Last edited by Donris
Friday, May 15, 2020 | History

2 edition of use of deterministic parsers on sublanguage for machine translation. found in the catalog.

use of deterministic parsers on sublanguage for machine translation.

Jacqueline McEwan Archibald

use of deterministic parsers on sublanguage for machine translation.

by Jacqueline McEwan Archibald

  • 28 Want to read
  • 0 Currently reading

Published by Aston University. Department of Computer Science and Applied Mathematics in Birmingham .
Written in English


Edition Notes

Thesis (PhD) - Aston University, 1992.

ID Numbers
Open LibraryOL13907858M

A recursive descent parser is a literal translation of the grammar’s rules straight into imperative code. Each rule becomes a function. , it’s still a valid input to the parser because users use the parser to learn what syntax is allowed. 6. 4 Wiring up the Parser. We are mostly done parsing expressions now. There is one other. Machine Translation: A Brief History Machine Translation: A Brief History W. John Hutchins The translation of natural languages by machine, first dreamt of in the seventeenth century, has become a reality in the late twentieth century. C o m p u t e r pro grams are producing by:

Shun Ha Sylvia Wong and Peter Hancox () An Investigation into the use of Argument Structure and Lexical Mapping Theory for Machine Translation. In: Jin Guo, Kim Teng Lua and Jie Xu eds. Language, Information and Computation: proceedings of the 12th Pacific Asia Conference, Singapore, February Singapore: Chinese and Oriental. the context of syntax-based machine translation itself, Katz-Brown et al. [7] have proposed a method for self-training in the context of syntactic pre-ordering. In this method, which they call targeted self-training, they first generate multiple parse trees using a syntactic parser, then use these trees toCited by: 1.

Unlike most books, it treats (almost) all parsing methods, not just the popular ones. No advanced mathematical knowledge is required; the book is based on an intuitive and engineering-like understanding of the processes involved in parsing, rather than on the set manipulations often used in implementation. The book features the following chapters. MACHINE TRANSLATION Human and Machine T ranslation each have their share of challenges. For example, n o two individual translators will produce identical translations of the same text in the same language pair, and it may take several roun ds of revisions File Size: KB.


Share this book
You might also like
Les Poissons

Les Poissons

artic imperative

artic imperative

The tarot for common folk

The tarot for common folk

A call to conscience

A call to conscience

IT/IS audit in banks in India

IT/IS audit in banks in India

Freedom of information reform in China

Freedom of information reform in China

The bone hook

The bone hook

Coast Guard miscellaneous legislation

Coast Guard miscellaneous legislation

Movement of herbicides in soil by mass flow

Movement of herbicides in soil by mass flow

Escape and fantasy

Escape and fantasy

Communication with and without words

Communication with and without words

Tokyo family.

Tokyo family.

microcomputer-based system for studies of the oesophageal functions.

microcomputer-based system for studies of the oesophageal functions.

continuity of the Church of England

continuity of the Church of England

private life of Marie Antoinette, queen of France and Navarre

private life of Marie Antoinette, queen of France and Navarre

civil, ecclesiastical, literary, commercial, and miscellaneous history of Leeds, Bradford, Wakefield, Dewsbury, Otley, and the district within ten miles of Leeds

civil, ecclesiastical, literary, commercial, and miscellaneous history of Leeds, Bradford, Wakefield, Dewsbury, Otley, and the district within ten miles of Leeds

Parasites of marine mammals

Parasites of marine mammals

Hearing on regulation of private employment agencies, Sacramento, California, September 28, 1977

Hearing on regulation of private employment agencies, Sacramento, California, September 28, 1977

Use of deterministic parsers on sublanguage for machine translation by Jacqueline McEwan Archibald Download PDF EPUB FB2

The present work reports Deterministic Parsing, a relatively new parsing technique, and its application to the sublanguage of an aircraft maintenance manual for Machine Translation. The aim has been to investigate the practicability of using Deterministic Parsers in the analysis stage of a Machine Translation : Jacqueline M.

Archibald. While it would be desirable to use syntactic parsers to distinguish between well-formed and ill-formed translation hypotheses, in past research on using parsers as language models, parser scores Author: Daniel Gildea. The book addresses all of these trade-offs, but doesn't stop at asymptotic complexity: in chapter 17 (the comparative survey), they note that general parsers may be a factor of ten or so slower than deterministic methods, even though both are by: sublanguage approach to machine translation (MT).

Before any sublanguage analysis can proceed, compilation of a corpus is necessary. To date, attention has been focussed on the criteria for compiling general language corpora. Chapter 2 addresses the problems of compiling corpora for sublanguage.

It has been proposed by a number of authors (cf. KittredgeKittredge/LehrbergerLuckhardt ) to use the sublanguage notion for solving some of the notorious problems in machine translation (MT) and natural language processing (NLP) in general, such as disambiguation and selection of target language equivalents.

Machine Translation (MT) is the use of computers in translating text from one natural language to another. This paper begins by an overview of the current research in machine translation (MT). Then, it presents a multi-level transformation approach to machine translation and the evaluation of the current research in MTFile Size: KB.

has been the ever expanding use of unrevised MT output, such as online translation services (Babel Fish, Google, etc.), applications in information extraction, document retrieval, intelligence analysis, electronic mail, and much more.

Traditional uses Machine translation (MT) has a long history – it is. 2 MACHINE TRANSLATION use them for the purposes of translation. For we must guard on the one hand against the cult of cybernetics and of the electronic brain, and on the other against the complacency shown by those who, hearing of Russian or American advances in the field, imagine that all will be well if they let the engineers of these great.

The Use of Lexical Semantics in Interlingual Machine Translation Book Reviews James Steele (ed.), Meaning-text Theory: Linguistics, Lexicography, and Implications (Neil Green) The use of a deterministic parser to produce grammatical structures and an expert system to analyse them and produce an object model is proposed.

This invention relates to a means and a method for translating source text into a target text where the context information is taken into consideration. A source text unit is defined around a translation unit which is to be translated.

This source text unit is mapped onto a bilingual sublanguage space where the bilingual sublanguage space comprises a source sublanguage space and mappings to Cited by:   Machine Translation Wednesday, August 1, Fidditch, a deterministic parser developed by Donald Hindle first at the University of Pennsylvania and subsequently at AT&T Bell Labs (Hindle), is used to provide an initial parse of 11 This use of pseudo-attachment is identical to its original use in Church's parser (Church ).

Statistical Machine Translation by Parsing I. Dan Melamed Computer Science Department New York University New York, NY, U.S.A. lastname @ Abstract In an ordinary syntactic parser, the input is a string, and the grammar ranges over strings.

This paper explores generalizations of ordinary parsing algo. An Interactive Japanese Parser for Machine Translation Hiroshi Maruyama [email protected] Hideo Watanabe wat [email protected] Shiho Ogino IBM Research, Tokyo h Laboratory Sanbancho, Chiyod~-ku, Tokyo Japan Abstract fin this paper, we describe a working system for.

Machine Translation assumes no previous knowledge of the field and provides the basic background information to the linguistic and computational foundations of the subject. It is an invaluable text for students of computational linguistics, artificial intelligence, natural language processing, and information science.

Statistical, Example based, and Rule-based Machine Translation (SMT, EBMT, and RBMT respectively) are used. • 23% of internet users, have used the machine translation and 40 % considering doing so • 30% the professionals have used the machine translation and 18% perform a proofreading.

Lavie and M. Denkowski. The Meteor metric for automatic evaluation of machine translation. Machine Translation, 23(). Google Scholar Digital Library; P.

Liang, A. Bouchard-Côté, D. Klein, and B. Taskar. An end-to-end discriminative approach to machine translation. In ACL ' Google Scholar Digital Library. Comparative Evaluation of Online Machine Translation Systems with Legal Texts* Chunyu Kit** and Tak Ming Wong*** The authors discuss both the proper use of available online machine transla-tion (MT) technologies for law library users and their comparative evalua-tion of the performance of a number of representative online MT systems inFile Size: KB.

Baseline Machine Translation systems The extensions and evaluations we describe below start from three baseline systems: The phrase-based SMT baseline is a domain-enhanced version of several state-of-the-art phrase-based systems, as indicated in the Shared task of Machine Translation File Size: KB.

Text Input. This is the first phase in the machine translation process and is the first module in any MT system. The sentence categories can be classified based on the degree of difficulty of translation.

Sentences that have relations, expectations, assumptions, and conditions make the MT system understand very difficult. Context sensitive parsers Deterministic Recursive descent semantic net parsers Enforce word-based case frame constraints Chapter Contents Natural Language Understanding in Prolog Prolog-Based Semantic Representations A Context-Free Parser in Prolog Probabilistic Parsers in Prolog A Context-Sensitive Parser in Prolog.Machine Translation WiSe / Example-Based Machine Translation Dr.

Mariana Neves January 23th, File Size: 2MB.a general parser (Link Parser) to sublanguages, focusing on the parsing of texts in biology. Our main proposal is the use of terminology (iden-ti cation and analysis of terms) in order to re-duce the complexity of the text to be parsed.

Several other strategies are explored and nally combined among which text normalization, lex.