面向低资源语言的无监督双语词典归纳
Unsupervised Bilingual Lexicon Induction for Low Resource Languages
AI总结：
本文研究了同时使用多种基于结构的无监督双语词典归纳（UBLI）改进技术是否能带来同等收益，通过VecMap框架在多个低资源语言对上实验确定了最佳扩展组合，并发布了相应双语词典。
摘要：
双语词典在各种自然语言处理任务中起着至关重要的作用。然而，许多低资源语言（LRLs）没有这样的词典，并且由于同样的原因，无法从有监督的双语词典归纳（BLI）技术中受益。为了解决这个问题，引入了无监督的BLI（UBLI）技术。这一方向上的一个突出技术是基于结构的UBLI。这是一种迭代方法，其中最初从单语嵌入中学习到的种子词典被迭代地改进。对这一核心思想已有许多改进，但它们都是相互独立地进行实验的。在本文中，我们研究同时使用这些技术是否会带来同等的收益。我们使用常用的基于结构的UBLI框架VecMap的无监督版本，并使用低资源语言对English-Sinhala、English-Tamil和English-Punjabi进行了一系列全面的实验。这些实验帮助我们确定了扩展的最佳组合。我们还发布了English-Sinhala和English-Punjabi的双语词典。
英文摘要：
Bilingual lexicons play a crucial role in various Natural Language Processing tasks. However, many low-resource languages (LRLs) do not have such lexicons, and due to the same reason, cannot benefit from the supervised Bilingual Lexicon Induction (BLI) techniques. To address this, unsupervised BLI (UBLI) techniques were introduced. A prominent technique in this line is structure-based UBLI. It is an iterative method, where a seed lexicon, which is initially learned from monolingual embeddings is iteratively improved. There have been numerous improvements to this core idea, however they have been experimented with independently of each other. In this paper, we investigate whether using these techniques simultaneously would lead to equal gains. We use the unsupervised version of VecMap, a commonly used structure-based UBLI framework, and carry out a comprehensive set of experiments using the LRL pairs, English-Sinhala, English-Tamil, and English-Punjabi. These experiments helped us to identify the best combination of the extensions. We also release bilingual dictionaries for English-Sinhala and English-Punjabi.
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。
