Head Finalization: A Simple Reordering Rule for SOV Languages
Head Finalization: A Simple Reordering Rule for SOV Languages
复制标题
DOI：
--
复制
发表时间：
2010-07
期刊：
影响因子：
--
通讯作者：
Hideki Isozaki;Katsuhito Sudoh;Hajime Tsukada;Kevin Duh
中科院分区：
文献类型：
--
作者：
Hideki Isozaki;Katsuhito Sudoh;Hajime Tsukada;Kevin Duh
英语是一种典型的主谓宾语，而日语是一种典型的SOV语言。传统的统计机器翻译(SMT)系统在这些语言家族中的每一个中都工作得很好。然而，基于SMT的从SVO语言到SOV语言的翻译并不能很好地工作，因为它们的词序完全不同。最近，一些小组提出了基于规则的预处理方法来缓解这个问题(Xu等人，2009年；Hong等人，2009年)。这些方法通过使用一组手工编写的规则重写SVO语句，以派生出更多类似SOV的语句。在本文中，我们提出了一种替代的单重排序规则：Head Finish。这是一种基于语法的预处理方法，具有简单的优点。我们不必担心词性标记或规则权重，因为强大的Enju解析器允许我们在一般级别上实现规则。我们的实验表明，它的结果，头尾英语(HFE)，遵循几乎相同的顺序与日语。我们还表明，该规则提高了自动评估分数。
English is a typical SVO (Subject-Verb-Object) language, while Japanese is a typical SOV language. Conventional Statistical Machine Translation (SMT) systems work well within each of these language families. However, SMT-based translation from an SVO language to an SOV language does not work well because their word orders are completely different. Recently, a few groups have proposed rule-based preprocessing methods to mitigate this problem (Xu et al., 2009; Hong et al., 2009). These methods rewrite SVO sentences to derive more SOV-like sentences by using a set of handcrafted rules. In this paper, we propose an alternative single reordering rule: Head Finalization. This is a syntax-based preprocessing approach that offers the advantage of simplicity. We do not have to be concerned about part-of-speech tags or rule weights because the powerful Enju parser allows us to implement the rule at a general level. Our experiments show that its result, Head Final English (HFE), follows almost the same order as Japanese. We also show that this rule improves automatic evaluation scores.