In modern machine translation practice, a statistical phrasal or hierarchical translation system usually relies on a huge set of translation rules extracted from bi-lingual training data. This approach not only results in space and efficiency issues, but also suffers from the sparse data problem. In this paper, we propose to use factorized grammars, an idea widely accepted in the field of linguistic grammar construction, to generalize translation rules, so as to solve these two problems. We designed a method to take advantage of the XTAG English Grammar to facilitate the extraction of factorized rules. We experimented on various setups of low-resource language translation, and showed consistent significant improvement in BLEU over state-ofthe-art string-to-dependency baseline systems with 200K words of bi-lingual training data.

We present a new translation model that include undecorated hierarchical-style phrase rules, decorated source-syntax rules, and partially decorated rules. Results show an increase in translation performance of up to 0.8 % BLEU for German–English translation when trained on the news-commentary corpus, using syntactic annotation from a source language parser. We also experimented with annotation from shallow taggers and found this increased performance by 0.5 % BLEU. 1

This paper presents a novel filtration criterion to restrict the rule extraction for the hierarchical phrase-based translation model, where a bilingual but relaxed wellformed dependency restriction is used to filter out bad rules. Furthermore, a new feature which describes the regularity that the source/target dependency edge triggers the target/source word is also proposed. Experimental results show that, the new criteria weeds out about 40 % rules while with translation performance improvement, and the new feature brings another improvement to the baseline system, especially on larger corpus. 1

Hierarchical phrase-based (HPB) translation provides a powerful mechanism to capture both short and long distance phrase reorderings. However, the phrase reorderings lack of contextual information in conventional HPB systems. This paper proposes a contextdependent phrase reordering approach that uses the maximum entropy (MaxEnt) model to help the HPB decoder select appropriate reordering patterns. We classify translation rules into several reordering patterns, and build a MaxEnt model for each pattern based on various contextual features. We integrate the MaxEnt models into the HPB model. Experimental results show that our approach achieves significant improvements over a standard HPB system on large-scale translation tasks. On Chinese-to-English translation, the absolute improvements in BLEU (caseinsensitive) range from 1.2 to 2.1. 1

Machine translation has advanced considerably in recent years, but primarily due to the availability of larger data sets. Translation of low-frequency phrases and resourcepoor languages is still a serious problem. In this work we explore a deeper integration of context, structure, and similarity within machine translation. Instead of modeling phrase pairs in abstract, we propose modeling each instance of a translation in the corpus. Unlike the traditional SMT approach that builds a mixture of independent, simple distributions for each phrase pair, our model is a mixture of translation instances. The significance lies in that we use a distance measure to assesses the relevance of each translation instance. It permits simple the integration of instance-specific features which we plan to exploit in three key directions. First, we will introduce non-local features that identify the relevant context of an instance in order to favor those that are most similar to the input. Second, we will mark-up the corpus with metadata from multiple external sources to sharpen the scoring of each translation instance and guide the overall translation process. Third, we will identify

Statistical machine translation (SMT) models have recently begun to include source context modeling, under the assumption that the proper lexical choice of the translation for an ambiguous word can be determined from the context in which it appears. Various types of lexical and syntactic features have been explored as effective source context to improve phrase selection in SMT. In the present work, we introduce lexico-syntactic descriptions in the form of supertags as source-side context features in the state-of-the-art hierarchical phrase-based SMT (HPB) model. These features enable us to exploit source similarity in addition to target similarity, as modelled by the language model. In our experiments two kinds of supertags are employed: those from lexicalized tree-adjoining grammar (LTAG) and combinatory categorial grammar (CCG). We use a memory-based classification framework that enables the efficient estimation of these features. Despite the differences between the two supertagging approaches, they give similar improvements. We evaluate the performance of our approach on an English-to-Dutch translation task, and report statistically significant improvements of 4.48 % and 6.3 % BLEU scores in translation quality when adding CCG and LTAG supertags, respectively, as context-informed features. 1

for the degree of Doctor of Philosophy. Machine translation has advanced considerably in recent years, primarily due to the availability of larger datasets. Translation of low-frequency phrases and resourcepoor languages is still a serious problem. In this work, we explore modeling each instance of translation in the corpus. A translation instance reflects a source and target correspondence at one specific location in the corpus. The significance of this approach is that our model is able to capture that some instances of translation are more relevant than others. We have implemented this approach in Cunei, a new platform for machine translation that permits the scoring of instance-specific features. Leveraging per-instance alignment features, we demonstrate that Cunei can outperform Moses, a widely used machine translation system. We then expand on this baseline system in three principal directions, each of which shows further gains. First, we score the source context of a translation instance in order to favor those that are most similar to the input. Second, we model

Part-of-speech language modeling is commonly used as a component in statistical machine translation systems, but there is mixed evidence that its usage leads to significant improvements. We argue that its limited effectiveness is due to the lack of lexicalization. We introduce a new approach that builds a separate local language model for each word and part-of-speech pair. The resulting models lead to more context-sensitive probability distributions and we also exploit the fact that different local models are used to estimate the language model probability of each word during decoding. Our approach is evaluated for Arabic- and Chinese-to-English translation. We show that it leads to statistically significant improvements for multiple test sets and also across different genres, when compared against a competitive baseline and a system using a part-of-speech model. 1