Hierarchical Phrase-Based Translation

By David Chiang. International Conference on Computational Logic, 2007

1,324 citations recorded by the source corpus.

We present a statistical machine translation model that uses hierarchical phrasesphrases that contain subphrases. The model is formally a synchronous context-free grammar but is learned from a parallel text without any syntactic annotations. Thus it can be seen as combining fundamental ideas from both syntax-based translation and phrase-based translation. We describe our system's training and decoding methods in detail, and evaluate it for translation speed and translation accuracy. Using BLEU as a metric of translation accuracy, we find that our system performs significantly better than the Alignment Template System, a state-of-the-art phrase-based system.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/0db6eb46ca9941660acc775e3ca39bf4434c18be

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

The CMU Machine Translation Systems at WMT 2014 (2014, methodology): “Our primary German–English and Hindi– English systems were Hiero-based (Chiang, 2007), while our contrastive German–English sys-tem used cdec’s tree-to-tree SCFG formalism.”
Addressing the Rare Word Problem in Neural Machine Translation (2014, background): “For more than a decade, the standard MT approach [14] has been subject to intensive research and resulted in better systems over time [13, 4, 3, 8].”
The QT21/HimL Combined Machine Translation System (2016, background): “The UEDIN-LMU HPBT system is a hierarchical phrase-based machine translation system (Chi-ang, 2005) built jointly by the University of Ed-inburgh and LMU Munich.”
A Systematic Exploration of Diversity in Machine Translation (2013, methodology): “, 2003) and for ZH→EN we used a hierarchical phrase-based model (Chiang, 2007).”
The RWTH Aachen German-English Machine Translation System for WMT 2014 (2014, background): “In hierarchical phrase-based translation (Chiang, 2007), a weighted synchronous context-free grammar is induced from parallel text.”
Encoding Source Language with Convolutional Neural Network for Machine Translation (2015, methodology): “, 2014) is originally tested in the hierarchical phrase-based (Chiang, 2007) SMT and stringto-dependency (Shen et al.”
Iterative parameter mixing for distributed large-margin training of structured predictors for natural language processing (2015, methodology): “Indeed, Chu et al. (2007) do exactly this.”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, background): “Along with phrase-based statistical machine translation, other work has explored hierarchical phrases [65, 66] and more linguistically motivated approaches to syntax-based Example word and statistical machine translation [338] such as mapping between syntactic trees and linear phrase alignments, ada”
The Edinburgh/LMU Hierarchical Machine Translation System for WMT 2016 (2016, methodology): “Hierarchical search is conducted with a customized version of the CYK + parsing algorithm (Chappelier and Rajman, 1998) and cube pruning (Chiang, 2007).”
Why Catalan-Spanish Neural Machine Translation? Analysis, comparison and combination with standard Rule and Phrase-based technologies (2017, methodology): “This corpus-based approach uses deep learning techniques (Kalchbrenner and Blunsom, 2013; Cho et al., 2014; Sutskever et al., 2014) and it may be taking over previous popular corpus-based approaches such as statistical phrase or hierarchical-based (Koehn et al., 2003; Chiang, 2007).”
Syntactically Guided Neural Machine Translation (2016, methodology): “We report on investigations motivated by the idea that the structured search spaces defined by syntactic machine translation approaches such as Hiero (Chiang, 2007) can be used to guide Neural Machine Translation (NMT) (Kalchbrenner and”
Investigating the Usefulness of Generalized Word Representations in SMT (2014, methodology): “…domain features (Hasler et al., 2012), a distortion limit of 6, 100-best translation options, Minimum Bayes Risk decoding (Kumar and Byrne, 2004), Cube Pruning (Huang and Chiang, 2007), with a stack-size of 1000 during tuning and 5000 during test and the no-reordering-over-punctuation heuristic.”
Towards Enhancing Faithfulness for Neural Machine Translation (2020, methodology): “Compared with human translations or traditional statistical machine translation (SMT) (Koehn et al., 2007b; Chiang, 2007), NMT”
Sentence Compression Beyond Word Deletion (2008, methodology): “We adopt a popular approach in syntax-inspired machine translation to address this problem (Chiang, 2007).”
Large-scale Exact Decoding: The IMS-TTT submission to WMT14 (2014, background): “We are aware that this might introduce search errors, and that an integrated language model might improve translation quality (see e.g. Chiang (2007) where 3–4 BLEU points are gained by LM integration).”
Forest Reranking: Discriminative Parsing with Non-Local Features (2008, methodology): “For non-local features, we adapt cube pruning from forest rescoring (Chiang, 2007; Huang and Chiang, 2007), since the situation here is analogous to machine translation decoding with integrated language models: we can view the scores of unit non-local features as the language model cost, computed…”
On the Impact of Various Types of Noise on Neural Machine Translation (2018, methodology): “…based systems as our SMT paradigm, we note that there are other statistical machine translation approaches such as hierarchical phrase-based models (Chiang, 2007) and syntax-based models (Galley et al., 2004, 2006) that may have better performance in certain language pairs and in low resource…”
Edinburgh’s Statistical Machine Translation Systems for WMT16 (2016, methodology): “Decoding for the string-to-tree models is based on Sennrich’s (2014) recursive variant of the CYK+ parsing algorithm combined with LM integration via cube pruning (Chiang, 2007).”
Fast and Robust Neural Network Joint Models for Statistical Machine Translation (2014, result): “Therefore, we also present results using a simpler version of our decoder which emulates Chiang’s original Hiero implementation (Chiang, 2007).”