Tree parsing for tree-adjoining machine translation
Tree parsing for tree-adjoining machine translation
复制标题
DOI：
10.1093/logcom/exs050
复制
发表时间：
2014-04
期刊：
影响因子：
--
通讯作者：
Matthias Büchse;H. Vogler;M. Nederhof
中科院分区：
文献类型：
--
作者：
Matthias Büchse;H. Vogler;M. Nederhof
树分析是统计机器翻译中的一个重要问题。在这种情况下，给出了（a）描述从一种语言到另一种语言的翻译的同步语法和（B）可识别的树集合;目的是构建从给定集合导出元素的那些派生的集合的有限表示，无论是在源侧（输入限制）还是在目标侧（输出限制）。在树邻接机器翻译中，文法是一种同步树邻接文法。对于这种情况，只描述了树解析问题的部分解决方案，一些仅限于未加权的情况，一些仅限于单语情况。我们引入一类同步树邻接语法，它在输入和输出限制下有效地关闭到加权正则树语言，即受限制的翻译可以再次由同一类中的语法表示;这使得例如级联限制成为可能。此外，我们提出了一个算法，构造这些文法的输入和输出限制。
Tree parsing is an important problem in statistical machine translation. In this context, one is given (a) a synchronous grammar that describes the translation from one language into another and (b) a recognizable set of trees; the aim is to construct a finite representation of the set of those derivations that derive elements from the given set, either on the source side (input restriction) or on the target side (output restriction). In tree-adjoining machine translation the grammar is a kind of synchronous tree-adjoining grammar. For this case, only partial solutions to the tree parsing problem have been described, some being restricted to the unweighted case, some to the monolingual case. We introduce a class of synchronous tree-adjoining grammars which is effectively closed under input and output restrictions to weighted regular tree languages, i.e. the restricted translations can again be represented by grammars in the same class; this enables, e.g. cascading restrictions. Moreover, we present an algorithm that constructs these grammars for input and output restriction.