Hierarchical phrase-based translation with weighted finite state transducers

Iglesias, Gonzalo; Gispert, Adrià de; Banga, Eduardo Rodríguez; Byrne, William

doi:10.3115/1620754.1620817

Cited by 17 publications

(20 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section we describe the HiFST decoder [47,79,81]. As stated in Section 2.3.1 the CYK algorithm produces a large number of derivations that share sub-derivations.…”

Section: Hierarchical Phrase-based Decoding With Wfstsmentioning

confidence: 99%

“…For example, another alternative is a push down automata (PDA) [79]. A PDA representation can be used for a larger T at the cost of a smaller language model M.…”

Section: Apply the Language Model Via Intersectionmentioning

confidence: 99%

“…In this section we describe HiFST [47,81], a hierarchical phrase-based decoder that uses a WFST. The HiFST decoder produces word lattices and applies the full language model using WFST operations.…”

Section: Hifstmentioning

confidence: 99%

See 2 more Smart Citations

The Geometry of Statistical Machine Translation

Waite¹,

Byrne²

2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Most modern statistical machine translation systems are based on the linear model. There are many reasons for the prevalence of the linear model: other component models can be incorporated as features, there are many methods for estimating their parameters, and the resulting model scores can be easily used in finite-state representations.One popular method for estimating the parameters of a linear model is minimum error rate training (MERT). Galley and Quirk describe an optimal MERT algorithm that requires an exponential runtime for multiple sentences. We find that this form of MERT can be represented using convex geometry. Using this geometric representation we describe an optimal algorithm that runs in polynomial time with respect to the number of feasible solutions, and describe Projected MERT, a practical implementation of multidimensional MERT in low dimensions.Using this geometric representation of MERT we investigate whether the optimisation of linear models is tractable in general. It has been believed that the number of feasible solutions of a linear model is exponential with respect to the number of training sentences, however we show that the exponential explosion is due to feature dimension. A result that has important ramifications because of the current trend of building statistical machine translation systems around a large number of sparse features.We also show how these convex geometric descriptions of linear models can be neatly integrated into finite-state representations using tropical geometry. The resulting semirings provide a formulation for multidimensional MERT that can be applied to lattices and hypergraphs.In contrast to this theoretical work, we also present practical descriptions of tools and techniques used for fast parameter estimation and filtering of hierarchical phrase-based translation models and N-gram language models. These techniques allow us to quickly build rich models over large datasets. The resulting models are used as the basis of a machine translation system that performs competitively at international evaluations.

show abstract

“…In this section we describe the HiFST decoder [47,79,81]. As stated in Section 2.3.1 the CYK algorithm produces a large number of derivations that share sub-derivations.…”

Section: Hierarchical Phrase-based Decoding With Wfstsmentioning

confidence: 99%

“…For example, another alternative is a push down automata (PDA) [79]. A PDA representation can be used for a larger T at the cost of a smaller language model M.…”

Section: Apply the Language Model Via Intersectionmentioning

confidence: 99%

See 1 more Smart Citation

The Geometry of Statistical Machine Translation

Waite¹,

Byrne²

2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…Here we follow the approach of expanding this space onto a Finite-State Automata (FSA) described in (de Gispert et al, 2010;Iglesias et al, 2011). This means that in parsing, each cell M [x, y] is associated with an FSA F x,y , which encodes all the sequences generated by the grammar when covering the words marked by the bit string of that cell.…”

Section: Generation From Exact Parsingmentioning

confidence: 99%

“…GYRO builds on approaches developed for syntactic SMT (Chiang, 2007;de Gispert et al, 2010;Iglesias et al, 2011). The system generates strings in the form of weighted automata which can be rescored using higher-order n-gram LMs, dependency LMs (Shen et al, 2010), and Minimum Bayes Risk decoding, either using posterior probabilities obtained from GYRO or SMT systems.…”

Section: Introductionmentioning

confidence: 99%

Word Ordering with Phrase-Based Grammars

Gispert

Tomalin

Byrne

2014

Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

We describe an approach to word ordering using modelling techniques from statistical machine translation. The system incorporates a phrase-based model of string generation that aims to take unordered bags of words and produce fluent, grammatical sentences. We describe the generation grammars and introduce parsing procedures that address the computational complexity of generation under permutation of phrases. Against the best previous results reported on this task, obtained using syntax driven models, we report huge quality improvements, with BLEU score gains of 20+ which we confirm with human fluency judgements. Our system incorporates dependency language models, large n-gram language models, and minimum Bayes risk decoding.

show abstract

Cardinality pruning and language model heuristics for hierarchical phrase-based translation

Vilar

Ney

2011

Machine Translation

View full text Add to dashboard Cite

Hierarchical phrase-based translation with weighted finite state transducers

Cited by 17 publications

References 66 publications

The Geometry of Statistical Machine Translation

The Geometry of Statistical Machine Translation

Word Ordering with Phrase-Based Grammars

Cardinality pruning and language model heuristics for hierarchical phrase-based translation

Contact Info

Product

Resources

About