当你的表亲拥有正确的连接：面向相关数据不平衡语言的无监督双语词典归纳
When your Cousin has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages
AI总结：
针对相关高低资源语言间数据不平衡导致无监督双语词典归纳性能极差的问题，提出仅需在高资源语言掩码模型上推理的新方法，在多种印度低资源语言上验证了有效性并发布词典。
摘要：
现有的大多数无监督双语词典归纳（BLI）方法依赖于高质量的静态或上下文嵌入，这需要两种语言都有大型单语语料库。然而，无监督BLI最有可能在缺乏大型数据集的低资源语言（LRL）中发挥作用。通常，我们希望为LRL构建针对相关高资源语言（HRL）的双语资源，从而导致BLI面临严重的数据不平衡设置。我们首先表明，文献中最先进的BLI方法在严重数据不平衡的语言对中表现出接近零的性能，这表明这些设置需要更鲁棒的技术。然后，我们提出了一种在相关的LRL和HRL之间进行无监督BLI的新方法，该方法仅需在HRL的掩码语言模型上进行推理，并在真正低资源语言Bhojpuri和Magahi（各自单语token少于5M）与Hindi的对比中证明了其有效性。我们进一步在（中等资源）Marathi和Nepali上进行了实验，以比较不同资源范围下的方法表现，并发布了五种低资源印度语言（Bhojpuri、Magahi、Awadhi、Braj和Maithili）针对Hindi的所得词典。
英文摘要：
Most existing approaches for unsupervised bilingual lexicon induction (BLI) depend on good quality static or contextual embeddings requiring large monolingual corpora for both languages. However, unsupervised BLI is most likely to be useful for low-resource languages (LRLs), where large datasets are not available. Often we are interested in building bilingual resources for LRLs against related high-resource languages (HRLs), resulting in severely imbalanced data settings for BLI. We first show that state-of-the-art BLI methods in the literature exhibit near-zero performance for severely data-imbalanced language pairs, indicating that these settings require more robust techniques. We then present a new method for unsupervised BLI between a related LRL and HRL that only requires inference on a masked language model of the HRL, and demonstrate its effectiveness on truly low-resource languages Bhojpuri and Magahi (with <5M monolingual tokens each), against Hindi. We further present experiments on (mid-resource) Marathi and Nepali to compare approach performances by resource range, and release our resulting lexicons for five low-resource Indic languages: Bhojpuri, Magahi, Awadhi, Braj, and Maithili, against Hindi.
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。
