A Hierarchical Phrase-Based Model for Statistical Machine Translation

By David Chiang. 2005

1,315 citations recorded by the source corpus.

We present a statistical phrase-based translation model that uses hierarchical phrases---phrases that contain subphrases. The model is formally a synchronous context-free grammar but is learned from a bitext without any syntactic information. Thus it can be seen as a shift to the formal machinery of syntax-based translation systems without any linguistic commitment. In our experiments using BLEU as a metric, the hierarchical phrase-based model achieves a relative improvement of 7.5% over Pharaoh, a state-of-the-art phrase-based system.

Subfields: Artificial Intelligence, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

A Call for Clarity in Reporting BLEU Scores (2018, methodology): “.pl 8This paper’s observations stem in part from an early version of a research workﬂow I was using, which applied preprocessing to the reference, affecting scores by half a point. paper conﬁguration Chiang (2005) metric lc Bahdanau et al. (2014) (unclear) Luong et al. (2015b) user or metric (unclea”
On Using Monolingual Corpora in Neural Machine Translation (2015, methodology): “In addition to NMT-based systems, we also trained a phrase-based as well as hierarchical phrasebased SMT systems (Koehn et al., 2003; Chiang, 2005) with/without re-scoring by an external neural language model (CSLM, Schwenk, 2007b).”
Minimum Risk Training for Neural Machine Translation (2015, background): “…sentence to a target-language sentence without explicitly modeling latent structures (e.g., word alignment, phrase segmentation, phrase re-ordering, and SCFG derivation) that are vital in conventional statistical machine translation (SMT) (Brown et al., 1993; Koehn et al., 2003; Chiang, 2005).”
Learning for Semantic Parsing with Statistical Machine Translation (2006, methodology): “…target MRL. Complete MRs are then formed by combining these NL substrings and their translations under a parsing framework called the synchronous CFG (Aho and Ullman, 1972), which forms the basis of most existing statistical syntax-based translation models (Yamada and Knight, 2001; Chiang, 2005).”
Semi-Supervised Learning for Neural Machine Translation (2016, background): “We compared our approach with two state-of-the-art SMT and NMT systems: 1.”
Good-Enough Compositional Data Augmentation (2019, background): “A large body of work in natural language processing provides generalization to data like (2a) by adding structure to the learned predictor (Chelba and Jelinek, 1998; Chiang, 2005; Dyer et al., 2016).”
Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language (2014, methodology): “W ASP (Word-Alignment-based Semantic Parsing) (Wong & Mooney, 2006) uses state-of-the-art statistical machine translation (SMT) techniques (Brown, Cocke, Della Pietra, Della Pietra, Jelinek, Lafferty, Mercer, & Roossin, 1990; Yamada & Knight, 2001; Chiang, 2005) to learn semantic parsers.”
Insertion-based Decoding with Automatically Inferred Generation Order (2019, background): “Another line of work models sequence generation based on syntax structures (Yamada and Knight, 2001; Charniak et al., 2003; Chiang, 2005; Emami and Jelinek, 2005; Zhang et al., 2016; Dyer et al., 2016; Aharoni and Goldberg, 2017; Wang et al., 2018b; Eriguchi et al., 2017).”
11,001 New Features for Statistical Machine Translation (2009, background): “Hiero (Chiang, 2005) is a hierarchical, string-to-string translation system.”
Visualizing and Understanding Neural Machine Translation (2017, background): “In SMT (Koehn et al., 2003; Chiang, 2005), the translation process can be denoted as a derivation that comprises a sequence of translation rules (e.g., phrase pairs and synchronous CFG rules).”
Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes (2015, neutral): “WASP casts semantic parsing as a syntax-based statistical machine translation (SMT) task, where a synchronous context-free grammar (SCFG) (Wu, 1997; Chiang, 2005; Galley et al., 2006) is used to model the translation of natural language into a formal meaning representation.”
Abu-MaTran at WMT 2015 Translation Task: Morphological Segmentation and Web Crawling (2015, methodology): “…trained on word forms or morphs as described in Section 3, Factored Models (Koehn and Hoang, 2007) including morphological and sufﬁx information as provided by OMORFI , 11 in addition to surface forms, and ﬁnally hierarchical phrase-based SMT (Chiang, 2005) as an unsupervised tree-based model.”
Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus (2007, methodology): “Like most existing work on syntax-based SMT (Chiang, 2005; Galley et al., 2006), we construct G using rules extracted from word alignments.”
Combining Word Reordering Methods on different Linguistic Abstraction Levels for Statistical Machine Translation (2013, background): “Hierarchical MT systems (Chiang, 2005) construct a syntactic hierarchy during decoding, which is independent of linguistic categories.”
English-to-Czech Factored Machine Translation (2007, background): “…experiments, structured language models (Chelba and Jelinek, 1998) might be considered to improve clause coherence, until full-featured syntax-based MT models (Yamada and Knight (2002), Eisner (2003), Chiang (2005) among many others) are tested when translating to morphologically rich languages.”
Deep Neural Machine Translation with Linear Associative Unit (2017, background): “Unlike conventional Statistical Machine Translation (SMT) systems (Koehn et al., 2003; Chiang, 2005; Liu et al., 2006; Xiong et al., 2006; Mi et al., 2008) which consist of multiple separately tuned components, NMT aims at building upon a single and large neural network to directly map input text to”
A Simple and Effective Hierarchical Phrase Reordering Model (2008, background): “Coming from the other direction, such observations about phrase reordering between different languages are precisely the kinds of facts that parsing approaches to machine translation are designed to handle and do successfully handle (Wu, 1997; Melamed, 2003; Chiang, 2005).”