---
title: "Computational Investigations of Pragmatic Effects in Natural"
description: "The second introduces a new task: deciding whether a context licenses… 96.63% accuracy on WSJ/PTB. 14 references, cited by 1 paper here."
authors: ["Jad Kabbara"]
year: 2019
venue: "Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop"
source: "https://aclanthology.org/N19-3010/"
doi: "10.18653/v1/n19-3010"
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/kabbara-2019-computational-investigations-pragmatic-effects-natural/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/kabbara-2019-computational-investigations-pragmatic-effects-natural/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/page/7/) / Computational Investigations of Pragmatic Effects in Natural Language

# Computational Investigations of Pragmatic Effects in Natural Language

**Authors:** [Jad Kabbara](https://md.research.elamur.ai/free/en/authors/jad-kabbara/) · **Year:** 2019 · **Venue:** [Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop](https://md.research.elamur.ai/free/en/venues/conference-of-the-north-american-chapter-of-the-association-for-computational/) ([Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop 2019](https://md.research.elamur.ai/free/en/venues/conference-of-the-north-american-chapter-of-the-association-for-computational/2019/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/N19-3010/) · [PDF](https://aclanthology.org/N19-3010.pdf) · [DOI 10.18653/v1/n19-3010](https://doi.org/10.18653/v1/n19-3010) · [OpenAlex](https://openalex.org/W2953539158)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/kabbara-2019-computational-investigations-pragmatic-effects-natural/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
This student-workshop thesis proposal argues that NLP has focused on literal meaning while neglecting pragmatics, the context-dependent intended meaning. It reports two finished studies that use function words as testbeds for pragmatic reasoning. The first is definiteness prediction: choosing *the*, *a(n)* or no article for a noun phrase. An attention-equipped LSTM beats a feature-engineered classifier. Longer context helps it handle article choices that seem to depend on coreference, including synonymous mentions. The second introduces a new task: deciding whether a context licenses an adverbial presupposition trigger such as *again* or *also*. The author builds binary datasets from Penn Treebank and English Gigaword and proposes a parameter-free weighted pooling attention model that outperforms the baselines on most triggers. The remaining plan has four parts:
- a crowdsourced corpus of presuppositional effects,
- summarizers that insert or drop adverbs to stay coherent,
- reading-comprehension questions whose answers are implied rather than stated,
- multi-task reuse of presupposition-aware representations.

The work matters because it treats implicit, presupposed content as a core modeling target rather than an afterthought.

## Key points
- Definiteness model: an LSTM with attention, POS tags, pre-trained vectors and extended context reaches 96.63% accuracy on WSJ/PTB. This is a 51% relative error reduction over the logistic regression of De Felice (2008), which used 10 types of hand-crafted features.
- Ablations showed that pre-trained initialization, extra context, POS tags and attention all help, but by different amounts. Attention weights were used to interpret predictions.
- The presupposition trigger datasets come from Penn Treebank and English Gigaword and cover five adverbs: too, again, also, still, yet. Class balance and the adverb's syntactic governor were controlled so that models cannot succeed through shallow correlations.
- The weighted pooling attention is a self-attention variant that learns how to reweight attention scores rather than averaging hidden states uniformly. It adds no parameters over the LSTM baseline and reaches 82.42% accuracy for "also" on Gigaword. Baselines were logistic regression, RNN and CNN models.
- The author notes that SQuAD is unsuitable for pragmatic QA because its answers are always explicit text spans.

## Interesting ideas
- When building positive vs. negative contexts for a trigger, the author matches confounds such as label balance and the governing word, so a classifier cannot win through syntax alone.
- Adverbs like again, also, still and yet signal that a similar or earlier event exists, or that a state continues or ends. Reading them as event-history markers turns a function word into a world-state constraint.
- Article choice reflects discourse status: indefinites introduce a new referent, and definites point back to a known one, sometimes through a synonym.
- The proposed QA probes ask yes/no questions whose answer follows only from a presupposition. Hard negatives put the trigger on a different person, so a pure trigger detector fails.
- A summarizer should check, sentence by sentence, whether adding or dropping a trigger adverb keeps the presupposed context true and the output coherent.

## For Mova

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

- **I1** (learn): Our negative controls could pair each trigger-bearing test sentence with a governor-matched sentence lacking the trigger, checking that rules respond to discourse rather than to head verbs.
- **I2** (world): Each "again" could add a presupposed earlier event with the same frame before the current one in the event order, and "still/yet" could assert that a state persists.
- **I3** (frames): The coreference step could treat "a N" as opening a new entity and "the N" as a strong cue to link to an earlier, possibly synonymous mention.
- **I4** (answer): We could write fable and tale tests like "Had X done this before?" with distractors where another character carries "again", checking that answers come from the world model.
- **I5** (back): The graph-to-text generator could emit "again/also/still" only when the meaning graph holds the matching prior or parallel event, and omit it otherwise.

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

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 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

## Cite

Cite as: Jad Kabbara. 2019. Computational Investigations of Pragmatic Effects in Natural Language. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop.

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

```bibtex
@inproceedings{kabbara2019computational,
  title = {{Computational Investigations of Pragmatic Effects in Natural Language}},
  author = {Jad Kabbara},
  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop},
  year = {2019},
  doi = {10.18653/v1/n19-3010},
  url = {https://doi.org/10.18653/v1/n19-3010}
}
```

- [← previous Automatic Propbank Generation for Turkish](https://md.research.elamur.ai/free/en/papers/ak-2019-automatic-propbank-generation-turkish/)
- [next → Few-Shot and Zero-Shot Learning for Historical Text Normalization](https://md.research.elamur.ai/free/en/papers/bollmann-2019-few-shot-zero-shot-learning/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/7/)

## References

14 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ashish Vaswani, Noam Shazeer, Niki Parmar, Llion Jones, Jakob Uszkoreit, Aidan N Gomez, and Ł ukasz Kaiser. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in Neural Information Processing Systems 30, pages 5994–6004.
2. Andre Cianflone, Yulan Feng, Jad Kabbara, and Jackie Chi Kit Cheung. 2018. [Let’s do it “again”: A first computational approach to detecting adverbial presupposition triggers](https://md.research.elamur.ai/free/en/papers/cianflone-2018-let-s-do-it-again/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2747– 2755, Melbourne, Australia. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/p18-1256)
3. Rachele De Felice. 2008. Automatic error detection in non-native English. Ph.D. thesis, University of Oxford. [↗](https://doi.org/10.5287/ora-zba61jymp)
4. Gottlob Frege. 1892. Über sinn und bedeutung. Zeitschrift für Philosophie und philosophische Kri-tik, 100:25–50. [find](https://scholar.google.com/scholar?q=Gottlob+Frege%2E+1892%2E+U%CC%88ber+sinn+und+bedeutung%2E+Zeitschrift+fu%CC%88r+Philosophie+und+philosophische+Kri%2Dtik%2C+100%3A25%E2%80%9350%2E)
5. David Graff, Junbo Kong, Ke Chen, and Kazuaki Maeda. 2007. English gigaword third edition. Technical report, Linguistic Data Consortium. [↗](https://doi.org/10.35111/k4mz-9k30)
6. Jad Kabbara, Yulan Feng, and Jackie Chi Kit Cheung. 2016. Capturing pragmatic knowledge in article usage prediction using lstms. In COLING, pages 2625–2634. [find](https://scholar.google.com/scholar?q=Jad+Kabbara%2C+Yulan+Feng%2C+and+Jackie+Chi+Kit+Cheung%2E+2016%2E+Capturing+pragmatic+knowledge+in+article+usage+prediction+using+lstms%2E+In+COLING%2C+pages+2625%E2%80%932634%2E)
7. Layth Muthana Khaleel. 2010. An analysis of presupposition triggers in english journalistic texts. Of College Of Education For Women, 21(2):523–551. [find](https://scholar.google.com/scholar?q=Layth+Muthana+Khaleel%2E+2010%2E+An+analysis+of+presupposition+triggers+in+english+journalistic+texts%2E+Of+College+Of+Education+For+Women%2C+21%282%29%3A523%E2%80%93551%2E)
8. Yang Liu, Zhiyuan Liu, Tat-Seng Chua, and Maosong Sun. 2015. Topical word embeddings. In AAAI Conference on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Yang+Liu%2C+Zhiyuan+Liu%2C+Tat%2DSeng+Chua%2C+and+Maosong+Sun%2E+2015%2E+Topical+word+embeddings%2E+In+AAAI+Conference+on+Artificial+Intelligence%2E)
9. Thang Luong, Hieu Pham, and Christopher D Manning. 2015. [Bilingual word representations with monolingual quality in mind](https://md.research.elamur.ai/free/en/papers/luong-2015-bilingual-word-representations-monolingual-quality/). In Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing, pages 151–159.
10. Mitchell P. Marcus, Mary A. Marcinkiewicz, and Beatrice Santorini. 1993. [Building a large annotated corpus of English: The Penn Treebank](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/). Computational Linguistics, 19(2):313–330. [↗](https://doi.org/10.21236/ada273556)
11. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. [Distributed representations of words and phrases and their compositionality](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/). In Advances in Neural Information Processing Systems, pages 3111–3119. [↗](https://doi.org/10.48550/arxiv.1310.4546)
12. Romain Paulus, Caiming Xiong, and Richard Socher. 2018. [A deep reinforced model for abstractive summarization](https://md.research.elamur.ai/free/en/papers/paulus-2017-deep-reinforced-model-abstractive-summarization/). In International Conference on Learning Representations, Vancouver, Canada. [↗](https://doi.org/10.48550/arxiv.1705.04304)
13. Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In EMNLP, volume 14, pages 1532– 1543.
14. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. [Squad: 100,000+ questions for machine comprehension of text](https://md.research.elamur.ai/free/en/papers/rajpurkar-2016-squad-100-000-questions-machine/). In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392. [↗](https://doi.org/10.48550/arxiv.1606.05250)

*Updated 24 October 2026*