This paper presents a simple and robust consensus decoding approach for combining multiple Machine Translation (MT) system outputs. A consensus network is constructed from an N-best list by aligning the hypotheses against an alignment reference, where the alignment is based on minimising the translation edit rate (TER). The Minimum Bayes Risk (MBR) decoding technique is investigated for the selection of an appropriate alignment reference. Several alternative decoding strategies proposed to retain coherent phrases in the original translations. Experimental results are presented primarily based on three-way combination of Chinese-English translation outputs, and also presents results for six-way system combination. It is shown that worthwhile improvements in translation performance can be obtained using the methods discussed.

Translation rule extraction is a fundamental problem in machine translation, especially for linguistically syntax-based systems that need parse trees from either or both sides of the bitext. The current dominant practice only uses 1-best trees, which adversely affects the rule set quality due to parsing errors. So we propose a novel approach which extracts rules from a packed forest that compactly encodes exponentially many parses. Experiments show that this method improves translation quality by over 1 BLEU point on a state-of-the-art tree-to-string system, and is 0.5 points better than (and twice as fast as) extracting on 30best parses. When combined with our previous work on forest-based decoding, it achieves a 2.5 BLEU points improvement over the baseline, and even outperforms the hierarchical system of Hiero by 0.7 points. 1

This paper presents a syntax-driven approach to question answering, specifically the answer-sentence selection problem for short-answer questions. Rather than using syntactic features to augment existing statistical classifiers (as in previous work), we build on the idea that questions and their (correct) answers relate to each other via loose but predictable syntactic transformations. We propose a probabilistic quasi-synchronous grammar, inspired by one proposed for machine translation (D. Smith and Eisner, 2006), and parameterized by mixtures of a robust nonlexical syntax/alignment model with a(n optional) lexical-semantics-driven log-linear model. Our model learns soft alignments as a hidden variable in discriminative training. Experimental results using the TREC dataset are shown to significantly outperform strong state-of-the-art baselines. 1

We compare and contrast the strengths and weaknesses of a syntax-based machine translation model with a phrase-based machine translation model on several levels. We briefly describe each model, highlighting points where they differ. We include a quantitative comparison of the phrase pairs that each model has to work with, as well as the reasons why some phrase pairs are not learned by the syntax-based model. We then evaluate proposed improvements to the syntax-based extraction techniques in light of phrase pairs captured. We also compare the translation accuracy for all variations. 1

In adding syntax to statistical MT, there is a tradeoff between taking advantage of linguistic analysis, versus allowing the model to exploit linguistically unmotivated mappings learned from parallel training data. A number of previous efforts have tackled this tradeoff by starting with a commitment to linguistically motivated analyses and then finding appropriate ways to soften that commitment. We present an approach that explores the tradeoff from the other direction, starting with a context-free translation model learned directly from aligned parallel text, and then adding soft constituent-level constraints based on parses of the source language. We obtain substantial improvements in performance for translation from Chinese and Arabic to English. 1

We show that phrase structures in Penn Treebank style parses are not optimal for syntaxbased machine translation. We exploit a series of binarization methods to restructure the Penn Treebank style trees such that syntactified phrases smaller than Penn Treebank constituents can be acquired and exploited in translation. We find that by employing the EM algorithm for determining the binarization of a parse tree among a set of alternative binarizations gives us the best translation result. 1

This paper presents a new hypothesis alignment method for combining outputs of multiple machine translation (MT) systems. An indirect hidden Markov model (IHMM) is proposed to address the synonym matching and word ordering issues in hypothesis alignment. Unlike traditional HMMs whose parameters are trained via maximum likelihood estimation (MLE), the parameters of the IHMM are estimated indirectly from a variety of sources including word semantic similarity, word surface similarity, and a distance-based distortion penalty. The IHMM-based method significantly outperforms the state-of-the-art TER-based alignment model in our experiments on NIST benchmark datasets. Our combined SMT system using the

Currently there are several approaches to machine translation (MT) based on different paradigms; e.g., phrasal, hierarchical and syntax-based. These three approaches yield similar translation accuracy despite using fairly different levels of linguistic knowledge. The availability of such a variety of systems has led to a growing interest toward finding better translations by combining outputs from multiple systems. This paper describes three different approaches to MT system combination. These combination methods operate on sentence, phrase and word level exploiting information from-best lists, system scores and target-to-source phrase alignments. The word-level combination provides the most robust gains but the best results on the development test sets (NIST MT05 and the newsgroup portion of GALE 2006 dry-run) were achieved by combining all three methods. 1

We present an efficient, novel two-pass approach to mitigate the computational impact resulting from online intersection of an n-gram language model (LM) and a probabilistic synchronous context-free grammar (PSCFG) for statistical machine translation. In first pass CYK-style decoding, we consider first-best chart item approximations, generating a hypergraph of sentence spanning target language derivations. In the second stage, we instantiate specific alternative derivations from this hypergraph, using the LM to drive this search process, recovering from search errors made in the first pass. Model search errors in our approach are comparable to those made by the state-of-the-art “Cube Pruning ” approach in (Chiang, 2007) under comparable pruning conditions evaluated on both hierarchical and syntax-based grammars. 1

This paper presents a translation model that is based on tree sequence alignment, where a tree sequence refers to a single sequence of subtrees that covers a phrase. The model leverages on the strengths of both phrase-based and linguistically syntax-based method. It automatically learns aligned tree sequence pairs with mapping probabilities from word-aligned biparsed parallel texts. Compared with previous models, it not only captures non-syntactic phrases and discontinuous phrases with linguistically structured features, but also supports multi-level structure reordering of tree typology with larger span. This gives our model stronger expressive power than other reported models. Experimental results on the NIST MT-2005 Chinese-English translation task show that our method statistically significantly outperforms the baseline systems. 1