基于多语言同词化图的低资源语言跨语言迁移学习
Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs
AI总结：
本文直接从未标注平行语料库构建多语言同词化图ColexNet和ColexNet+，并训练出高质量多语言嵌入，在多项任务上超越基线，证明了同词化在低资源语言跨语言迁移学习中的有效性。
摘要：
在比较语言学中，同词化指一个词汇形式表达两个或多个不同含义的现象。现有的同词化模式研究依赖于标注词表，限制了其在NLP中的可扩展性和实用性。相反，我们直接从未标注的平行语料库中识别了1,335种语言中超过2,000个概念的同词化模式。随后，我们提出了简单有效的方法来从同词化模式构建多语言图：ColexNet和ColexNet+。ColexNet的节点是概念，边是同词化关系。在ColexNet+中，概念节点还通过中间节点进行连接，每个中间节点代表1,334种语言中某一种语言的一个ngram。我们使用ColexNet+训练$\overrightarrow{\mbox{ColexNet+}}$，这是一种非常适合迁移学习的高质量多语言嵌入。在我们的实验中，我们首先展示了ColexNet在跨语言同词化数据集CLICS上实现了高召回率。然后，我们在往返翻译、句子检索和句子分类任务上评估了$\overrightarrow{\mbox{ColexNet+}}$，结果表明我们的嵌入超越了几个迁移学习基线。这证明了在多语言NLP中使用同词化作为信息源的益处。
英文摘要：
In comparative linguistics, colexification refers to the phenomenon of a lexical form conveying two or more distinct meanings. Existing work on colexification patterns relies on annotated word lists, limiting scalability and usefulness in NLP. In contrast, we identify colexification patterns of more than 2,000 concepts across 1,335 languages directly from an unannotated parallel corpus. We then propose simple and effective methods to build multilingual graphs from the colexification patterns: ColexNet and ColexNet+. ColexNet's nodes are concepts and its edges are colexifications. In ColexNet+, concept nodes are additionally linked through intermediate nodes, each representing an ngram in one of 1,334 languages. We use ColexNet+ to train $\overrightarrow{\mbox{ColexNet+}}$, high-quality multilingual embeddings that are well-suited for transfer learning. In our experiments, we first show that ColexNet achieves high recall on CLICS, a dataset of crosslingual colexifications. We then evaluate $\overrightarrow{\mbox{ColexNet+}}$ on roundtrip translation, sentence retrieval and sentence classification and show that our embeddings surpass several transfer learning baselines. This demonstrates the benefits of using colexification as a source of information in multilingual NLP.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
