Mova0.5 pre-release⌕
☰
home / docs / papers / English / Let's do it "again": A First Computational Approach to Detecting Adverbial Presupposition Triggers

Let's do it "again": A First Computational Approach to Detecting Adverbial Presupposition Triggers

What it is about

The task is to predict, from the preceding discourse, whether an adverbial presupposition trigger (too, again, also, still, yet) belongs on a given head word. The adverb is removed and the model sees up to 50 tokens before the head plus the rest of the sentence. Positive samples come from the Penn Treebank and Gigaword. Negatives are contexts with the same governor but no adverb, so the governor alone gives no clue; the excess sense of too (governor an adjective or adverb, «too far») is filtered out. A logistic regression on bigrams is barely above chance except for too and yet. A BiLSTM with a parameter-free self-attention pooling (weighted pooling over a token-by-token matching matrix) reaches 76% on PTB and 82% on Gigaword also, but only about 60% on again, still and the pooled set. The analysis shows that the cue is a recurring event or entity earlier in the text («continue» licensing still).

Ideas

For Mova

33. Implicature and presupposition §6.1–6.3 (triggers, what Mova computes, licensing); prag/src/infer.rs (presuppositions), world/src/talk.rs; measure: per-adverb accuracy on the governor-controlled set against the majority baseline.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/p18-1256 · arXiv 1806.04262

@inproceedings{cianflone2018let,
  title = {{Let's do it "again": A First Computational Approach to Detecting Adverbial Presupposition Triggers}},
  author = {Cianflone, Andre and Feng, Yulan and Kabbara, Jad and Cheung, Jackie Chi Kit},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2018},
  doi = {10.18653/v1/p18-1256},
  eprint = {1806.04262},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/p18-1256}
}

References

34 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Advances in Neural Information Processing Systems (NIPS 2015), pages 649–657, Montreal, Canada. find
  2. David I. Beaver and Bart Geurts. 2014. Presupposition. In Edward N. Zalta, editor, The Stanford Encyclopedia of Philosophy, winter 2014 edition. Metaphysics Research Lab, Stanford University. find
  3. R. Blutner, H. Zeevat, K. Bach, A. Bezuidenhout, R. Breheny, S. Glucksberg, F. Happé, F. Recanati, and D. Wilson. 2003. Optimality Theory and Pragmatics. Palgrave Studies in Pragmatics, Language and Cognition. Palgrave Macmillan UK. find
  4. Yiming Cui, Zhipeng Chen, Si Wei, Shijin Wang, Ting Liu, and Guoping Hu. 2017. Attention-overattention neural networks for reading comprehension. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 593–602. find
  5. G. R. Miller E. B. Coleman. 1968. A measure of information gained during prose learning. Reading Research Quarterly, 3(3):369–386. find
  6. Joseph W. Culhane Earl F. Rankin. 1969. Comparable cloze and multiple-choice comprehension test scores. Journal of Reading, 13(3):193–198. find
  7. Gottlob Frege. 1892. Über sinn und bedeutung. Zeitschrift für Philosophie und philosophische Kri-tik, 100:25–50. find
  8. David Graff, Junbo Kong, Ke Chen, and Kazuaki Maeda. 2007. English gigaword third edition. Technical report, Linguistic Data Consortium. find
  9. Alex Graves. 2013. Generating sequences with recurrent neural networks. CoRR, abs/1308.0850. ↗
  10. Felix Hill, Antoine Bordes, Sumit Chopra, and Jason Weston. 2015. The goldilocks principle: Reading children’s books with explicit memory representations. CoRR, abs/1511.02301. ↗
  11. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation, 9(8):1735–1780. find
  12. 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
  13. Qiang Kang. 2012. The use of too as a pragmatic presupposition trigger. Canadian Social Science, 8(6):165–169. find
  14. David Kaplan. 1970. What is Russell’s theory of descriptions? In Wolfgang Yourgrau and Allen D. Breck, editors, Physics, Logic, and History, pages 277–295. Plenum Press. find
  15. Layth Muthana Khaleel. 2010. An analysis of presupposition triggers in english journalistic texts. Of College Of Education For Women, 21(2):523–551. find
  16. Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1746–1751, Doha, Qatar. find
  17. Diederik Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceeding of the 2015 International Conference on Learning Representation (ICLR 2015), San Diego, California. find
  18. Razvan Pascanu, Tomas Mikolov, and Yoshua Bengio. 2013. On the difficulty of training recurrent neural networks. In Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28, ICML’13, pages 1310–1318. find
  19. Romain Paulus, Caiming Xiong, and Richard Socher. 2018. A deep reinforced model for abstractive summarization. In International Conference on Learning Representations, Vancouver, Canada. find
  20. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830. find
  21. Ellen Riloff and Michael Thelen. 2000. A rule-based question answering system for reading comprehension tests. In Proceedings of the 2000 ANLP/-NAACL Workshop on Reading Comprehension Tests As Evaluation for Computer-based Language Understanding Sytems - Volume 6, ANLP/NAACL-ReadingComp ’00, pages 13–19, Stroudsburg, PA, USA. Association for Computational Linguistics. find
  22. Nitish Srivastava, Geoffrey E Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. Journal of machine learning research, 15(1):1929–1958. find
  23. Robert Stalnaker. 1973. Presuppositions. Journal of philosophical logic, 2(4):447–457. find
  24. Dan Klein and Christopher D. Manning. 2002. A generative constituent-context model for improved grammar induction. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, pages 128–135, Stroudsburg, PA, USA. Association for Computational Linguistics. find
  25. Robert Stalnaker. 1998. On the representation of context. Journal of Logic, Language and Information, 7(1):3–19. find
  26. Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David Mc-Closky. 2014. The Stanford CoreNLP natural language processing toolkit. In Association for Computational Linguistics (ACL) System Demonstrations, pages 55–60. find
  27. Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, and Rob Fergus. 2015. End-to-end memory networks. In Advances in Neural Information Processing Systems 28, pages 2440–2448. find
  28. Mitchell P. Marcus, Mary A. Marcinkiewicz, and Beatrice Santorini. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2):313–330. find our card
  29. Gábor Melis, Chris Dyer, and Phil Blunsom. 2017. On the state of the art of evaluation in neural language models. CoRR, abs/1707.05589. ↗
  30. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems, pages 3111–3119. find
  31. Peter F. Strawson. 1950. 59(235):320–344. On referring. find
  32. Mind, Wilson L. Taylor. 1953. Cloze procedure: A new tool for measuring readability. Journalism Quarterly, 30(4):415. find
  33. Ashish Vaswani, Noam Shazeer, Niki Parmar, Llion Jones, Jakob Uszkoreit, Aidan N Gomez, and Ł ukasz Kaiser. 2017. Attention is all you need. In Advances in Neural Information Processing Systems 30, pages 5994–6004. find
  34. Javad Zare, Ehsan Abbaspour, and Mahdi Rajaee Nia. 2012. Presupposition trigger—a comparative analysis of broadcast news discourse. International Journal of Linguistics, 4(3):734–743. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/cianflone-2018-let-s-do-it-again/