Often, the training procedure for statistical machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is only a loose relation to the final translation quality on unseen text. In this paper, we analyze various training criteria which directly optimize translation quality.

In this article we describe HiFST, a lattice-based decoder for hierarchical phrase-based translation and alignment. The decoder is implemented with standard Weighted Finite-State Transducer (WFST) operations as an alternative to the well-known cube pruning procedure. We find that the use of WFSTs rather than k-best lists requires less pruning in translation search, resulting in fewer search errors, better parameter optimization, and improved translation performance. The direct generation of translation lattices in the target language can improve subsequent rescoring procedures, yielding further gains when applying long-span language models and Minimum Bayes Risk decoding. We also provide insights as to how to control the size of the search space defined by hierarchical rules. We show that shallow-n grammars, low-level rule catenation, and other search constraints can help to match the power of the translation system to specific language pairs.

The need to meaningfully combine sets of rankings often comes up when one deals with ranked data. Although a number of heuristic and supervised learning approaches to rank aggregation exist, they require domain knowledge or supervised ranked data, both of which are expensive to acquire. In order to address these limitations, we propose a mathematical and algorithmic framework for learning to aggregate (partial) rankings without supervision. We instantiate the framework for the cases of combining permutations and combining top-k lists, and propose a novel metric for the latter. Experiments in both scenarios demonstrate the effectiveness of the proposed formalism. 1.

In this paper, we describe the machine translation system in the evaluation campaign of the Fourth Workshop on Statistical Machine Translation at EACL 2009. We describe the modular design of our multiengine MT system with particular focus on the components used in this participation. We participated in the translation task for the following translation directions: French– English and English–French, in which we employed our multi-engine architecture to translate. We also participated in the system combination task which was carried out by the MBR decoder and Confusion Network decoder. We report results on the provided development and test sets. 1

We describe refinements to hierarchical translation search procedures intended to reduce both search errors and memory usage through modifications to hypothesis expansion in cube pruning and reductions in the size of the rule sets used in translation. Rules are put into syntactic classes based on the number of non-terminals and the pattern, and various filtering strategies are then applied to assess the impact on translation speed and quality. Results are reported on the 2008 NIST Arabic-to-English evaluation task. 1

ccb cs jhu edu Manual evaluation of translation quality is generally thought to be excessively time consuming and expensive. We explore a fast and inexpensive way of doing it using Amazon’s Mechanical Turk to pay small sums to a large number of non-expert annotators. For $10 we redundantly recreate judgments from a WMT08 translation task. We find that when combined non-expert judgments have a high-level of agreement with the existing gold-standard judgments of machine translation quality, and correlate more strongly with expert judgments than Bleu does. We go on to show that Mechanical Turk can be used to calculate human-mediated translation edit rate (HTER), to conduct reading comprehension experiments with machine translation, and to create high quality reference translations. 1

Statistical machine translation (SMT) models require bilingual corpora for training, and these corpora are often multilingual with parallel text in multiple languages simultaneously. We introduce an active learning task of adding a new language to an existing multilingual set of parallel text and constructing high quality MT systems, from each language in the collection into this new target language. We show that adding a new language using active learning to the EuroParl corpus provides a significant improvement compared to a random sentence selection baseline. We also provide new highly effective sentence selection methods that improve AL for phrase-based SMT in the multilingual and single language pair setting. 1

The best systems for machine translation of natural language are based on statistical models learned from data. Conventional representation of a statistical translation model requires substantial offline computation and representation in main memory. Therefore, the principal bottlenecks to the amount of data we can exploit and the complexity of models we can use are available memory and CPU time, and current state of the art already pushes these limits. With data size and model complexity continually increasing, a scalable solution to this problem is central to future improvement. Callison-Burch et al. (2005) and Zhang and Vogel (2005) proposed a solution that we call translation by pattern matching, which we bring to fruition in this dissertation. The training data itself serves as a proxy to the model; rules and parameters are computed on demand. It achieves our desiderata of minimal offline computation and compact representation, but is dependent on fast pattern matching algorithms on text. They demonstrated its application to a common model based on the translation of contiguous substrings, but leave some open problems. Among these is a question: can this approach match the performance of conventional methods despite unavoidable differences that it induces in the model? We show how to answer this question affirmatively. The main

In this paper we describe a new iterative translation process designed to leverage the massive number of online users who have minimal or no bilingual skill. The iterative process is supported by combining existing machine translation methods with monolingual human speakers. We have built a Web-based prototype that is capable of yielding high quality translations at much lower cost than traditional professional translators. Preliminary evaluation results of this prototype confirm the validity of the approach. Author Keywords Monolingual, translation, translation interface, human computation, distributed human computation, wisdom of crowds, crowdsourcing, machine translation. ACM Classification Keywords H5.m. Information interfaces and presentation (e.g., HCI):

In this paper, we propose a framework for combining outputs from multiple on-line machine translation systems. This framework consists of several modules, including selection, substitution, insertion, and deletion. We evaluate the combination framework on IWSLT07 in travel domain, for the translation direction from Chinese to English. Three different on-line machine translation systems, Google, Yahoo, and TransWhiz, are used in the investigation. The experimental results show that our proposed combination framework improves BLEU score from 19.15 to 20.55. It achieves an absolute improvement of 1.4 in the BLEU score.