The minimum Bayes risk (MBR) decoding objective improves BLEU scores for machine translation output relative to the standard Viterbi objective of maximizing model score. However, MBR targeting BLEU is prohibitively slow to optimize over k-best lists for large k. In this paper, we introduce and analyze an alternative to MBR that is equally effective at improving performance, yet is asymptotically faster — running 80 times faster than MBR in experiments with 1000-best lists. Furthermore, our fast decoding procedure can select output sentences based on distributions over entire forests of translations, in addition to k-best lists. We evaluate our procedure on translation forests from two large-scale, state-of-the-art hierarchical machine translation systems. Our forest-based decoding objective consistently outperforms k-best list MBR, giving improvements of up to 1.0 BLEU. 1

We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram counts, the same quantities that arise in forestbased consensus and minimum Bayes risk decoding methods. Our continuous objective can be optimized using simple gradient ascent. However, computing critical quantities in the gradient necessitates a novel dynamic program, which we also present here. Assuming BLEU as an evaluation measure, our objective function has two principle advantages over standard max BLEU tuning. First, it specifically optimizes model weights for downstream consensus decoding procedures. An unexpected second benefit is that it reduces overfitting, which can improve test set BLEU scores when using standard Viterbi decoding. 1

Machine translation benefits from two types of decoding techniques: consensus decoding over multiple hypotheses under a single model and system combination over hypotheses from different models. We present model combination, a method that integrates consensus decoding and system combination into a unified, forest-based technique. Our approach makes few assumptions about the underlying component models, enabling us to combine systems with heterogenous structure. Unlike most system combination techniques, we reuse the search space of component models, which entirely avoids the need to align translation hypotheses. Despite its relative simplicity, model combination improves translation quality over a pipelined approach of first applying consensus decoding to individual systems, and then applying system combination to their output. We demonstrate BLEU improvements across data sets and language pairs in large-scale experiments. 1

A novel and robust approach to improving statistical machine translation fluency is developed within a minimum Bayesrisk decoding framework. By segmenting translation lattices according to confidence measures over the maximum likelihood translation hypothesis we are able to focus on regions with potential translation errors. Hypothesis space constraints based on monolingual coverage are applied to the low confidence regions to improve overall translation fluency. 1

Discriminative training for machine translation has been well studied in the recent past. A limitation of the work to date is that it relies on the availability of high-quality in-domain bilingual text for supervised training. We present an unsupervised discriminative training framework to incorporate the usually plentiful target-language monolingual data by using a rough “reverse ” translation system. Intuitively, our method strives to ensure that probabilistic “round-trip ” translation from a targetlanguage sentence to the source-language and back will have low expected loss. Theoretically, this may be justified as (discriminatively) minimizing an imputed empirical risk. Empirically, we demonstrate that augmenting supervised training with unsupervised data improves translation performance over the supervised case for both IWSLT and NIST tasks. 1

We present a unified approach to performing minimum risk training and minimum Bayes risk (MBR) decoding with BLEU in a phrase-based model. Key to our approach is the use of a Gibbs sampler that allows us to explore the entire probability distribution and maintain a strict probabilistic formulation across the pipeline. We also describe a new sampling algorithm called corpus sampling which allows us at training time to use BLEU instead of an approximation thereof. Our approach is theoretically sound and gives better (up to +0.6%BLEU) and more stable results than the standard MERT optimization algorithm. By comparing our approach to lattice MBR, we are also able to gain crucial insights about both methods. 1

This dissertation is the result of my own work and includes nothing which is the outcome of work done in collaboration except where specifically indicated in the text. It has not been submitted in whole or in part for a degree at any other university. Some of the work has been published previously in conference proceedings (Blackwood et al., 2008a; Blackwood

We present minimum Bayes-risk system combination, a method that integrates consensus decoding and system combination into a unified multi-system minimum Bayes-risk (MBR) technique. Unlike other MBR methods that re-rank translations of a single SMT system, MBR system combination uses the MBR decision rule and a linear combination of the component systems ’ probability distributions to search for the minimum risk translation among all the finite-length strings over the output vocabulary. We introduce expected BLEU, an approximation to the BLEU score that allows to efficiently apply MBR in these conditions. MBR system combination is a general method that is independent of specific SMT models, enabling us to combine systems with heterogeneous structure. Experiments show that our approach bring significant improvements to single-system-based MBR decoding and achieves comparable results to different state-of-the-art system combination methods. 1

Although discriminative training guarantees to improve statistical machine translation by incorporating a large amount of overlapping features, it is hard to scale up to large data due to decoding complexity. We propose a new algorithm to generate translation forest of training data in linear time with the help of word alignment. Our algorithm also alleviates the oracle selection problem by ensuring that a forest always contains derivations that exactly yield the reference translation. With millions of features trained on 519K sentences in 0.03 second per sentence, our system achieves significant improvement by 0.84 BLEU over the baseline system on the NIST Chinese-English test sets. 1

We propose Maximum Ranking Correlation (MRC) as an objective function in discriminative tuning of parameters in a linear model of Statistical Machine Translation (SMT). We try to maximize the ranking correlation between sentence level BLEU (SBLEU) scores and model scores of the N-best list, while the MERT paradigm focuses on the potential 1-best candidates of the N-best list. After we optimize the MER and the MRC objectives using an multiple objective optimization algorithm at the same time, we interpolate them to obtain parameters which outperform both. Experimental results on WMT French–English data set confirm that our method significantly outperforms MERT on out-of-domain data sets, and performs marginally better than MERT on in-domain data sets, which validates the usefulness of MRC on both domain specific and general domain data.