Typological Distance and Accuracy Degradation in Zero-Shot Cross-Lingual Transfer
Description
Named Entity Recognition (NER) and Part-of-Speech (POS) tagging are critical tasks for Natural Language Processing (NLP), yet their availability for low-resource languages (LRLs) like Bodo remains limited. This article presents a comparative empirical study investigating the effectiveness of Google's Gemini 2.0 Flash Thinking Experiment model for zero-shot cross-lingual transfer of POS and NER tagging to Bodo. We explore two distinct methodologies: (1) direct translation of English sentences to Bodo followed by tag transfer, and (2) prompt-based tag transfer on parallel English-Bodo sentence p
Research goal: How does the typological distance between English and target languages correlate with accuracy degradation in zero-shot cross-lingual transfer after intermediate-task training on XTREME NER and POS tagging tasks?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.
Notes
Files
paper.pdf
Files
(78.2 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:6cd4f112458c1bf5cfb6798c730fbaf5
|
78.2 kB | Preview Download |