Machine Translation without a source text

What it is about

The authors propose an MT system that works without a prepared source text. A monolingual writer begins with a rough sketch of what they want to say, and the system acts as an «intelligent secretary» with knowledge of the foreign language. It asks the writer questions in a keyboard dialogue to collect what the target text needs, such as intention and register, which a finished source text would not state. The argument rests on the view that translation is under-constrained, and that domain knowledge, as in sublanguage approaches, fills the gap. The conclusion says that fully automatic high-quality MT is not to be expected, and that interactive systems should be explored. No evaluation is given in the part read.

Ideas

• I1. Record unresolved choices: when the encoder has two near-equal options for a meta token (for example a register or a form of address), log it as an open question with the verse and the cost of each option, rather than choosing silently. Per author, the log shows where a human decision would help.
• I2. Size the question load: count per verse how many choices the encoder leaves open, and report the share that a single extra fact (the author's register) would close. This measures whether questions are worth asking before any interactive design is built.
• I3. Domain knowledge as the sublanguage of the Bible pairs: the meta concepts and frame anchors already form a restricted domain. Write down, per book, which concepts are domain facts and which are the author's choice, so that the choices that need a question are the ones outside the domain.

For Mova

The question log is a natural form of the delta: an open choice can become an author override once a translator decides it. It is a measurable control for the author DELTA, since a choice that never changes the residual need not be asked. No interactive system is planned, and the idea is recorded for the translator's analysis only.

Topics: Machine translation

Cite

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

@inproceedings{somers1990machine,
  title = {{Machine Translation without a source text}},
  author = {Somers, Harold L. and Tsujii, Jun-ichi and Jones, Danny},
  booktitle = {COLING 1990 Volume 3: Papers presented to the 13th International Conference on Computational Linguistics},
  year = {1990},
  url = {https://aclanthology.org/C90-3048/}
}

References

21 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. H. ARYrA, K. KOGURE, I. NOGAITO, H. MAEDA & H. IIDA (1987) 'Media ni izon suru kaiwa no y6shiki: dcnwakaiwa to kiib6do no kaiwai no hikaku (Media-dependent conversation manners: comparison of telephone and keyboard conversations)'. Jrh6 Short Gakkai 87.34 (Jbh5 Short Gakkai Kenkyh Hbkoku, Shizen Gengo Short 61-NLP-5, 1987.5.22). find
2. C. BOITET (1989) 'Speech synthesis and Dialogue Based Machine Translation'. ATR Symposium on Basic Research for Telephone Interpretation, Kyoto, December 1989. Preprints, 6-5-1-9. find
3. H. IIDA (1987) 'Distinctive features of conversations and inter-keyboard interpretation'. Workshop on Natural Language Dialogue Interpretation, Advanced Telecommunications Research Institute (ATR), Osaka, November 1987. find
4. R.L. JOHNSON & P. WttlTELOCK (1987) 'Machine translation as an expert task'. In S. Nirenburg (ed)Machine translation: theoretical and methodological issues, Cambridge: Cambridge University Press, 136-144. find
5. D. JONES & J. TsuJn (1990) 'High quality machine-driven text translation'. Third International Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages, Austin, Texas, June 1990. find
6. M. KAY (1980) The proper place of men and machines in language translation. Research Report CSL-80-11. find
7. Xerox Palo Alto Research Center, Palo Alto, California, October 1980. find
8. M. KOSAKA, V. TELLER & R. GRISHMAN (1988) 'A sublanguage approach to Japanese-English machine translation'. In D. Maxwell, K. Schubert & T. Witkam (eds) New directions in machine translation, Dordrecht: Foris, 109-120. find
9. J. LEHRBERGER & L. BOURBEAU (1988) Machine translation: Linguistic characteristics of MT systems and general methodology of evaluation. Amsterdam: John Benjamins. find
10. A.K. MELBY (1982) 'Multi-level translation aids in a distributed system'. In J. Horeck9 (ed) COLING 82: Proceedings of the Ninth International Conference on Computational Linguistics, Amsterdam: North-Holland, 215-220. find
11. S. MIIKE, K. HASEBE, H. SOMERS & S. AMANO (1988) 'Experiences with an on-line translating dialogue system'. 26th Annual Meeting of the Association for Computational Linguistics. find
12. Buffalo, NY, June 1988. Proceedings, 155-162. find
13. K. NAGASAKi (1971) (Hito ni warawarenai) Kotoba dzukai to hanashi kata. T6ky6: Bunwa Shobo. find
14. R. REILLY (1989) 'Communication failure in dialogue: implications for natural language understanding'. In J. Peckham (ed) Recent developments and applications of Natural Language Processing, London: Kogan Page, 244-261. find
15. A. ROTHKEGEL (1986) 'Textverstehen und Transfer in der maschinellen Ubersetzung'. In I. B~ttori & H.J. Weber (Hgg) Neue Ansiitze in Maschineller Ubersetzung: Wissensrepr'asen. ration und Textbezug, Tiibingen: Max Niemeyer Verlag, 197-227. find
16. H. SAITO & M. TOMITA (1986) 'On automatic composition of stereotypic documents in foreign languages'. Presented at 1st Intemational Conference on Applications of Artificial Intelligence to Engineering Problerns, Southampton, April 1986. Research Report CMU-CS-86-107, Department of Computer Science, Carnegie-Mellon University. find
17. M.G. STEER & F.W.M. STENTIFORD (1989) 'Speech language translation'. In J. Peckham (ed) Recent developments and applications of Natural Language Processing, London: Kogan Page, 129-140. find
18. T. WACHTEL (1986) 'Pragmatic sensitivity in NL interfaces and the structure of conversation'. I Ith International Conference on Computational Linguistics, Proceedings of Coling '86, Bonn, 35-41. HJ. find
19. WEBER (1987) Converging approaches in Machine Translation: domain knowledge and discours [sic] knowledge. Linguistic Agency University of Duisburg Series B, No.164. find
20. P.J. WltlTELOCK, M.M. WOOD, B.J. CHANDLER, N. HOLDEN & H.J. HORSFALL (1986) 'Strategies for interactive machine translation: the experience and implications of the UMIST Japanese project', l lth International Conference on Computational Linguistics, Proceedings of Coling '86, Bonn, 329-334. find
21. M.M. WOOD & B.J. CHANDLER (1988) 'Machine translation for monolinguals'. In D. Vargha (ed) COLtNG Budapest: Proceedings of the 1 2 t h International Conference on Computational Linguistics, Budapest: John yon Neumann Society for Computing Sciences, 760-763. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/somers-1990-machine-translation-without-source-text/