Generating Non-Projective Word Order in Statistical Linearization
نویسندگان
چکیده
We propose a technique to generate nonprojective word orders in an efficient statistical linearization system. Our approach predicts liftings of edges in an unordered syntactic tree by means of a classifier, and uses a projective algorithm for tree linearization. We obtain statistically significant improvements on six typologically different languages: English, German, Dutch, Danish, Hungarian, and Czech.
منابع مشابه
Breaking the barrier of context-freeness
This paper presents a generative probabilistic dependency model of parallel texts that can be used for statistical machine translation and parallel parsing. Unlike syntactic models that are based on context-free dependency grammars, the dependency model proposed in this paper is based on a sophisticated notion of dependency grammar that is capable of modelling non-projective word order and isla...
متن کاملRe-ordering Source Sentences for SMT
We propose a pre-processing stage for Statistical Machine Translation (SMT) systems where the words of the source sentence are re-ordered as per the syntax of the target language prior to the alignment process, so that the alignment found by the statistical system is improved. We take a dependency parse of the source sentence and linearize it as per the syntax of the target language, before it ...
متن کاملStatistical Parsing with Context-Free Filtering Grammar
Statistical Parsing with Context-Free Filtering Grammar Michael Demko Master of Science Graduate Department of Computer Science University of Toronto 2007 Statistical parsers that simultaneously generate both phrase-structure and lexical dependency trees have been limited in two important ways: the detection of non-projective dependencies has not been integrated with other parsing decisions, or...
متن کاملTowards Non-projective High-Order Dependency Parser
This paper demonstrates a novel high-order dependency parsing framework that targets nonprojective languages. It imitates how a human parses sentences in an intuitive way. At every step of the parse, it determines which word is the easiest to process among all the remaining words, identifies its head word and then folds it under the head word. This greedy framework achieves competitive accuracy...
متن کاملA Case Study of a Free Word Order
The paper aims at the investigation of free word order. It concentrates on the relationship between (formal) dependencies and word order. The investigation is performed by means of a semi-automatic application of a method of analysis by reduction to Czech syntactically annotated data. The paper also presents the analysis of introspectively created Czech sentences demonstrating complex phenomena...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012