An introduction to machine translation

By W. J. Hutchins, H. Somers. 1992

How researchers see this paper

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

In Machine Translation

Citations in the corpus

Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation (2016, methodology): “Our approach has been shown to work reliably in a Google-scale production setting and enables us to scale to a large number of languages quickly.”
Review of "Mining the Web: discovering knowledge from hypertext data" by Soumen Chakrabati. Morgan Kaufman 2003. (2002, unknown): “NL techniques can now parse relatively well-formed sentences in many languages [91, 210, 79, 200], disambiguate words with multiple senses with high accuracy [4, 181, 32], tag words in running text with part-of-speech information [4, 85], represent NL documents in a canonical machine-usable form [19”
Cross-view action recognition via view knowledge transfer (2011, methodology): “two articles belong to a same category, we must either translate one of them to the other language or translate both of them into an interlingua, as is used in machine translation [14].”
Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals (2020, methodology): “In line with these advances, the ﬁ eld of MT has shifted to the use of deep-learning neural-based methods 8 – 11 , which replaced previous approaches, such as rule-based systems 12 or statistical phrase-based methods 13,14 .”
Survey on reinforcement learning for language processing (2021, methodology): “Machine translation (MT) consists in automatically translating sentences from one natural language to another one, using a computing device [51].”
Enabling technology for multilingual natural language generation: the KPML development environment (1997, unknown): “This avoids the problem noted for interlin-gua in Machine Translation (cf., e.g., Hutchins and Somers (1992, p120)) of having to select a ‘neutral’ form: the selection of ‘zeks’ above as the neutral form might be argued diachronically, but this is not an ideal situation when engineering large-scale…”
Apertium: a free/open-source platform for rule-based machine translation (2011, background): “On the one hand, rule-based MT (RBMT) depends on explicit linguistic data such as morphological dictionaries, bilingual dictionaries, grammars, and structural transfer rules (see Hutchins and Somers 1992, Chap.”
Discovering word senses from text (2002, background): “INTRODUCTION Using word senses versus word forms is useful in many applications such as information retrieval [20], machine translation [5] and question-answering [16].”
The UA-Prompsit hybrid machine translation system for the 2014 Workshop on Statistical Machine Translation (2014, methodology): “The RBMT process can be split into three different steps (Hutchins and Somers, 1992): (i) analysis of the SL text to build an SL intermediate represen- tation; (ii) transfer from that SL intermediate representation into a TL intermediate representation; and (iii) generation of the final translation…”
Data mining for hypertext: a tutorial survey (2000, background): “NL techniques can now parse relatively well-formed sentences in many languages [36, 71, 28, 68], disambiguate polysemous words with high accuracy [3, 62, 11], tag words in running text with part-of-speech information [3, 32], represent NL documents in a canonical machine-usable form [67, 40, 65], an”
MT on and for the Web (2010, background): “We start with 1994, because it is the first time MT appeared on the Internet, and because the prior period has largely been covered elsewhere: see in particular [6, 10, 11].”