Elamur Research⌕
☰
home / papers / 2002 / Book Reviews: Early Years in Machine Translation: Memoirs and Biographies of Pioneers edited by W. John Hutchins, Reviewed by Warren J. Plath; Patterns of Text: In Honour of Michael Hoey edited by Mike Scott and Geoff Thompson, Reviewed by Graeme Hirst; Word Frequency Distributions by R. Harald Baayen, Reviewed by Geoffrey Sampson; Data-Driven Techniques in Speech Synthesis edited by R. I. Damper, Reviewed by Thierry Dutoit; Empirical Linguistics by Geoffrey Sampson, Reviewed by Steven Abney; Computational Nonlinear Morphology with Emphasis on Semitic Languages by George Anton Kiraz, Reviewed by Markus Walther

Book Reviews: Early Years in Machine Translation: Memoirs and Biographies of Pioneers edited by W. John Hutchins, Reviewed by Warren J. Plath; Patterns of Text: In Honour of Michael Hoey edited by Mike Scott and Geoff Thompson, Reviewed by Graeme Hirst; Word Frequency Distributions by R. Harald Baayen, Reviewed by Geoffrey Sampson; Data-Driven Techniques in Speech Synthesis edited by R. I. Damper, Reviewed by Thierry Dutoit; Empirical Linguistics by Geoffrey Sampson, Reviewed by Steven Abney; Computational Nonlinear Morphology with Emphasis on Semitic Languages by George Anton Kiraz, Reviewed by Markus Walther

Paper · 2002

Summary

This item is a 2002 batch of six book reviews from Computational Linguistics. Only two reviews survive in the extracted text. Warren J. Plath reviews W. John Hutchins's edited volume Early Years in Machine Translation, a collection of memoirs and biographies of MT pioneers from the 1950s and 1960s. He walks through its geographically grouped chapters and praises the editor's introduction, which gives an overview, a chronology and sources. He also flags the contributors' sharply conflicting accounts of the same projects and events. Markus Walther reviews George Anton Kiraz's book on computational approaches to nonlinear morphology, which focuses mainly on the Semitic languages and proposes a multitape finite-state formalism for root-and-pattern morphology. Walther questions both its linguistic motivation and its claimed efficiency advantages. He argues that intersection-based alternatives can be extended to keep the same benefits, and that newer compilation techniques remove the speed argument. He still recommends the book because its formalism is described in enough detail to implement. The other four reviews (Baayen, Scott & Thompson, Damper, Sampson) are outside the visible text.

Key points

  • The Hutchins volume. Published by John Benjamins in 2000 (xii+400 pp, $95). It collects about 26 contributors, with sections on the US, the Soviet Union, the UK, Western and Eastern Europe, and Japan.
  • Recurring milestones. Weaver's 1949 memorandum and the 1966 ALPAC report appear throughout. Soviet authors disagree about whether ALPAC actually ended funding in the USSR.
  • Systems the memoirs describe:
    • Georgetown's GAT-SLC, which paired a linguistic component with a computational one.
    • Yngve's COMIT language and his depth hypothesis.
    • Kulagina's FR-I and its dependency-tree successor FR-II.
    • Toma's SYSTRAN, described as MT's first commercial success.
  • Walther's efficiency counterpoint. Beesley and Karttunen (2000) introduced a compile-replace operator that cut compile time for a large Arabic morphology from hours to minutes, without needing a multitier model.
  • Walther's further criticisms of Kiraz:
    • Kiraz leaves out the empirical evaluation from his own 2000 paper.
    • Kiraz's own system is a hybrid of several composed stages, which raises the question of whether the multitape formalism alone is expressive enough.

Interesting ideas

  • I1. Walther suggests labelling each automaton transition with a pair (segment, origin), where origin sets are unioned so the analysis records whether each segment came from the root, the vowel pattern or an affix. This keeps analysis reversible without extra tapes.
  • I2. Instead of positing abstract underlying stems (such as Syriac *katab), Walther restates the fricativization rule as a surface-true prosodic condition (after noncoda segments). This avoids hidden intermediate forms.
  • I3. Walther notes that compile-time speed claims are fragile because hardware keeps getting faster, while run-time behaviour is the real selling point. Such claims should be backed by included empirical measurements.
  • I4. The memoir collection shows eyewitnesses giving contradictory versions of the same events: Georgetown described as harmonious versus as "armed camps", and ALPAC's Soviet impact asserted versus denied.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (tokens): the morphology/lemma module could tag every character span with its source morpheme, so each lemma decision carries its own explanation.
  • I2 (tokens): morphological rules should be stated over observable surface contexts where possible, which keeps them checkable against corpus forms.
  • I3 (learn): evaluation reports should measure run-time parsing and answering costs and publish the numbers, rather than arguing from build-time efficiency.
  • I4 (world): the world model should store conflicting claims attributed to their speakers, rather than merging them into one fact. This supports questions like "who says what happened".

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 works

🧭 Topics 4Research subjects and languages the work is about.Machine translation · 1,087 worksSemitic languages · 2,908 worksSpeech & spoken language · 480 worksMorphology · 405 works

Cite

Cite as 2002. Book Reviews: Early Years in Machine Translation: Memoirs and Biographies of Pioneers edited by W. John Hutchins, Reviewed by Warren J. Plath; Patterns of Text: In Honour of Michael Hoey edited by Mike Scott and Geoff Thompson, Reviewed by Graeme Hirst; Word Frequency Distributions by R. Harald Baayen, Reviewed by Geoffrey Sampson; Data-Driven Techniques in Speech Synthesis edited by R. I. Damper, Reviewed by Thierry Dutoit; Empirical Linguistics by Geoffrey Sampson, Reviewed by Steven Abney; Computational Nonlinear Morphology with Emphasis on Semitic Languages by George Anton Kiraz, Reviewed by Markus Walther. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work.

@article{anon2002book,
  title = {{Book Reviews: Early Years in Machine Translation: Memoirs and Biographies of Pioneers edited by W. John Hutchins, Reviewed by Warren J. Plath; Patterns of Text: In Honour of Michael Hoey edited by Mike Scott and Geoff Thompson, Reviewed by Graeme Hirst; Word Frequency Distributions by R. Harald Baayen, Reviewed by Geoffrey Sampson; Data-Driven Techniques in Speech Synthesis edited by R. I. Damper, Reviewed by Thierry Dutoit; Empirical Linguistics by Geoffrey Sampson, Reviewed by Steven Abney; Computational Nonlinear Morphology with Emphasis on Semitic Languages by George Anton Kiraz, Reviewed by Markus Walther}},
  journal = {Computational Linguistics},
  year = {2002},
  url = {https://aclanthology.org/J02-4008/}
}

References

27 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Barzilay, Regina and Michael Elhadad. 1999. Using lexical chains for text summarization. In Inderjeet Mani and Mark T. Maybury, editors, Advances in Automatic Text Summarization. MIT Press, pages 111–121.
  2. Byrd, Roy and Yael Ravin. 1999. Identifying and extracting relations in text. In Proceedings of the Fourth International Conference on Applications of Natural Language to Information Systems (NLDB-99), Klagenfurt, Austria. find
  3. Caraballo, Sharon A. 1999. Automatic construction of a hypernym-labeled noun hierarchy from text. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, pages 120–126, College Park, MD.
  4. Cooper, Alan. 1999. The Inmates Are Running the Asylum: Why High-Tech Products Drive Us Crazy and How to Restore the Sanity. Sams Publishing, Indianapolis. find
  5. Halliday, M. A. K. 1994. An Introduction to Functional Grammar. Arnold, London, second edition. find
  6. Halliday, M. A. K. and Ruqaiya Hasan. 1976. Cohesion in English. Longman. find
  7. Hearst, Marti A. 1992. Automatic acquisition of hyponyms from large text corpora. In Proceedings of the 14th International Conference on Computational Linguistics (COLING-92), pages 539–545. Nantes, France.
  8. Hearst, Marti A. 1997. TextTiling: Segmenting text into multi-paragraph subtopic passages. Computational Linguistics, 23(1):33–64. find
  9. Hearst, Marti A. 1998. Automated discovery of WordNet relations. In Christiane Fellbaum, editor, WordNet: An Electronic Lexical Database. MIT Press, pages 131– 151. ↗
  10. Hoey, Michael. 1983. On the Surface of Discourse. Allen and Unwin, London. find
  11. Hoey, Michael. 1991. Patterns of Lexis in Text. Oxford University Press. find
  12. Hoey, Michael. 1993. Data, Description, Discourse: Papers on the English Language in Honour of John McH Sinclair. HarperCollins, London. find
  13. Hoey, Michael. 2001. Textual Interaction: An Introduction to Written Discourse Analysis. Routledge, London. find
  14. Hunston, Susan and Gill Francis. 2000. Pattern Grammar: A Corpus-Driven Approach to the Lexical Grammar of English. John Benjamins, Amsterdam. find
  15. Johnson, Christopher. 2001. Review of Susan Hunston and Gill Francis, Pattern Grammar: A Corpus-Driven Approach to the Lexical Grammar of English. Computational Linguistics, 27(2):318–320. find
  16. Johnson, Jeff. 2000. GUI Bloopers: Don’ts and Do’s for Software Developers and Web Designers. Morgan Kaufmann, San Francisco. find
  17. Levin, Beth. 1993. English Verb Classes and Alternations: A Preliminary Investigation. University of Chicago Press. find
  18. Maedche, Alexander and Steffan Staab. 2000. Semi-automatic engineering of ontologies from text. In Proceedings of the 12th International Conference on Software Engineering and Knowledge Engineering (SEKE 2000), Chicago, pages 231–239. find
  19. Mann, William C. and Sandra Thompson. 1988. Rhetorical structure theory: Toward a functional theory of text organization. Text, 8(3):243–281. ↗
  20. Marcu, Daniel. 2000. The Theory and Practice of Discourse Parsing and Summarization. MIT Press, Cambridge. ↗
  21. Morin, Emmanuel and Christian Jacquemin. 1999. Projecting corpus-based semantic links on a thesaurus. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, pages 389–396, College Park, MD. Graeme Hirst is book review editor of Computational Linguistics. His research topics include the problem of near synonymy in lexical choice and the use of lexical relations in intelligent spelling correction. Hirst’s address is Department of Computer Science, University of Toronto, Toronto, Ontario, Canada M5S 3G4; e-mail: gh@cs.toronto.edu; URL: http://www.cs.toronto.edu/∼gh. ↗
  22. Morris, Jane and Graeme Hirst. 1991. Lexical cohesion, the thesaurus, and the structure of text. Computational Linguistics, 17(1):21–48. find
  23. Sinclair, John M, editor-in-chief. 1987. Collins COBUILD English Language Dictionary. Collins, London. find
  24. Sinclair, John M., Michael Hoey, and Gwyneth Fox. 1993. Techniques of Description: Spoken and Written Discourse: A Festschrift for Malcolm Coulthard. Routledge, London. ↗
  25. Thelen, Michael and Ellen Riloff. 2002. A bootstrapping method for learning semantic lexicons using extraction pattern contexts. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002), Philadelphia, pages 214–221.
  26. Winter, Eugene. 1982. Towards a Contextual Grammar of English: The Clause and Its Place in the Definition of Sentence. Allen and Unwin, London. Word Frequency Distributions R. Harald Baayen (University of Nijmegen) find
  27. Dordrecht: Kluwer Academic Publishers (Text, speech and language technology series, edited by Nancy Ide and Jean Véronis, volume 18), 2001, xxii+333 pp and CD-ROM; hardbound, ISBN 0-7923-7017-1, $108.00, – C 117.00, £74.00; paperwork, ISBN 1-4020-0927-5, $48.00, – C 48.00, £30.00 Reviewed by Geoffrey Sampson University of Sussex find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/anon-2002-book-reviews-early-years-machine/