Identifying Zero Pronouns in Japanese Dialogue

Summary

The paper addresses how to recover zero pronouns in Japanese dialogue for an automatic Japanese-English conversation translation system under development at ATR. Zero pronouns are omitted obligatory case arguments that are recoverable only from discourse, context or world knowledge. The author first examines simulated inter-terminal dialogues and finds that zero pronouns largely take on the role that English personal pronouns play. The proposed model has two parts. The first is Topic-driven Discourse Structure (TDS), a recursive topic hierarchy built on a unification-based parser with HPSG/JPSG-style grammar, which resolves mostly non-human zero pronouns as a side effect of structuring the discourse. The second resolves mostly human (first and second person) zero pronouns using constraints from honorific, deictic, speech-act and mental-activity predicates. The components are applied in sequence: syntax first, then topic structure, then predicate information. In the analysed data, about 80% of zero pronouns fall into cases this combined approach can handle. The work shows that topic continuity and pragmatic information carried by predicates are practical clues to Japanese zero anaphora.

Key points

Pilot data: 94 sentences in 2 dialogue sequences, with English translations.
- Of 53 English personal pronouns, 51 correspond to Japanese zero pronouns.
- Of 15 zero pronouns with non-human antecedents, 14 refer to a current topic.
Human referents: of 74 first- and second-person zero pronouns, 55 are resolvable through predicate information. The remaining 19 are set phrases or cases that depend on the whole context.
Grammar encoding: topics are stored in a stack-valued TOPIC foot feature that comes from the particle wa, and omitted arguments are stored in SLASH, following HPSG (Pollard & Sag) and JPSG (Gunji).
TDS mechanism: TDS relies on a recursive rule over discourse nodes with a TOP feature and default inheritance, stated in extended PATR-II notation. A Topic Supplementation Principle fills SLASH arguments from the topic stack. Topic introduction is extended to markers such as no koto desu ga and to existential ga patterns.
Coverage and positioning: 79.8% of zero pronouns in the data were identifiable by the approach. The author contrasts it with Kameyama's centering-based account.

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: Linguistics & languages

Topics: Discourse analysis · Coreference resolution

Cited by

10 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 6 not yet.

Cite

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

@inproceedings{yoshimoto1988identifying,
  title = {{Identifying Zero Pronouns in Japanese Dialogue}},
  author = {Yoshimoto, Kei},
  booktitle = {Coling Budapest 1988 Volume 2: International Conference on Computational Linguistics},
  year = {1988},
  doi = {10.3115/991719.991795},
  url = {https://doi.org/10.3115/991719.991795}
}

References

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

Arita, H. et al., 1987, "Media ni izonsuru kaiwa no ySsiki." [Media-dependent conversation manners] WGNLMeetingReportC1-5, Information Processing Society of Japan. find
Firbas, J., 1966, "On defining the theme in functional sentence analysis." TravauxLinguistgques dePrague 1. find
Klincksieck: Grosz, B., A. Joshi & S. Weinstein, 1983, "Providing a unified account of definite noun phrases in discourse." Proceedings of the 21st Annual Meeting of the Association of Computational Linguistics. find
Gunji, T., 1987, Japanese Phrase Structure Grammar. Reidel. find
Kameyama, M., 1985, "Zero anaphora: the case of Japanese." Stanlbrd Universily Ph.D. Dissertation. ,1986, "A Property-sharing constraint in centering," Proceedings of the 24th Annual Meeting of the Association of Computational Linguistics. find
Kogure, K. et al., 1988, "A Method of analyzing Japanese speech act types." The 2nd International Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages. find
Maeda, H. et al., 1988, "Parsing Japanese honorifics in unification-based grammar." Proceedings of the 26th Annual Meeting of the Association of Computational Linguistics. find
Pollard, C. & I. Sag, 1987, Information-Based Syntax and Semantics. vol. I. CSLI Lecture Notes 13. find
Yoshimoto, K., 1987, "Identification of Zero Pronouns in Japanese." The XIVth International Congress of Linguists. Aug. 10, Berlin. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . \\ , ] f j \\ /" / jJ ] find

This page in Markdown → https://md.research.elamur.ai/free/papers/yoshimoto-1988-identifying-zero-pronouns-japanese-dialogue/

📄 Identifying Zero Pronouns in Japanese Dialogue