构建首个阿姆哈拉语抽取式问答基准，解决翻译对齐难题
AmaSQuAD: A Benchmark for Amharic Extractive Question Answering
- 用细调BERT和最长公共子序列方法修复翻译后的问题-答案错位
- 模型在AmaSQuAD上F1提升至57.5%，在AmQA上准确率微增
- 适合低资源语言研究者、跨语言NLP开发者参考
本研究提出一种将抽取式问答数据集翻译至低资源语言的新框架，以创建阿姆哈拉语的AmaSQuAD数据集（SQuAD 2.0的翻译版）。针对翻译后问题与答案的错位及上下文多答案实例问题，采用基于细调BERT模型的嵌入余弦相似度与最长公共子序列（LCS）进行对齐。此外，在合成的AmaSQuAD数据集上对XLM-R模型进行微调。结果表明，模型在AmaSQuAD开发集上的F1分数从36.55%提升至44.41%，50.01%提升至57.5%；在人工标注的AmQA数据集上，F1分数从67.80%升至68.80%，精确匹配率从52.50%升至52.66%。AmaSQuAD数据集已公开。
原文摘要 · Abstract (English)
This research presents a novel framework for translating extractive question-answering datasets into low-resource languages, as demonstrated by the creation of the AmaSQuAD dataset, a translation of SQuAD 2.0 into Amharic. The methodology addresses challenges related to misalignment between translated questions and answers, as well as the presence of multiple answer instances in the translated context. For this purpose, we used cosine similarity utilizing embeddings from a fine-tuned BERT-based model for Amharic and Longest Common Subsequence (LCS). Additionally, we fine-tune the XLM-R model on the AmaSQuAD synthetic dataset for Amharic Question-Answering. The results show an improvement in baseline performance, with the fine-tuned model achieving an increase in the F1 score from 36.55% to 44.41% and 50.01% to 57.5% on the AmaSQuAD development dataset. Moreover, the model demonstrates improvement on the human-curated AmQA dataset, increasing the F1 score from 67.80% to 68.80% and the exact match score from 52.50% to 52.66%.The AmaSQuAD dataset is publicly available Datasets
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。