The Alignment Template Approach to Statistical Machine Translation

By Franz Joseph Och, Hermann Ney. International Conference on Computational Logic, 2004

1,060 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/c6a83c4fcc99ba6753109301949c5b7cfa978079

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 Molecular Biology

Citations in the corpus

Outside the Closed World: On Using Machine Learning for Network Intrusion Detection (2010, methodology): “Examples from other domains include product recommendations systems such as used by Amazon [3] and Netﬂix [4]; optical character recognition systems (e.g., [5], [6]); natural language translation [7]; and also spam detection, as an example closer to home [8].”
Model With Minimal Translation Units, But Decode With Phrases (2013, background): “Phrase-based SMT segments a bilingual sentence pair into phrases that are continuous sequences of words (Och and Ney, 2004; Koehn et al., 2003) or discontinuous sequences of words (Galley and Manning, 2010).”
Semantic Parsing via Paraphrasing (2014, methodology): “We use the word alignments to construct a phrase table by applying the consistent phrase pair heuristic (Och and Ney, 2004) to all 5-grams.”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, background): “In the 2000s, phrasebased approaches [185, 262] have proved very successful and became widely used [227].”
Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search (2017, background): “However, greedy selection of the most probable output at each timestep, i.e.:”
Building a Semantic Parser Overnight (2015, methodology): “We also use the word alignments to construct a phrase table by applying the consistent phrase pair heuristic (Och and Ney, 2004).”
A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages (2010, methodology): “The core translation structure of a phrase-based SMT model is the phrase table, which is learned from a bilingual parallel sentence-aligned corpus, typically using the alignment template approach (Och and Ney, 2004).”
Tuning as Ranking (2011, background): “…scenario; as implied in the synthetic data experiment of Section 3, the algorithm makes poor choices for its weights and this leads to low-quality k-best lists and dismal performance, near 0 BLEU in every iteration. phrase-based system (hereafter, PBMT) follows the model of Och and Ney (2004).”
Learning Continuous Phrase Representations for Translation Modeling (2014, background): “Since computing the argmax exactly is intractable, it is commonly performed approximatedly by beam search (Och and Ney 2004).”
Tree-to-String Alignment Template for Statistical Machine Translation (2006, methodology): “To extract tree-to-string alignment templates from a word-aligned, source side parsed sentence pair T ( f J 1 ) , e I 1 , A i , we need ﬁrst identify TSA s (Tree-String-Alignment) using similar criterion as suggested in (Och and Ney, 2004).”
Phrasal: A Toolkit for New Directions in Statistical Machine Translation (2014, methodology): “The standard multi-stack beam search (Och and Ney, 2004) is also an option.”
Can Markov Models Over Minimal Translation Units Help Phrase-Based SMT? (2013, background): “Phrase-based models (Koehn et al., 2003; Och and Ney, 2004) learn local dependencies such as reorderings, idiomatic collocations, deletions and insertions by memorization.”