Parallel Text Processing

Alignment and Use of Translation Corpora

 

Edited by

Jean Véronis

 

Université de Provence,

Aix-en-Provence, France

 

Contents

Foreword.................................................................................................. xi

Terminological note................................................................................. xiii

Preface by Martin Kay............................................................................ XV

Contributors............................................................................................ xxi

Introduction

1.   From the Rosetta stone to the information society.......................... 1 [abstract]

A survey of parallel text processing

Jean Véronis

Alignment Methodology

2.   Pattern recognition for mapping bitext correspondence................ 25 [abstract]

I. Dan Melamed

3.   Multilingual text alignment........................................................... 49 [abstract]

Aligning three or more versions of a text

Michel Simard


4.   A comprehensive bilingual word alignment system...................... 69 [abstract]

Application to disparate languages: Hebrew and English

Yaacov Choueka, Ehud S. Conley and Ido Dagan

5.   A knowledge-lite approach to word alignment............................. 97 [abstract]

Lars Ahrenberg, Mikael Andersson and Magnus Merkel

6.   From sentences to words and clauses......................................... 117 [abstract]

Stelios Piperidis, Harris Papageorgiou and Sotiris Boutsis

7.   Bracketing and aligning words and constituents in parallel text using

Stochastic Inversion Transduction Grammars............................ 139 [abstract]

Dekai Wu

8.   The translation network.............................................................. 169 [abstract]

A model for a fine-grained description of translations

Diana Santos

9.   Parallel text alignment using crosslingual information retrieval

techniques.................................................................................. 187 [abstract]

Christian Fluhr, Frédérique Bisson and Faïza Elkateb

10. Parallel alignment of structured documents................................ 201 [abstract]

Laurent Romary and Patrice Bonhomme

APPLICATIONS

1 1. A statistical view on bilingual lexicon extraction...................... 219 [abstract]

From parallel corpora to non-parallel corpora
Pascale Fung

12. Terminology extraction from parallel technical texts.................. 237 [abstract]

Ingeborg Blank

13. Term alignment in use................................................................ 253 [abstract]

Machine-aided human translation

Éric Gaussier, David Hull and Salah Aït-Mokhtar

14. Automatic dictionary extraction for cross-language information

retrieval...................................................................................... 275 [abstract]

Ralf D. Brown, Jaime G. Carbonell and Yiming Yang


15.                                                                                                     Parallel texts in computer-assisted language learning............................................................................................. 299 [abstract]

John Nerbonne

RESOURCES AND EVALUATION

16.                                                                                                     Japanese-English aligned bilingual corpora  313 [abstract]

Hitoshi Isahara and Masahiko Haruno

17.                                                                                                     Building a parallel corpus of English/Panjabi     335 [abstract]

Sukhdave Singh, Tony McEnery and Paul Baker

18. Sharing of translation memory databases derived from aligned

parallel text................................................................................. 347 [abstract]

Alan K. Melby

19.                                                                                                     Evaluation of parallel text alignment systems     369 [abstract]

The ARCADE project

Jean Véronis and Philippe Langlais

Index of terms........................................................................................ 389

Index of authors..................................................................................... 395

Index of languages and writing systems................................................. 401