--- title: "Exploring the steps of Verb Phrase Ellipsis — Liu 2016" description: "The authors release the converted BNC data for research. 14 references, cited by 10 papers here." authors: ["Zhengzhong Liu", "Edgar Gonzàlez Pellicer", "Daniel Gillick"] year: 2016 venue: "Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016)" source: "https://aclanthology.org/W16-0705/" doi: "10.18653/v1/w16-0705" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/liu-2016-exploring-steps-verb-phrase-ellipsis/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2016-exploring-steps-verb-phrase-ellipsis/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/page/3/) / Exploring the steps of Verb Phrase Ellipsis # Exploring the steps of Verb Phrase Ellipsis **Authors:** [Zhengzhong Liu](https://md.research.elamur.ai/free/en/authors/zhengzhong-liu/), Edgar Gonzàlez and [Dan Gillick](https://md.research.elamur.ai/free/en/authors/daniel-gillick/) · **Year:** 2016 · **Venue:** Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016), co-located with NAACL 2016 **Link:** [aclanthology.org/W16-0705](https://aclanthology.org/W16-0705/) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) [**15** citations](https://openalex.org/works?filter=cites:W2512180100) OpenAlex, 2026-10-14 · [**10** citations in our library](https://md.research.elamur.ai/free/en/papers/liu-2016-exploring-steps-verb-phrase-ellipsis/cited-by/) of the 140,884 papers whose bibliographies we read · [Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016)](https://aclanthology.org/volumes/W16-07/) · [licence](https://creativecommons.org/licenses/by/4.0/) - [Publisher's page](https://aclanthology.org/W16-0705/) - [PDF](https://aclanthology.org/W16-0705.pdf) - [DOI 10.18653/v1/w16-0705](https://doi.org/10.18653/v1/w16-0705) - [OpenAlex](https://openalex.org/W2512180100) **Authors (3)** 1. [Zhengzhong Liu](https://openalex.org/A5029648803) [ORCID](https://orcid.org/0009-0007-6686-2577) · [Semantic Scholar](https://www.semanticscholar.org/author/1808004) · h 16 · 1,141 citations · 73 works 2. Edgar Gonzàlez Pellicer 3. [Daniel Gillick](https://openalex.org/A5110778504) [Semantic Scholar](https://www.semanticscholar.org/author/2396669) · h 13 · 974 citations · 29 works Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart. ## What it is about The paper splits VP ellipsis (VPE) resolution into three tasks: target detection, antecedent head resolution and antecedent boundary detection. Each task gets its own learned model, and the authors also test joint learning over pairs of tasks. A logistic regression model works better for target detection and for boundary detection. A ranking model works better for choosing the antecedent head. Joint models with ranking fail on target detection because the classes are very unbalanced. Candidate generation is a limit of its own: the oracle keeps only about 93% of the targets, a loss of about 7% on both corpora. The data are the WSJ section of the Penn Treebank with the Bos and Spenader (2011) VPE annotation, and a BNC version converted from Nielsen (2005) and checked by hand. The authors release the converted BNC data for research. ## Ideas - I3. Joint against separate: try one joint perceptron over target and head decisions, with balanced sampling of the negative targets, and compare with the separate models on the same test set. The paper's failure on class imbalance says the sampling must be checked first. ## For Mova - I1. `en/src/expert.rs` and `en/src/ctx.rs`: build the three stages as three separate components, each with its own rule set and its own report line. Target detection uses the trigger, head resolution uses c-command and parallelism, and boundary detection uses the clause structure. - I2. Candidate ceiling first: measure how many gold targets the candidate generator keeps on an `en` parse of a test set we may use, before any ranker is tuned. The paper's 7% loss is the reason to do this first. The code is `en/src/expert.rs`, `en/src/ctx.rs` and the `coref` crate (for the ranker). The chapter is [languages/en/29-ellipsis-word-order-information-structure.md](https://mova.elamur.ai/free/en/docs/languages/en/29-ellipsis-word-order-information-structure/). The WSJ data is Penn Treebank data, which is licensed, and the BNC part is NC; both are for measurement only. Measure first: the candidate ceiling on a test set we may use. ## Institutions [🏢**Google** Mountain View · United States 272 works · 255,532 citations](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**Carnegie Mellon University** Pittsburgh · United States 278 works · 138,810 citations](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) ## Cite Cite as Zhengzhong Liu, Edgar Gonzàlez Pellicer and Daniel Gillick. 2016. Exploring the steps of Verb Phrase Ellipsis. Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016). The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.18653/v1/w16-0705](https://doi.org/10.18653/v1/w16-0705) ```bibtex @inproceedings{liu2016exploring, title = {{Exploring the steps of Verb Phrase Ellipsis}}, author = {Zhengzhong Liu, Edgar Gonzàlez Pellicer and Daniel Gillick}, booktitle = {Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016)}, year = {2016}, doi = {10.18653/v1/w16-0705}, url = {https://doi.org/10.18653/v1/w16-0705} } ``` - [← previous Unsupervised Ranking Model for Entity Coreference Resolution](https://md.research.elamur.ai/free/en/papers/ma-2016-unsupervised-ranking-model-entity-coreference/) - [next → Improving event prediction by representing script participants](https://md.research.elamur.ai/free/en/papers/ahrendt-2016-improving-event-prediction-representing-script/) - [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/3/) ## References 14 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Johan Bos and Jennifer Spenader. 2011. An annotated corpus for the analysis of VP ellipsis. Language Resources and Evaluation, 45(4):463–494. [find](https://scholar.google.com/scholar?q=Johan+Bos+and+Jennifer+Spenader%2E+2011%2E+An+annotated+corpus+for+the+analysis+of+VP+ellipsis%2E+Language+Resources+and+Evaluation%2C+45%284%29%3A463%E2%80%93494%2E) 2. Mary Dalrymple, Stuart M. Shieber, and Fernando C. N. Pereira. 1991. Ellipsis and higher-order unification. Linguistics and Philosophy, 14(4):399–452. [find](https://scholar.google.com/scholar?q=Mary+Dalrymple%2C+Stuart+M%2E+Shieber%2C+and+Fernando+C%2E+N%2E+Pereira%2E+1991%2E+Ellipsis+and+higher%2Dorder+unification%2E+Linguistics+and+Philosophy%2C+14%284%29%3A399%E2%80%93452%2E) 3. Ofer Dekel, Yoram Singer, and Christopher D. Manning. 2003. Log-linear models for label ranking. In Advances in Neural Information Processing Systems, page None. [find](https://scholar.google.com/scholar?q=Ofer+Dekel%2C+Yoram+Singer%2C+and+Christopher+D%2E+Manning%2E+2003%2E+Log%2Dlinear+models+for+label+ranking%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+page+None%2E) 4. Greg Durrett, David Hall, and Dan Klein. 2013. Decentralized Entity-Level Modeling for Coreference Resolution. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 114–124. [our card](https://md.research.elamur.ai/free/en/papers/durrett-2013-decentralized-entity-level-modeling-coreference/) 5. Daniel Hardt. 1992. An algorithm for VP ellipsis. In Proceedings of the 30th annual meeting on Association for Computational Linguistics, number January, pages 9–14. [find](https://scholar.google.com/scholar?q=Daniel+Hardt%2E+1992%2E+An+algorithm+for+VP+ellipsis%2E+In+Proceedings+of+the+30th+annual+meeting+on+Association+for+Computational+Linguistics%2C+number+January%2C+pages+9%E2%80%9314%2E) 6. Daniel Hardt. 1997. An empirical approach to VP ellipsis. Computational Linguistics, 23(4):525–541. [our card](https://md.research.elamur.ai/free/en/papers/hardt-1997-empirical-approach-vp-ellipsis/) 7. Daniel Hardt. 1998. Improving Ellipsis Resolution with Transformation-Based Learning. AAAI Fall Symposium, pages 41–43. [find](https://scholar.google.com/scholar?q=Daniel+Hardt%2E+1998%2E+Improving+Ellipsis+Resolution+with+Transformation%2DBased+Learning%2E+AAAI+Fall+Symposium%2C+pages+41%E2%80%9343%2E) 8. Leif Arda Nielsen. 2003a. A corpus-based study of Verb Phrase Ellipsis Identification and Resolution. In Proceedings of the 6th Annual CLUK Research Colloquium, page Proceedings of the 6th Annual CLUK Research Colloq. [find](https://scholar.google.com/scholar?q=Leif+Arda+Nielsen%2E+2003a%2E+A+corpus%2Dbased+study+of+Verb+Phrase+Ellipsis+Identification+and+Resolution%2E+In+Proceedings+of+the+6th+Annual+CLUK+Research+Colloquium%2C+page+Proceedings+of+the+6th+Annual+CLUK) 9. Leif Arda Nielsen. 2003b. Using Machine Learning techniques for VPE detection. In Proceedings of Recent Advances in Natural Language Processing, pages 339– 346. [find](https://scholar.google.com/scholar?q=Leif+Arda+Nielsen%2E+2003b%2E+Using+Machine+Learning+techniques+for+VPE+detection%2E+In+Proceedings+of+Recent+Advances+in+Natural+Language+Processing%2C+pages+339%E2%80%93+346%2E) 10. Leif Arda Nielsen. 2004a. Robust VPE detection using automatically parsed text. In Proceedings of the Student Workshop, ACL 2004, pages 31–36. [our card](https://md.research.elamur.ai/free/en/papers/nielsen-2004-robust-vpe-detection-automatically-parsed/) 11. Leif Arda Nielsen. 2004b. Verb phrase ellipsis detection using automatically parsed text. In Proceedings of the 20th international conference on Computational Linguistics - COLING ’04. [our card](https://md.research.elamur.ai/free/en/papers/nielsen-2004-verb-phrase-ellipsis-detection-automatically/) 12. Leif Arda Nielsen. 2005. A corpus-based study of Verb Phrase Ellipsis Identification and Resolution. Doctor of philosopy, King’s College London. [find](https://scholar.google.com/scholar?q=Leif+Arda+Nielsen%2E+2005%2E+A+corpus%2Dbased+study+of+Verb+Phrase+Ellipsis+Identification+and+Resolution%2E+Doctor+of+philosopy%2C+King%E2%80%99s+College+London%2E) 13. Altaf Rahman and Vincent Ng. 2009. Supervised models for coreference resolution. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, number August, pages 968–977. [our card](https://md.research.elamur.ai/free/en/papers/rahman-2009-supervised-models-coreference-resolution/) 14. Stuart M. Shieber, Fernando C. N. Pereira, and Mary Dalrymple. 1996. Interactions of scope and ellipsis. Linguistics and Philosophy, 19(5):527–552. [find](https://scholar.google.com/scholar?q=Stuart+M%2E+Shieber%2C+Fernando+C%2E+N%2E+Pereira%2C+and+Mary+Dalrymple%2E+1996%2E+Interactions+of+scope+and+ellipsis%2E+Linguistics+and+Philosophy%2C+19%285%29%3A527%E2%80%93552%2E)