机器翻译
计算机科学
人工智能
判决
自然语言处理
机器翻译软件可用性
解析
基于迁移的机器翻译
短语
基于规则的机器翻译
机器翻译评价
基于实例的机器翻译
动态形式等价
稳健性(进化)
语法
基因
生物化学
化学
作者
Pinjia He,Clara Meister,Zhendong Su
标识
DOI:10.48550/arxiv.1907.08710
摘要
In recent years, machine translation software has increasingly been integrated into our daily lives. People routinely use machine translation for various applications, such as describing symptoms to a foreign doctor and reading political news in a foreign language. However, the complexity and intractability of neural machine translation (NMT) models that power modern machine translation make the robustness of these systems difficult to even assess, much less guarantee. Machine translation systems can return inferior results that lead to misunderstanding, medical misdiagnoses, threats to personal safety, or political conflicts. Despite its apparent importance, validating the robustness of machine translation systems is very difficult and has, therefore, been much under-explored. To tackle this challenge, we introduce structure-invariant testing (SIT), a novel metamorphic testing approach for validating machine translation software. Our key insight is that the translation results of "similar" source sentences should typically exhibit similar sentence structures. Specifically, SIT (1) generates similar source sentences by substituting one word in a given sentence with semantically similar, syntactically equivalent words; (2) represents sentence structure by syntax parse trees (obtained via constituency or dependency parsing); (3) reports sentence pairs whose structures differ quantitatively by more than some threshold. To evaluate SIT, we use it to test Google Translate and Bing Microsoft Translator with 200 source sentences as input, which led to 64 and 70 buggy issues with 69.5\% and 70\% top-1 accuracy, respectively. The translation errors are diverse, including under-translation, over-translation, incorrect modification, word/phrase mistranslation, and unclear logic.
科研通智能强力驱动
Strongly Powered by AbleSci AI