---
title: "Learning to Detect Hedges and their Scope Using CRF (2010)"
description: "The paper describes a CoNLL-2010 shared task entry that identifies speculative language (hedges) in… 12 references, cited by 3 papers here."
authors: ["Qi Zhao", "Chengjie Sun", "Bingquan Liu", "Yong Cheng"]
year: 2010
venue: "Proceedings of the Fourteenth Conference on Computational Natural Language Learning – Shared Task"
source: "https://aclanthology.org/W10-3014/"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhao-2010-learning-detect-hedges-their-scope/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhao-2010-learning-detect-hedges-their-scope/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2010](https://md.research.elamur.ai/free/en/papers/2010/page/2/) / Learning to Detect Hedges and their Scope Using CRF

# Learning to Detect Hedges and their Scope Using CRF

**Authors:** Qi Zhao, [Chengjie Sun](https://md.research.elamur.ai/free/en/authors/chengjie-sun/), [Bingquan Liu](https://md.research.elamur.ai/free/en/authors/bingquan-liu/) and [Yong Cheng](https://md.research.elamur.ai/free/en/authors/yong-cheng/) · **Year:** 2010 · **Venue:** [Proceedings of the Fourteenth Conference on Computational Natural Language Learning – Shared Task](https://md.research.elamur.ai/free/en/venues/conll/) ([CoNLL 2010](https://md.research.elamur.ai/free/en/venues/conll/2010/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/W10-3014/) · [PDF](https://aclanthology.org/W10-3014.pdf) · [OpenAlex](https://openalex.org/W2166006644)

**Citations:** 7 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/zhao-2010-learning-detect-hedges-their-scope/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper describes a CoNLL-2010 shared task entry that identifies speculative language (hedges) in biomedical writing. It covers both subtasks: flagging uncertain sentences and finding the span each hedge cue governs. The authors treat cue detection as sequence labeling with a CRF (CRF++ 0.51). Features are word, POS, lemma and chunk tags from GENIA Tagger, plus a new HCDic feature. HCDic is a hedge cue dictionary built from the BioScope abstracts, and each entry is graded by how often it occurs outside speculative sentences. A sentence counts as uncertain if any cue is found in it. A second CRF marks only the first and last token of each scope, and simple rules then guarantee exactly one scope per cue. On BioScope, HCDic lifts cue-level F-score from about 0.68 to 0.75, and the sentence-level task reaches roughly 84%. Scope detection stays weak (F about 37.6%), and the method transfers poorly to Wikipedia weasel words. The work shows both how useful and how limited a small, graded lexicon can be for a closed cue vocabulary.

## Key points
- BioScope abstracts contain 143 distinct hedge cues, averaging 1.44 words each and at most 4 words. A typical speculative sentence has about one cue (1.28 per sentence).
- HCDic grades cues into four types (L, H, FL, FH) using the non-speculative/speculative occurrence ratio. FL and FH are split at a threshold of 1.0, and cues seen more than 5 times only in speculative sentences become H.
- At cue level on BioScope, all features give P 0.7671 / R 0.7393 / F 0.7529, compared with F 0.6781 without HCDic. Task 1 sentence-level F is about 0.84.
- On Wikipedia, recall falls to 0.2001 (F 0.3120), even after the weasel dictionary is compressed from 1984 cues to 170 adjective "core words".
- Task 2 scope results are P 34.8%, R 41%, F 37.6%. About 86.1% of scopes start at the cue itself, and more than 80% end at the sentence end.

## Interesting ideas
- Instead of a binary dictionary hit, give each lexicon entry a reliability grade based on how often the word appears in non-target contexts, and feed that grade to the learner as a feature. This lets the model concentrate on ambiguous words like "or" versus near-certain ones like "suggesting".
- Cast scope detection as predicting only the boundary tokens (start and end) rather than labeling every token inside the span. Then repair the output with deterministic rules: keep the nearer head and the farther tail, and fall back to "cue to sentence end".
- When lexical cues are mostly multiword and rare, as with weasel phrases like "many persons", collapse them to a recurring core word to keep dictionary coverage.
- Cue-level errors largely disappear at sentence level: one found cue is enough, and a false cue in an already speculative sentence still gives the right answer. Evaluating at several granularities shows where errors actually matter.

## For Mova

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

- **I1** (frames): A graded hedge/modal lexicon could mark frame assertions as asserted, likely or uncertain, with the grade recorded as the explanation.
- **I2** (tree): Hedge scope could be projected from the UD subtree of the cue verb or modal, with these fallback rules as an explainable backup when the parse is unsure.
- **I3** (world): Vague quantifiers and attribution phrases reduced to core words could tag world-model facts as having unattributed or vague sources.
- **I4** (learn): Report hedge or modality accuracy at both the token and the proposition level, so downstream answer quality is not misjudged from token scores alone.

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

## Institutions

- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 158 works · 28,841 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 234 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 231 works

## Cite

Cite as: Qi Zhao, Chengjie Sun, Bingquan Liu and Yong Cheng. 2010. Learning to Detect Hedges and their Scope Using CRF. Proceedings of the Fourteenth Conference on Computational Natural Language Learning – Shared Task.

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

```bibtex
@inproceedings{zhao2010learning,
  title = {{Learning to Detect Hedges and their Scope Using CRF}},
  author = {Qi Zhao, Chengjie Sun, Bingquan Liu and Yong Cheng},
  booktitle = {Proceedings of the Fourteenth Conference on Computational Natural Language Learning – Shared Task},
  year = {2010},
  url = {https://aclanthology.org/W10-3014/}
}
```

- [← previous Cross-linguistic Attribute Selection for REG: Comparing Dutch and English](https://md.research.elamur.ai/free/en/papers/theune-2010-cross-linguistic-attribute-selection-reg/)
- [next → Towards Semi-Automated Annotation for Prepositional Phrase Attachment](https://md.research.elamur.ai/free/en/papers/rosenthal-2010-semi-automated-annotation-prepositional-phrase/)
- [↑ back to papers of 2010](https://md.research.elamur.ai/free/en/papers/2010/page/2/)

## References

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

1. Richárd Farkas, Veronika Vincze, György Móra, János Csirik, and György Szarvas. 2010. [The CoNLL-2010 Shared Task: Learning to Detect Hedges and their Scope in Natural Language Text](https://md.research.elamur.ai/free/en/papers/farkas-2010-conll-2010-shared-task-learning/). In Proceedings of the Fourteenth Conference on Computational Natural Language Learning (CoNLL-2010): Shared Task , pages 1–12, Uppsala, Sweden, July. Computational Linguistics.
2. Association Halil Kilicoglu, and Sabine Bergler. 2008. [Recognizing speculative language in biomedical research articles: a linguistically motivated perspective](https://md.research.elamur.ai/free/en/papers/kilicoglu-2008-recognizing-speculative-language-biomedical-research/). BMC Bioinformatics , 9(Suppl 11):S10.
3. John Lafferty, Andrew K. McCallum, and Fernando Pereira. 2001. Conditional random fields: probabilistic models for segmenting and labeling sequence data. In ICML , pages 282–289. [find](https://scholar.google.com/scholar?q=John+Lafferty%2C+Andrew+K%2E+McCallum%2C+and+Fernando+Pereira%2E+2001%2E+Conditional+random+fields%3A+probabilistic+models+for+segmenting+and+labeling+sequence+data%2E+In+ICML+%2C+pages+282%E2%80%93289%2E)
4. George Lakoff. 1972. [Hedges: a study in meaning criteria and the logic of fuzzy concepts](https://md.research.elamur.ai/free/en/papers/lakoff-1973-hedges-study-meaning-criteria/). Chicago Linguistics Society Papers , 8:183–228. [↗](https://doi.org/10.1007/bf00262952)
5. Marc Light, Xin Y. Qiu, and Padmini Srinivasan. 2004 The language of bioscience: facts,speculations, and statements in between. In BioLINK 2004: Linking Biological Literature, Ontologies and Databases , pages 17–24. [find](https://scholar.google.com/scholar?q=Marc+Light%2C+Xin+Y%2E+Qiu%2C+and+Padmini+Srinivasan%2E+2004+The+language+of+bioscience%3A+facts%2Cspeculations%2C+and+statements+in+between%2E+In+BioLINK+2004%3A+Linking+Biological+Literature%2C+Ontologies+and+Databases)
6. Ben Medlock, and Ted Briscoe. 2007. [Weakly supervised learning for hedge classification in scientific literature](https://md.research.elamur.ai/free/en/papers/medlock-2007-weakly-supervised-learning-hedge-classification/). In Proceedings of ACL 2007 , pages 992–999.
7. Roser Morante, and Walter Daelemans. 2009. [Learning the scope of hedge cues in biomedical texts](https://md.research.elamur.ai/free/en/papers/morante-2009-learning-scope-hedge-cues-biomedical/). In Proceedings of the BioNLP 2009
8. Workshop , pages 28-36, Boulder, Colorado, June 2009. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Workshop+%2C+pages+28%2D36%2C+Boulder%2C+Colorado%2C+June+2009%2E+Association+for+Computational+Linguistics%2E)
9. Roser Morante, and Walter Daelemans. 2009. A metalearning approach to processing the scope of negation. In Proceedings of CoNLL-2009 . Boulder, Colorado. [find](https://scholar.google.com/scholar?q=Roser+Morante%2C+and+Walter+Daelemans%2E+2009%2E+A+metalearning+approach+to+processing+the+scope+of+negation%2E+In+Proceedings+of+CoNLL%2D2009+%2E+Boulder%2C+Colorado%2E)
10. György Szarvas. 2008. [Hedge classification in biomedical texts with a weakly supervised selection of keywords](https://md.research.elamur.ai/free/en/papers/szarvas-2008-hedge-classification-biomedical-texts-weakly/). In Proceedings of ACL 2008 , pages 281–289, Columbus, Ohio, USA. ACL.
11. Yoshimasa Tsuruoka, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John McNaught, Sophia Ananiadou, and Jun’ichi Tsujii. 2005. Developing a robust part-of-speech tagger for biomedical text. In: Advances in Informatics, PCI 2005 , pages 382– 392. [find](https://scholar.google.com/scholar?q=Yoshimasa+Tsuruoka%2C+Yuka+Tateishi%2C+Jin%2DDong+Kim%2C+Tomoko+Ohta%2C+John+McNaught%2C+Sophia+Ananiadou%2C+and+Jun%E2%80%99ichi+Tsujii%2E+2005%2E+Developing+a+robust+part%2Dof%2Dspeech+tagger+for+biomedical+text%2E+In%3A+Advances+in)
12. Veronika Vincze, György Szarvas, Richárd Farkas, György Móra, and János Csirik. 2008. The BioScope corpus: biomedical texts annotated for uncertainty, negation and their scopes. BMC Bioinformatics , 9(Suppl 11):S9. for [↗](https://doi.org/10.1186/1471-2105-9-s11-s9)

*Updated 1 November 2026*