Using Hedge Detection to Improve Committed Belief Tagging

What it is about

The paper adds hedge features to a committed-belief tagger. The tagger marks each proposition head as committed belief (CB), non-committed belief (NCB), reported belief (ROB) or non-belief (NA: desire, intention, question). Hedges are found from a 117-term dictionary in two ways: plain lemma lookup, or hand rules over POS and dependencies that separate hedge from non-hedge uses. For example, about as a preposition is not a hedge; likely as amod of a noun is not; assume, tend and appear are hedges only with a clausal complement; sure and completely are hedges only under negation; supposed to and should have are not. Features for the word itself, its parent, children, siblings and ancestors, plus a sentence flag, go into an SVM. On the DEFT forum corpus (5-fold CV), rule-based hedge features raise NCB F1 from 23.7 to 30.4 and ROB from 23.3 to 27.4; overall F1 rises only from 67.5 to 68.1, because those classes are rare.

Ideas

• I1. Give each Mova frame a commitment value next to neg and cond in prag::frames (prag/src/frames.rs): committed, non-committed (a hedge or modal governs the predicate), reported (inside the quote of a Say frame whose speaker is not the narrator), or not a belief (wish, intention, question). Most of the information is already present: Say frames, cond, modals in feats.
• I2. Let the student weigh by it. In world/src/knowledge.rs a remembered frame that is non-committed («maybe the wolf ate it») or reported («the fox said the cheese was poisoned») should support an option less than a committed narrator fact. Measure course test counts and the world knowledge diagnose step-5 share (right option outscored).
• I3. Hedge rules that look at the parent and siblings, not only the token: a hedge counts for a proposition when it is the head's child (advmod) or the head's governing verb («I think [p]»). The same tree position decides which frame inherits non-commitment in I1. Test it on frame bench lines with think, maybe or seem.
• I4. Negation flips boosters into hedges («not sure», «isn't completely true»). Reuse infer::negated for this one rule in the hedge slot.

For Mova

32. Politeness and hedging §8 (epistemic modality and evidentiality), 33. Implicature and presupposition (speaker commitment); prag/src/frames.rs, prag/src/feats.rs, world/src/knowledge.rs; measures: frame bench F1 unchanged (no regression), course test counts, the diagnose breakdown.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/w18-1301

@inproceedings{ulinski2018using,
  title = {{Using Hedge Detection to Improve Committed Belief Tagging}},
  author = {Ulinski, Morgan and Benjamin, Seth and Hirschberg, Julia},
  booktitle = {Proceedings of the Workshop on Computational Semantics beyond Events and Roles},
  year = {2018},
  doi = {10.18653/v1/w18-1301},
  url = {https://doi.org/10.18653/v1/w18-1301}
}

References

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

1. 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(11):S9. find
2. David Clausen. 2010. Hedgehunter: A system for hedge detection and uncertainty classification. In Proceedings of the Fourteenth Conference on Computational Natural Language Learning, pages 120– 125, Uppsala, Sweden. Association for Computational Linguistics. find
3. Andreas Vlachos and Mark Craven. 2010. Detecting speculative language using syntactic dependencies and logistic regression. In Proceedings of the Fourteenth Conference on Computational Natural Language Learning, pages 18–25, Uppsala, Sweden. Association for Computational Linguistics. find
4. 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. In Proceedings of the Fourteenth Conference on Computational Natural Language Learning, pages 1–12, Uppsala, Sweden. Association for Computational Linguistics. Vinodkumar Prabhakaran, Tomas By, Julia Hirschberg, Owen Rambow, Samira Shaikh, Tomek Strzalkowski, Jennifer Tracey, Michael Arrigo, Ru-payan Basu, Micah Clark, Adam Dalton, Mona find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/ulinski-2018-hedge-detection-improve-committed-belief/