[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/ast-1996-eisner-three-new-probabilistic-models-dependency/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [English](https://md.mova.elamur.ai/free/en/docs/papers/en/) / Three New Probabilistic Models for Dependency Parsing: An Exploration

# Three New Probabilistic Models for Dependency Parsing: An Exploration

**Authors:** Jason M. Eisner · **Year:** 1996 · **Venue:** COLING 1996, Volume 1: The 16th International Conference on Computational Linguistics **Link:** [aclanthology.org/C96-1058](https://aclanthology.org/C96-1058/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) — summary only

[**609** citations](https://openalex.org/works?filter=cites:W2052449326) openalex · 2026-10-19[**298** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/ast-1996-eisner-three-new-probabilistic-models-dependency/) of the 140673 papers whose bibliographies we read[COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics](https://aclanthology.org/volumes/C96-1/)[licence](https://creativecommons.org/licenses/by-nc-sa/3.0/)

- [Publisher's page](https://aclanthology.org/C96-1058/)
- [PDF](https://aclanthology.org/C96-1058.pdf)
- [DOI 10.3115/992628.992688](https://doi.org/10.3115/992628.992688)
- [OpenAlex](https://openalex.org/W2052449326)

**Authors (1)**

1. [Eisner, Jason M.](https://openalex.org/A5052467896) [ORCID](https://orcid.org/0000-0002-8861-0772) · [Semantic Scholar](https://www.semanticscholar.org/author/145043214) · h 51 · 8141 citations · 307 works

Citations and author metrics from openalex (2026-10-19); authors with the same name are not always told apart.

## What it is about

The paper gives an O(n^3) bottom-up dynamic-programming parser for projective dependency trees, which became the basis of most projective decoders. On top of it Eisner proposes three probabilistic models: a bigram lexical affinity model (A), a sense-tagging model (B) in which words are generated with their selectional preferences, and a generative model (C) in which each word fleshes out its own children, speaker-oriented. He trains them on dependency trees derived from the Wall Street Journal part of the Penn Treebank and tests on 400 held-out sentences. Model C performs best; the paper's full results give 93% correct tags and 87% correct parents for model C, while the pilot tables are the basis for the ranking. The main claim is that lexical word-pair statistics, not constituents, carry most of the parsing signal.

## Ideas

- I1. gparse/src/eisner.rs: use the Eisner chart as an exact decoder over the same scores as `en`'s perceptron, and report the search error: the share of EWT test sentences where the greedy `en` tree scores below the projective optimum.
- I2. en/src/parse.rs: check whether word-pair features (head word times child word) are present; if not, add them as in model A and measure cv LAS on the train folds.
- I3. en/src/ud.rs backoff tables: test whether conditioning the UPOS and FEATS backoff on the head lexeme, as in model C, improves UFeats on EWT test (95.66 now), with a run of `en ud-eval` each.

## For Mova

The chapters that match are 22-phrases and 23-complementation, where selectional preferences of heads and complements are described. The code touched is `gparse/src/eisner.rs` (the exact projective decoder), `en/src/parse.rs` (lexical features) and `en/src/ud.rs`. Measure first: the search error of `en` against the Eisner optimum on EWT test (idea I1), since it says whether better search is worth more than better features.

Topics: [Dependency parsing](https://md.mova.elamur.ai/free/en/docs/papers/topics/dependency-parsing/)

## Cite

The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.3115/992628.992688](https://doi.org/10.3115/992628.992688)

```
@inproceedings{eisner1996three,
  title = {{Three New Probabilistic Models for Dependency Parsing: An Exploration}},
  author = {Eisner, Jason M.},
  booktitle = {COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics},
  year = {1996},
  doi = {10.3115/992628.992688},
  url = {https://doi.org/10.3115/992628.992688}
}
```

- [← previous Discourse Structure and Dialogue Acts in Multiparty Dialogue: the STAC Corpus](https://md.mova.elamur.ai/free/en/docs/papers/asher-2016-discourse-structure-dialogue-acts-multiparty/)
- [next → Deletion phenomena in comparative constructions: English comparatives in a cross-linguistic perspective](https://md.mova.elamur.ai/free/en/docs/papers/atkari-2018-deletion-phenomena-comparative-constructions/)
- [↑ back to English](https://md.mova.elamur.ai/free/en/docs/papers/en/)

## References

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

1. Ezra Bla.(:k, Fred ,lelinck, et a.1. 1992. Towards history-ba,sed gramnl~u:s: using richer mod(,.ls [br probabilistic i,~trsing. [u Fifth I)AI~,FA Worksh.op ou £'pecch and Natural Language, Arden (7onfcrcn(:c Ceutcr, llnrrim~m, New York, Febrl,u'y. [find](https://scholar.google.com/scholar?q=Ezra+Bla%2E%28%3Ak%2C+Fred+%2Clelinck%2C+et+a%2E1%2E+1992%2E+Towards+history%2Dba%2Csed+gramnl%7Eu%3As%3A+using+richer+mod%28%2C%2Els+%5Bbr+probabilistic+i%2C%7Etrsing%2E+%5Bu+Fifth+I%29AI%7E%2CFA+Worksh%2Eop+ou+%C2%A3%27pecch+and+Natural+Language%2C+Arden+%287on)
2. ['(enne.th W. (3mr(:h. 1988. A stochastic parts pro-gi:ntll a, nd noun l)hra,se parser for unrestri(:tcd text. In /'roe, of the 2rid (;onf. on Applied Natural Lang'uage lJroccssing, 136 148, Austin, TX. Asso(:i~Lti(,n for ('~omput~Ltimml l,inguistics, Morristowu, N.I. [find](https://scholar.google.com/scholar?q=%5B%27%28enne%2Eth+W%2E+%283mr%28%3Ah%2E+1988%2E+A+stochastic+parts+pro%2Dgi%3Antll+a%2C+nd+noun+l%29hra%2Cse+parser+for+unrestri%28%3Atcd+text%2E+In+%2F%27roe%2C+of+the+2rid+%28%3Bonf%2E+on+Applied+Natural+Lang%27uage+lJroccssing%2C+136+148%2C+Austin%2C+T)
3. Mi(:ha.el ./. (',ollins. 1996. A new statistical parser based on bigr~un lexi(:~fl del)cndeucies, h, l~rocc.cd - iTtfJS of tit(; 24th A CL, S~l, nt~,, (~171'Z, (]A, July. [find](https://scholar.google.com/scholar?q=Mi%28%3Aha%2Eel+%2E%2F%2E+%28%27%2Collins%2E+1996%2E+A+new+statistical+parser+based+on+bigr%7Eun+lexi%28%3A%7Efl+del%29cndeucies%2C+h%2C+l%7Erocc%2Ecd+%2D+iTtfJS+of+tit%28%3B+24th+A+CL%2C+S%7El%2C+nt%7E%2C%2C+%28%7E171%27Z%2C+%28%5DA%2C+July%2E)
4. Ja.sol! 1'3isner. 199(;. An empirical (:omp~H'ison of prob-~dfility nlodcls for dependeucy gl:a, lnnlaJ:. Teehnic;d ILeport IRCS 96 11, University of PennsylvaJtilt. I!'red .felinck. 1985. M~rkov sour(:e modeliug of text gener~Ltiou. In .I. Skwirzinski, editor, hnpact of IS"o-tossing 7~chniques ou (… [find](https://scholar.google.com/scholar?q=Ja%2Esol%21+1%273isner%2E+199%28%3B%2E+An+empirical+%28%3Aomp%7EH%27ison+of+prob%2D%7Edfility+nlodcls+for+dependeucy+gl%3Aa%2C+lnnlaJ%3A%2E+Teehnic%3Bd+ILeport+IRCS+96+11%2C+University+of+PennsylvaJtilt%2E+I%21%27red+%2Efelinck%2E+1985%2E+M%7Erkov+sour)
5. Igor A, Mel'(:uk. 1988. l)cpcndcncy Syntax: 7?worg and l'racticc. St~te University of New York Press. [find](https://scholar.google.com/scholar?q=Igor+A%2C+Mel%27%28%3Auk%2E+1988%2E+l%29cpcndcncy+Syntax%3A+7%3Fworg+and+l%27racticc%2E+St%7Ete+University+of+New+York+Press%2E)
6. IL Meria.hlo. 1990. Tagging text with ;L probabilistic model, lu l~rocccdinw of the IBM Natural Language. 17'L, Paris, Fra.nce, pp. 161-172. [find](https://scholar.google.com/scholar?q=IL+Meria%2Ehlo%2E+1990%2E+Tagging+text+with+%3BL+probabilistic+model%2C+lu+l%7Erocccdinw+of+the+IBM+Natural+Language%2E+17%27L%2C+Paris%2C+Fra%2Ence%2C+pp%2E+161%2D172%2E)