We present a novel translation model, which simultaneously exploits the constituency and dependency trees on the source side, to combine the advantages of two types of trees. We take head-dependents relations of dependency trees as backbone and incorporate phrasal nodes of constituency trees as the source side of our translation rules, and the target side as strings. Our rules hold the property...

Example-Based Machine Translation (EBMT), like other corpus based methods, requires substantial parallel training data. One way to reduce data requirements and improve translation quality is to generalize parts of the parallel corpus into translation templates. This automated generalization process requires clustering. In most clustering approaches the optimal number of clusters (N ) is found e...

We examine a new, intuitive measure for evaluating machine-translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments. Translation Edit Rate (TER) measures the amount of editing that a human would have to perform to change a system output so it exactly matches a reference translation. We show that the single-refere...

Statistical machine translation (SMT) should benefit from linguistic information to improve performance but current state-of-the-art models rely purely on data-driven models. There are several reasons why prior efforts to build linguistically annotated models have failed or not even been attempted. Firstly, the practical implementation often requires too much work to be cost effective. Where ad...

It is possible to reduce the bulk of phrasetables for Statistical Machine Translation using a technique based on the significance testing of phrase pair co-occurrence in the parallel corpus. The savings can be quite substantial (up to 90%) and cause no reduction in BLEU score. In some cases, an improvement in BLEU is obtained at the same time although the effect is less pronounced if state-of-t...

In this paper we present a new automatic scoring method for machine translations. Like the now-traditional BLEU score it maps a proposed translation and a set of reference translations to a real number. This number is intended to reflect the quality of the proposed translation. We present some experiments that indicate that this new metric, the Bllip score (Brown Laboratory for Linguistic Infor...

Following the recent adoption by the machine translation community of automatic evaluation using the BLEU/NIST scoring process, we conduct an in-depth study of a similar idea for evaluating summaries. The results show that automatic evaluation using unigram cooccurrences between summary pairs correlates surprising well with human evaluations, based on various statistical metrics; while direct a...

System architecture, experimental settings and evaluation results of the EIWA in the WAT2014 Japanese to English (jaen) and Chinese to Japanese (zh-ja) tasks are described. Our system is combining rule-based machine translation (RBMT) and statistical post-editing (SPE). Evaluation results for ja-en task show 19.86 BLEU score, 0.7067 RIBES score, and 22.50 human evaluation score. Evaluation resu...