A Statistical Approach to Machine Translation

By Peter F. Brown, John Cocke, Stephen Della Pietra, V. D. Pietra, Frederick Jelinek, John D. Lafferty, Robert L. Mercer, Paul S. Roossin. 1990

Subfields: 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 Natural Language Processing

Citations in the corpus

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016, background): “Neural Machine Translation (NMT) [41, 2] has recently been introduced as a promising approach with the potential of addressing many shortcomings of traditional machine translation systems.”
LLaMA: Open and Efficient Foundation Language Models (2023, background): “This task, often framed as next token prediction, has long been considered a core problem in natural language processing (Bahl et al., 1983; Brown et al., 1990).”
Improving Neural Machine Translation Models with Monolingual Data (2015, methodology): “…Electronics Polska sp. z o.o. - Samsung R&D Institute Poland. cal machine translation, and we investigate the use of monolingual data for NMT. Language models trained on monolingual data have played a central role in statistical machine translation since the ﬁrst IBM models (Brown et al., 1990).”
Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “Some parallel corpora can be found “naturally” as the byproduct of an organization’s deliberate effort to disseminate information in multiple languages, for example, proceedings of the Canadian Parliament in French and English [Brown et al., 1990], and text produced by the United Nations in many dif”
A bit of progress in language modeling (2001, background): “This is useful in a large variety of areas including speech recognition, optical character recognition, handwriting recognition, machine translation, and spelling correction (Church, 1988; Brown et al., 1990; Hull, 1992; Kernighan et al., 1990; Srihari and Baltus, 1992).”
Style Transfer from Non-Parallel Text by Cross-Alignment (2017, background): “Word order recovery Our final experiments focus on the word ordering task, also known as bag translation (Brown et al., 1990; Schmaltz et al., 2016).”
Continual Learning for Neural Machine Translation (2021, background): “Early machine translation systems are mostly built upon statistical learning techniques, which mainly rely on various count-based features (Brown et al., 1990; Och, 2003; Koehn et al., 2007).”
Unsupervised Statistical Machine Translation (2018, background): “While originally motivated as a noisy channel model (Brown et al., 1990), phrase-based SMT is now formulated as a log-linear combination of several statistical models that score translation candidates (Koehn et al.”
Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language (2014, methodology): “The generation system, W ASP − 1 , uses a noisy-channel model (Brown et al., 1990): Where e refers to the NL string generated for a given input MR, f .”
Empirical Methods for Compound Splitting (2003, methodology): “First, we measured the impact on a word based statistical machine translation system, the widely studied IBM Model 4 [Brown et al., 1990], for which training tools [Al-Onaizan et al., 1999] and decoders [Germann et al., 2001] are freely available.”
Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods (2010, methodology): “Finally, an even more direct method to align equivalences in parallel sentence pairs can be effected by building on word alignment techniques from the field of statistical machine translation (Brown et al. 1990).”
Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods (2019, background): “It is been influenced from the well known NLP challenge of automatic translation between two languages (Brown et al., 1990; Bahdanau et al., 2014).”
Language modeling for soft keyboards (2002, methodology): “Besides speech recognition, language models are also used in many other areas, including handwriting recognition (Srihari and Baltus, 1992), machine translation (Brown et al. 1990), and spelling correction (Golding and Schabes, 1996).”
A Maximum Entropy Approach to Natural Language Processing (1996, unknown): “It includes a six-word window of French words: three to the left of yj and three to the right of yj. It also includes the part-of-speech tags for these words, and the classes of these words as derived from a mutual-information clustering scheme described in Brown et al. (1990) .”