This paper proposes a forest-based tree sequence to string translation model for syntaxbased statistical machine translation, which automatically learns tree sequence to string translation rules from word-aligned sourceside-parsed bilingual texts. The proposed model leverages on the strengths of both tree sequence-based and forest-based translation models. Therefore, it can not only utilize forest structure that compactly encodes exponential number of parse trees but also capture nonsyntactic translation equivalences with linguistically structured information through tree sequence. This makes our model potentially more robust to parse errors and structure divergence. Experimental results on the NIST MT-2003 Chinese-English translation task show that our method statistically significantly outperforms the four baseline systems. 1

While it is generally accepted that many translation phenomena are correlated with linguistic structures, employing linguistic syntax for translation has proven a highly non-trivial task. The key assumption behind many approaches is that translation is guided by the source and/or target language parse, employing rules extracted from the parse tree or performing tree transformations. These approaches enforce strict constraints and might overlook important translation phenomena that cross linguistic constituents. We propose a novel flexible modelling approach to introduce linguistic information of varying granularity from the source side. Our method induces joint probability synchronous grammars and estimates their parameters, by selecting and weighing together linguistically motivated rules according to an objective function directly targeting generalisation over future data. We obtain statistically significant improvements across 4 different language pairs with English as source, mounting up to +1.92 BLEU for Chinese as target. 1

We describe a scalable decoder for parsing-based machine translation. The decoder is written in Java and implements all the essential algorithms described in (Chiang, 2007) and (Li and Khudanpur, 2008b): chart-parsing, n-gram language model integration, beam- and cube-pruning, and k-best extraction. Additionally, parallel and distributed computing techniques are exploited to make it scalable. We demonstrate experimentally that our decoder is more than 30 times faster than a baseline decoder written in Python.

In this paper, we describe a new reranking strategy named word lattice reranking, for the task of joint Chinese word segmentation and part-of-speech (POS) tagging. As a derivation of the forest reranking for parsing (Huang, 2008), this strategy reranks on the pruned word lattice, which potentially contains much more candidates while using less storage, compared with the traditional n-best list reranking. With a perceptron classifier trained with local features as the baseline, word lattice reranking performs reranking with non-local features that can’t be easily incorporated into the perceptron baseline. Experimental results show that, this strategy achieves improvement on both segmentation and POS tagging, above the perceptron baseline and the n-best list reranking. 1

Traditional 1-best translation pipelines suffer a major drawback: the errors of 1-best outputs, inevitably introduced by each module, will propagate and accumulate along the pipeline. In order to alleviate this problem, we use compact structures, lattice and forest, in each module instead of 1-best results. We integrate both lattice and forest into a single tree-to-string system, and explore the algorithms of lattice parsing, lattice-forest-based rule extraction and decoding. More importantly, our model takes into account all the probabilities of different steps, such as segmentation, parsing, and translation. The main advantage of our model is that we can make global decision to search for the best segmentation, parse-tree and translation in one step. Medium-scale experiments show an improvement of +0.9 BLEU points over a state-of-the-art forest-based baseline. 1

Tree-to-string systems (and their forestbased extensions) have gained steady popularity thanks to their simplicity and efficiency, but there is a major limitation: they are unable to guarantee the grammaticality of the output, which is explicitly modeled in string-to-tree systems via targetside syntax. We thus propose to combine the advantages of both, and present a novel constituency-to-dependency translation model, which uses constituency forests on the source side to direct the translation, and dependency trees on the target side (as a language model) to ensure grammaticality. Medium-scale experiments show an absolute and statistically significant improvement of +0.7 BLEU points over a state-of-the-art forest-based tree-to-string system even with fewer rules. This is also the first time that a treeto-tree model can surpass tree-to-string counterparts. 1

In this paper we apply lightly-supervised training to a hierarchical phrase-based statistical machine translation system. We employ bitexts that have been built by automatically translating large amounts of monolingual data as additional parallel training corpora. We explore different ways of using this additional data to improve our system. Our results show that integrating a second translation model with only non-hierarchical phrases extracted from the automatically generated bitexts is a reasonable approach. The translation performance matches the result we achieve with a joint extraction on all training bitexts while the system is kept smaller due to a considerably lower overall number of phrases. 1

This paper compares several translation representations for a synchronous context-free grammar parse including CFGs/hypergraphs, finite-state automata (FSA), and pushdown automata (PDA). The representation choice is shown to determine the form and complexity of target LM intersection and shortest-path algorithms that follow. Intersection, shortest path, FSA expansion and RTN replacement algorithms are presented for PDAs. Chinese-to-English translation experiments using HiFST and HiPDT, FSA and PDA-based decoders, are presented using admissible (or exact) search, possible for HiFST with compact SCFG rulesets and HiPDT with compact LMs. For large rulesets with large LMs, we introduce a two-pass search strategy which we then analyze in terms of search errors and translation performance. 1

An end-to-end toolkit for large scale PSCFG based MT

In a linguistically-motivated syntax-based translation system, the entire translation process is normally carried out in two steps, translation rule matching and target sentence decoding using the matched rules. Both steps are very timeconsuming due to the tremendous number of translation rules, the exhaustive search in translation rule matching and the complex nature of the translation task itself. In this paper, we propose a hyper-tree-based fast algorithm for translation rule matching. Experimental results on the NIST MT-2003 Chinese-English translation task show that our algorithm is at least 19 times faster in rule matching and is able to help to save 57 % of overall translation time over previous methods when using large fragment translation rules. 1