--- title: "Weakly Supervised Learning of Presupposition Relations" description: "Tremper builds a weakly supervised, discriminative classifier that sorts verb pairs into five classes… 12 references, cited by 2 papers here." authors: ["Galina Tremper"] year: 2010 venue: "Proceedings of the ACL 2010 Student Research Workshop" source: "https://aclanthology.org/P10-3017/" 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/tremper-2010-weakly-supervised-learning-presupposition-relations/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tremper-2010-weakly-supervised-learning-presupposition-relations/) [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/) / Weakly Supervised Learning of Presupposition Relations between Verbs # Weakly Supervised Learning of Presupposition Relations between Verbs **Authors:** [Galina Tremper](https://md.research.elamur.ai/free/en/authors/galina-tremper/) · **Year:** 2010 · **Venue:** [Proceedings of the ACL 2010 Student Research Workshop](https://md.research.elamur.ai/free/en/venues/acl-student-research-workshop/) ([ACL Student Research Workshop 2010](https://md.research.elamur.ai/free/en/venues/acl-student-research-workshop/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/P10-3017/) · [PDF](https://aclanthology.org/P10-3017.pdf) · [OpenAlex](https://openalex.org/W2168472059) **Citations:** 5 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/tremper-2010-weakly-supervised-learning-presupposition-relations/cited-by/) in our library, of the 141,840 papers whose bibliographies we read ## Summary The paper targets presupposition between verbs, a lexical relation that WordNet and VerbOcean barely cover or merge with entailment. Examples are *find* presupposing *seek* and *manage* presupposing *try*. The two relations matter separately because a presupposition still holds when the sentence is negated, while an entailment does not. Tremper builds a weakly supervised, discriminative classifier that sorts verb pairs into five classes: presupposition, entailment, temporal inclusion, antonymy and other/no. Candidate pairs come from DIRT and are filtered with ukWAC frequencies and PMI. A few manually chosen seed pairs per class yield a training corpus that is partly hand-labelled, partly labelled by heuristics and partly built from WordNet synonyms. Sentences are parsed with XLE to extract shallow and deep features. One J48 binary classifier is trained per relation, and their votes are combined with confidence filters. Only the first iteration of the bootstrapping loop is evaluated. Type-level accuracy is about 36% overall, well above a random baseline, while token-level accuracy is lower. This is an early attempt to learn presupposition from corpora. ## Key points - **Candidate pairs:** DIRT provides 808,764 distinct pairs drawn from 5,604 distinct verbs. Filtering by ukWAC (parts 1–3) frequency and a PMI threshold of 2.0 leaves 199,393 candidates. - **Seeds and training data:** - Each relation gets three seed pairs, except temporal inclusion, which gets six. - The first training set has 15,717 sentences: 5,032 hand-labelled, 9,918 heuristically labelled and 757 from WordNet synonym pairs. - The data are rebalanced because temporal inclusion is about 2% of sentences and entailment about 39%. - **Features:** - verb distance and order, verb form, and negation - polarity verbs from the Nairn et al. lexicon - conjunctions, adverbials and PoS windows - length of the grammatical-function path between the verbs, from XLE parses - whether the verbs share a subject or object - **Ensemble and filtering:** - A classifier vote below 0.75 confidence is dropped, and ties go to the most confident classifier. - At type level, a verb pair can receive up to three labels if each covers more than 10% of its instances. - Bootstrapping keeps instances whose pattern-based reliability exceeds 0.3, following Pantel and Pennacchiotti (2006). - **Results:** - Antonymy scores best at type level (72% Majority, 42% Without NONE, against a 12% baseline). - At token level, the four real relations reach only 13–29%, mostly because single contexts are not informative enough. ## Interesting ideas - Negation works as a diagnostic: presuppositions survive under negation and entailments do not, so the polarity of contexts can separate two relations that otherwise look identical. - Rather than mining candidates with patterns, the method starts from a precomputed list of associated verbs and prunes it with frequency and PMI before any classification. - A small hand-made stoplist of contexts (e.g. *look* followed by *forward*) acts as cheap disambiguation when spreading seed labels to new sentences. - One binary classifier per relation is combined with confidence cut-offs, and type-level labels come from instance proportions with a cap on how many labels a pair may receive. - Deep features such as the dependency path length between two verbs and whether they share a subject or object add structural evidence beyond word windows. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (frames): The implicature layer can tag verb-licensed inferences as presupposed or entailed, and keep only the presupposed ones when the frame sits under negation. - **I2** (world): Verb-relation entries in compiled knowledge could be built by filtering a DIRT-style association list first and classifying only the survivors, which keeps cost and noise low. - **I3** (learn): When silver data is expanded from seeds, an explicit, inspectable blocklist of misleading contexts can stop systematic label leaks and stay explainable. - **I4** (learn): The same aggregation (discard weak votes, allow at most k labels, require a minimum share) can turn noisy per-sentence predictions into knowledge-graph facts with a stated support level. - **I5** (tree): The UD trees Mova already produces can feed these path and argument-sharing features directly into any verb-pair relation learner, with no bag of words. *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 - [Heidelberg University](https://md.research.elamur.ai/free/en/universities/heidelberg-university/) — University, Heidelberg, Germany · 27 works · 40,944 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works 🧭 Topics (1): [😉 Implicature](https://md.research.elamur.ai/free/en/topics/implicature/) · 72 works ## Cite Cite as: Galina Tremper. 2010. Weakly Supervised Learning of Presupposition Relations between Verbs. Proceedings of the ACL 2010 Student Research Workshop. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{tremper2010weakly, title = {{Weakly Supervised Learning of Presupposition Relations between Verbs}}, author = {Galina Tremper}, booktitle = {Proceedings of the ACL 2010 Student Research Workshop}, year = {2010}, url = {https://aclanthology.org/P10-3017/} } ``` - [← previous Uncertainty Detection as Approximate Max-Margin Sequence Labelling](https://md.research.elamur.ai/free/en/papers/tackstrom-2010-uncertainty-detection-as-approximate-max/) - [next → Using Syntactic and Semantic based Relations for Dialogue Act Recognition](https://md.research.elamur.ai/free/en/papers/kluwer-2010-syntactic-semantic-based-relations-dialogue/) - [↑ back to papers of 2010](https://md.research.elamur.ai/free/en/papers/2010/page/2/) ## References 12 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Baroni, M., Bernardini, S., Ferraresi, A., Zanchetta, E.: The WaCky Wide Web: a collection of very large linguistically processed web-crawled corpora. Journal of Language Resources and Evaluation, Vol.43 (3), 209–226 (2009) [find](https://scholar.google.com/scholar?q=Baroni%2C+M%2E%2C+Bernardini%2C+S%2E%2C+Ferraresi%2C+A%2E%2C+Zanchetta%2C+E%2E%3A+The+WaCky+Wide+Web%3A+a+collection+of+very+large+linguistically+processed+web%2Dcrawled+corpora%2E+Journal+of+Language+Resources+and+Evaluation%2C+Vol) 2. Bos, J.: Implementing the Binding and Accommodation Theory for Anaphora Resolution and Presupposition Projection. Computational Linguistics, Vol.29 (2), 179–210 (2003) [find](https://scholar.google.com/scholar?q=Bos%2C+J%2E%3A+Implementing+the+Binding+and+Accommodation+Theory+for+Anaphora+Resolution+and+Presupposition+Projection%2E+Computational+Linguistics%2C+Vol%2E29+%282%29%2C+179%E2%80%93210+%282003%29) 3. Chklovski, T., Pantel, P.: Verbocean: Mining the web for fine-grained semantic verb relations. Proceedings of EMNLP 2004, 33–40, Barcelona (2004) [find](https://scholar.google.com/scholar?q=Chklovski%2C+T%2E%2C+Pantel%2C+P%2E%3A+Verbocean%3A+Mining+the+web+for+fine%2Dgrained+semantic+verb+relations%2E+Proceedings+of+EMNLP+2004%2C+33%E2%80%9340%2C+Barcelona+%282004%29) 4. Crouch, D., Dalrymple, M., Kaplan, R., King, T., Maxwell, J., Newman, P.: XLE Documentation. Palo Alto Research Center (2008) [find](https://scholar.google.com/scholar?q=Crouch%2C+D%2E%2C+Dalrymple%2C+M%2E%2C+Kaplan%2C+R%2E%2C+King%2C+T%2E%2C+Maxwell%2C+J%2E%2C+Newman%2C+P%2E%3A+XLE+Documentation%2E+Palo+Alto+Research+Center+%282008%29) 5. Evert, S.: The CQP Query Language Tutorial (CWB Version 2.2.b90). IMS, Stuttgart (2005) [find](https://scholar.google.com/scholar?q=Evert%2C+S%2E%3A+The+CQP+Query+Language+Tutorial+%28CWB+Version+2%2E2%2Eb90%29%2E+IMS%2C+Stuttgart+%282005%29) 6. Fellbaum, C.: WordNet: An Electronic Lexical Database. 1st edition, MIT Press (1998) [find](https://scholar.google.com/scholar?q=Fellbaum%2C+C%2E%3A+WordNet%3A+An+Electronic+Lexical+Database%2E+1st+edition%2C+MIT+Press+%281998%29) 7. Lin, D., Pantel, P.: Discovery of Inference Rules for Question Answering. Natural Language Engineering, Vol.7, 343–360 (2001) [find](https://scholar.google.com/scholar?q=Lin%2C+D%2E%2C+Pantel%2C+P%2E%3A+Discovery+of+Inference+Rules+for+Question+Answering%2E+Natural+Language+Engineering%2C+Vol%2E7%2C+343%E2%80%93360+%282001%29) 8. Nairn, R., Condoravdi, C., Karttunen, L.: [Computing Relative Polarity for Textual Inference](https://md.research.elamur.ai/free/en/papers/nairn-2006-computing-relative-polarity-textual-inference/). Proc. of ICoS-5, Buxton, UK (2006) 9. Pantel, P., Pennacchiotti, M.: [Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations](https://md.research.elamur.ai/free/en/papers/pantel-2006-espresso-leveraging-generic-patterns-automatically/). COLING 2006, 113-120 (2006) 10. Pekar, V.: Discovery of event entailment knowledge from text corpora. Computer Speech & Language, Vol.22 (1), 1–16 (2008) [find](https://scholar.google.com/scholar?q=Pekar%2C+V%2E%3A+Discovery+of+event+entailment+knowledge+from+text+corpora%2E+Computer+Speech+%26+Language%2C+Vol%2E22+%281%29%2C+1%E2%80%9316+%282008%29) 11. Stalnaker, R.C.: Pragmatic Presuppositions. Semantics and Philosophy, New York: Univ. Press (1974) van der Sandt, R.: Presupposition Projection as Anaphora Resolution. Journal of Semantics, Vol.9, 333–377 (1992) [find](https://scholar.google.com/scholar?q=Stalnaker%2C+R%2EC%2E%3A+Pragmatic+Presuppositions%2E+Semantics+and+Philosophy%2C+New+York%3A+Univ%2E+Press+%281974%29+van+der+Sandt%2C+R%2E%3A+Presupposition+Projection+as+Anaphora+Resolution%2E+Journal+of+Semantics%2C+Vol%2E9%2C+333) 12. Witten, I., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques. (2005) [find](https://scholar.google.com/scholar?q=Witten%2C+I%2E%2C+Frank%2C+E%2E%3A+Data+Mining%3A+Practical+Machine+Learning+Tools+and+Techniques%2E+%282005%29) *Updated 24 October 2026*