvements over the baseline with a notable increase of 10% in Fact Retrieval. We release the corpus and models to assist research on code-switching and enriching XLMs with external knowledge.- Anthology ID:
- 2022.findings-emnlp.499
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6698–6714
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.499
- DOI:
- 10.18653/v1/2022.findings-emnlp.499
- Cite (ACL):
- Chenxi Whitehouse, Fenia Christopoulou, and Ignacio Iacobacci. 2022. EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6698–6714, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching (Whitehouse et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2022.findings-emnlp.499.pdf