We describe a novel approach to statistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation. This method requires a source-language dependency parser, target language word segmentation and an unsupervised word alignment component. We align a parallel corpus, project the source dependency parse onto the target sentence, extract dependency treelet translation pairs, and train a tree-based ordering model. We describe an efficient decoder and show that using these treebased models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser. 1.

A syntax-directed translator first parses the source-language input into a parsetree, and then recursively converts the tree into a string in the target-language. We model this conversion by an extended treeto-string transducer that have multi-level trees on the source-side, which gives our system more expressive power and flexibility. We also define a direct probability model and use a linear-time dynamic programming algorithm to search for the best derivation. The model is then extended to the general log-linear framework in order to rescore with other features like n-gram language models. We devise a simple-yet-effective algorithm to generate non-duplicate k-best translations for n-gram rescoring. Initial experimental results on English-to-Chinese translation are presented. 1

Among syntax-based translation models, the tree-based approach, which takes as input a parse tree of the source sentence, is a promising direction being faster and simpler than its string-based counterpart. However, current tree-based systems suffer from a major drawback: they only use the 1-best parse to direct the translation, which potentially introduces translation mistakes due to parsing errors. We propose a forest-based approach that translates a packed forest of exponentially many parses, which encodes many more alternatives than standard n-best lists. Large-scale experiments show an absolute improvement of 1.7 BLEU points over the 1-best baseline. This result is also 0.8 points higher than decoding with 30-best parses, and takes even less time. 1

Syntactic reordering approaches are an effective method for handling word-order differences between source and target languages in statistical machine translation (SMT) systems. This paper introduces a reordering approach for translation from Chinese to English. We describe a set of syntactic reordering rules that exploit systematic differences between Chinese and English word order. The resulting system is used as a preprocessor for both training and test sentences, transforming Chinese sentences to be much closer to English in terms of their word order. We evaluated the reordering approach within the MOSES phrase-based SMT system (Koehn et al., 2007). The reordering approach improved the BLEU score for the MOSES system from 28.52 to 30.86 on the NIST 2006 evaluation data. We also conducted a series of experiments to analyze the accuracy and impact of different types of reordering rules. 1

done while at Microsoft Research We describe a novel approach to statistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation. We depend on a source-language dependency parser and a word-aligned parallel corpus. The only target language resource assumed is a word breaker. These are used to produce treelet (“phrase”) translation pairs as well as several models, including a channel model, an order model, and a target language model. Together these models and the treelet translation pairs provide a powerful and promising approach to MT that incorporates the power of phrasal SMT with the linguistic generality available in a parser. We evaluate two decoding approaches, one inspired by dynamic programming and the

Probabilistic grammars offer great flexibility in modeling discrete sequential data like natural language text. Their symbolic component is amenable to inspection by humans, while their probabilistic component helps resolve ambiguity. They also permit the use of well-understood, generalpurpose learning algorithms. There has been an increased interest in using probabilistic grammars in the Bayesian setting. To date, most of the literature has focused on using a Dirichlet prior. The Dirichlet prior has several limitations, including that it cannot directly model covariance between the probabilistic grammar’s parameters. Yet, various grammar parameters are expected to be correlated because the elements in language they represent share linguistic properties. In this paper, we suggest an alternative to the Dirichlet prior, a family of logistic normal distributions. We derive an inference algorithm for this family of distributions and experiment with the task of dependency grammar induction, demonstrating performance improvements with our priors on a set of six treebanks in different natural languages. Our covariance framework permits soft parameter tying within grammars and across grammars for text in different languages, and we show empirical gains in a novel learning setting using bilingual, non-parallel data.

Abstract not found

Vertex Covering by Paths on Trees with applications in machine translation is the task to cover all vertices of a tree T = (V,E) by choosing a minimum-weight subset of given paths in the tree. The problem is NP-hard and has recently been solved by an exact algorithm running in O(4 C · |V | 2) time, where C denotes the maximum number of paths covering a tree vertex. We improve this running time to O(2 C · C · |V |). On the route to this, we introduce the problem Tree-like Weighted Hitting Set which might be of independent interest. In addition, for the unweighted case of Vertex Covering by Paths on Trees, we present an exact algorithm using a search tree of size O(2 k · k!), where k denotes the number of chosen covering paths. Finally, we briefly discuss the existence of a size-O(k 2) problem kernel. Key words: graph algorithms, combinatorial problems, fixed-parameter tractability, exact algorithms 1

The paper presents an efficient, wide-coverage, sentence generator for Dutch, which employs the Alpino grammar and lexicon. This generator consists of a chart-based sentence realizer that builds grammatical sentences for a given abstract dependency structure, and a maximum-entropy fluency ranker which selects the most fluent sentence from a set of candidate sentences for a given dependency structure. The coverage, speed and accuracy of the generator is evaluated on several corpora. 1

In this paper, we propose a novel dependency-based bracketing transduction grammar for statistical machine translation, which converts a source sentence into a target dependency tree. Different from conventional bracketing transduction grammar models, we encode target dependency information into our lexical rules directly, and then we employ two different maximum entropy models to determine the reordering and combination of partial dependency structures, when we merge two neighboring blocks. By incorporating dependency language model further, large-scale experiments on Chinese-English task show that our system achieves significant improvements over the baseline system on various test sets even with fewer phrases. 1