Phrase-based statistical machine translation

By Ulrich Germann. 2007

253 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Continual Few-Shot Learning for Text Classification (2021, background): “…a translation system makes a harmful mistake (e.g., translates “EMNLP” to “ICML”), a phrase-based system can be corrected by ﬁnding and modifying the responsible entries in the phrase table (Zens et al., 2002), whereas there is no equivalent way to correct that in an end-to-end neural MT system.”
LIMSI @ WMT’14 Medical Translation Task (2014, methodology): “2 System Overview 2.1 N CODE N CODE implements the bilingual n -gram approach to SMT (Casacuberta and Vidal, 2004; Mari˜no et al., 2006; Crego and Mari˜no, 2006) that is closely related to the standard phrase-based approach (Zens et al., 2002).”
Continuous Space Translation Models with Neural Networks (2012, methodology): “This may seem to be a step backwards, since the transition from word (Brown et al., 1993) to phrase-based models (Zens et al., 2002) is considered as one of the main recent improvement in MT.”
Towards Automatic Error Analysis of Machine Translation Output (2011, unknown): “Zhou et al. (2008) propose a diagnostic evaluation of linguistic check-points obtained automatically by aligning parsed source and target sentences.”
Story Generation from Sequence of Independent Short Descriptions (2017, background): “Unlike phrase Based [39] and syntax based [19] smt which translate words and phrases independently within a sentence, seq2seq considers entire sentence as a unit to be translated.”
LIMSI@WMT’16: Machine Translation of News (2016, methodology): “N CODE implements the bilingual n-gram approach to SMT (Casacuberta and Vidal, 2004; Crego and Mari˜no, 2006b; Mari˜no et al., 2006) that is closely related to the standard phrase-based approach (Zens et al., 2002).”
Towards Making the Most of ChatGPT for Machine Translation (2023, methodology): “For more CoT variants designed with different principles inspired by the philosophy in statistical MT (Zens et al., 2002; Koehn, 2009) will be explored in the future.”
The QT21/HimL Combined Machine Translation System (2016, methodology): “5 Each word in the reference that is assigned a POS tag of interest (noun, pronoun, adjective, determiner, or verb) is then compared to the word it is aligned to in the system output.”