Elaborative Simplification as Implicit Questions Under Discussion

What it is about

When editors simplify news for children (Newsela), they often add sentences that explain rather than shorten. The paper treats each such elaboration as the explicit answer to an implicit question and builds ELABQUD: 1,299 elaborations with a crowd-written QUD, the anchor sentence it arose from, and the target span it explains. The anchor is almost always the sentence right before; targets are mostly nouns (31% contain proper nouns) but half include a verb, and they are markedly rarer words than the rest of the text. The questions ask for a concept definition (34%), an example (16%), a consequence (14%), a cause (12%) or a procedure (8%). Question generators trained on earlier QUD data (DCQA, which sees the answer; INQUISITIVE, which does not) were fine-tuned on ELABQUD, and the generated questions, used as prompts, gave GPT-3 elaborations judged much better than unprompted ones.

Ideas

• I1. Audit Mova's own lesson texts the way editors elaborate: a rare content word (low frequency in Mova's word counts) that is not explained within the next two sentences by a definition-like frame (Fact(is a), an apposition, «that is», «which means») is a candidate gap. List them per course and check with world knowledge diagnose whether questions about those words fail more often; lessons are made by the teacher, so the list goes back into lesson writing.
• I2. Link an elaboration to its anchor in the frame reader: a definition, example («for example», «such as») or consequence sentence right after a sentence containing its target attaches to the target's frame or entity, with the paper's question type as the link label. «What is a raft?» or «Give an example of…» can then follow the link. Measure on course questions of these types.
• I3. In world/src/qud.rs, default the anchor of an accommodated QUD to the previous sentence (the paper's data shows that is nearly always right) and type the candidate QUD by the paper's top five (concept, example, consequence, cause, procedure) using surface cues; reject a type whose answer cue is absent.

For Mova

36. Discourse relations and coherence §9 and §11.5 (QUD stack), 37-register-and-variation.md (simplified and school registers). Code: world/src/qud.rs, prag/src/frames.rs (elaboration links), world/src/knowledge.rs and the course lessons (gap audit). Measures: unexplained rare words per course; course questions about defined words answered right.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2023.emnlp-main.336

@inproceedings{wu2023elaborative,
  title = {{Elaborative Simplification as Implicit Questions Under Discussion}},
  author = {Wu, Yating and Sheffield, William and Mahowald, Kyle and Li, Junyi Jessy},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
  year = {2023},
  doi = {10.18653/v1/2023.emnlp-main.336},
  url = {https://doi.org/10.18653/v1/2023.emnlp-main.336}
}

References

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

1. Sweta Agrawal and Marine Carpuat. 2022. An imitation learning curriculum for text editing with non-autoregressive models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7550–7563. find
2. Fernando Alva-Manchego, Carolina Scarton, and Lucia Specia. 2020. Data-driven sentence simplification: Survey and benchmark. Computational Linguistics, 46(1):135–187. find
3. Ron Artstein and Massimo Poesio. 2008. Inter-coder agreement for computational linguistics. Computational linguistics, 34(4):555–596. find
4. Katherine Atwell, Junyi Jessy Li, and Malihe Alikhani. 2021. Where are we in discourse relation recognition? In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 314–325. find
5. Anton Benz and Katja Jasinskaja. 2017. Questions under discussion: From sentence to discourse. Discourse Processes, 54(3):177–186. find
6. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems, volume 33, pages 1877–1901. find
7. Marc Brysbaert, Boris New, and Emmanuel Keuleers. 2012. Adding part-of-speech information to the subtlex-us word frequencies. Behavior research methods, 44(4):991–997. find
8. Shuyang Cao and Lu Wang. 2021. Controllable open-ended question generation with a new question type ontology. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6424–6439. https://www.tacc.utexas.edu ↗
9. John Carroll, Guido Minnen, Yvonne Canning, Siobhan Devlin, and John Tait. 1998. Practical simplification of english newspaper text to assist aphasic readers. In Proceedings of the AAAI-98 Workshop on Integrating Artificial Intelligence and Assistive Technology, pages 7–10. find
10. Najoung Kim, Song Feng, Chulaka Gunasekara, and Luis Lastras. 2020. Implicit discourse relation classification: We need to talk about evaluation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5404– 5414. find our card
11. Jerwin Jan S Damay, Gerard Jaime D Lojico, Kimberly Amanda L Lu, D Tarantan, and E Ong. 2006. SIMTEXT: Text simplification of medical literature. In Proceedings of the 3rd National Natural Language Processing Symposium-Building Language Tools and Resources, pages 34–38. find
12. Wei-Jen Ko, Te-yuan Chen, Yiyan Huang, Greg Durrett, and Junyi Jessy Li. 2020. Inquisitive question generation for high level text comprehension. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6544–6555. find our card
13. Jan De Belder and Marie-Francine Moens. 2010. Text simplification for children. In Prroceedings of the SIGIR workshop on accessible search systems, pages 19–26. find
14. Wei-Jen Ko, Cutter Dalton, Mark Simmons, Eliza Fisher, Greg Durrett, and Junyi Jessy Li. 2022. Discourse comprehension: A question answering framework to represent sentence connections. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11752– 11764. find
15. Kordula De Kuthy, Nils Reiter, and Arndt Riester. 2018. Qud-based annotation of discourse structure and information structure: Tool and evaluation. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation. find our card
16. Ashwin Devaraj, Iain Marshall, Byron C Wallace, and Junyi Jessy Li. 2021. Paragraph-level simplification of medical texts. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4972–4984. find
17. Yue Dong, Zichao Li, Mehdi Rezagholizadeh, and Jackie Chi Kit Cheung. 2019. Editnts: An neural programmer-interpreter model for sentence simplification through explicit editing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3393–3402. find
18. Soojeong Eom, Markus Dickinson, and Rebecca Sachs. 2012. Sense-specific lexical information for reading assistance. In Proceedings of the Seventh Workshop on Building Educational Applications Using NLP, pages 316–325. find
19. Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin, 76(5):378. find
20. Christoph Hesse, Anton Benz, Maurice Langner, Felix Theodor, and Ralf Klabunde. 2020. Annotating quds for generating pragmatically rich texts. In Proceedings of the Workshop on Discourse Theories for Text Planning, pages 10–16. find
21. Sasikiran Kandula, Dorothy Curtis, and Qing Zeng-Treitler. 2010. A semantic and syntactic text simplification tool for health content. In AMIA annual symposium proceedings, pages 366–370. find
22. Andrew Kehler and Hannah Rohde. 2017. Evaluating an expectation-driven question-under-discussion model of discourse interpretation. Discourse Processes, 54(3):219–238. ↗
23. Wei-Jen Ko, Yating Wu, Cutter Dalton, Dananjay Srinivas, Greg Durrett, and Junyi Jessy Li. 2023. Discourse analysis via questions and answers: Parsing dependency structures of questions under discussion. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11181–11195. find our card
24. Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D. Manning, Christopher R’e, Diana Acosta-Navas, Drew A. Hudson, E. Zelikman, Esin Durmus, Faisal Ladhak, Frieda Rong, Hongyu Ren, Huaxiu Yao, Jue Wang, Keshav Santhanam, Laurel J. Orr, Lucia Zheng, Mert Yuksekgonul, Mirac Suzgun, Nathan S. Kim, Neel Guha, Niladri S. Chatterji, O. Khattab, Peter Henderson, Qian Huang, Ryan Chi, Sang Michael Xie, Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas F. Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, and Yuta Koreeda. 2022. Holistic evaluation of language models. ArXiv, abs/2211.09110. ↗
25. Shashi Narayan, Joshua Maynez, Reinald Kim Amplayo, Kuzman Ganchev, Annie Louis, Fantine Huot, Anders Sandholm, Dipanjan Das, and Mirella Lapata. 2023. Conditional generation with a question-answering blueprint. Transactions of the Association for Computational Linguistics, 11:974– 996. ↗
26. Benjamin Newman, Luca Soldaini, Raymond Fok, Arman Cohan, and Kyle Lo. 2023. A controllable QA-based framework for decontextualization. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. find
27. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318. find our card
28. Kathryn Parker and Craig Chaudron. 1987. The effects of linguistic simplifications and elaborative modifications on l2 comprehension. Technical report, University of Hawaii working papers in ESL. find
29. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The penn discourse treebank 2.0. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08). find our card
30. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Technical Report. find
31. Justus J. Randolph. 2005. Free-marginal multirater kappa (multirater k[free]): An alternative to fleiss’ fixed-marginal multirater kappa. find
32. Luz Rello, Ricardo Baeza-Yates, Laura Dempere-Marco, and Horacio Saggion. 2013. Frequent words improve readability and short words improve understandability for people with dyslexia. In IFIP Conference on Human-Computer Interaction, pages 203–219. find
33. Bonnie Webber, Rashmi Prasad, Alan Lee, and Aravind Joshi. 2019. The penn discourse treebank 3.0 annotation manual. Philadelphia, University of Pennsylvania, 35:108. find our card
34. Matthijs Westera, Laia Mayol, and Hannah Rohde. 2020. TED-Q: TED talks and the questions they evoke. In Proceedings of The 12th Language Resources and Evaluation Conference, pages 1118– 1127. find
35. Wei Xu, Chris Callison-Burch, and Courtney Napoles. 2015. Problems in current text simplification research: New data can help. Transactions of the Association for Computational Linguistics, 3:283–297. find
36. Yasukata Yano, Michael H Long, and Steven Ross. 1994. The effects of simplified and elaborated texts on foreign language reading comprehension. Language learning, 44(2):189–219. find
37. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations. find
38. Craige Roberts. 2012. Information structure: Towards an integrated formal theory of pragmatics. Semantics and pragmatics, 5:6–1. ↗ our card
39. Advaith Siddharthan. 2014. A survey of research on text simplification. ITL-International Journal of Applied Linguistics, 165(2):259–298. find
40. Neha Srikanth and Junyi Jessy Li. 2021. Elaborative simplification: Content addition and explanation generation in text simplification. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 5123–5137. find
41. Renliang Sun, Hanqi Jin, and Xiaojun Wan. 2021. Document-level text simplification: Dataset, criteria and baseline. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7997–8013. find
42. Zachary W Taylor, Maximus H Chu, and Junyi Jessy Li. 2022. Text simplification of college admissions instructions: A professionally simplified and verified corpus. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6505–6515. find
43. Jan Van Kuppevelt. 1995. Discourse structure, topicality and questioning. Journal of linguistics, 31(1):109–147. ↗
44. Christiane Von Stutterheim and Wolfgang Klein. 1989. Referential movement in descriptive and narrative discourse. In North-Holland Linguistic Series: Linguistic Variations, volume 54, pages 39–76. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/wu-2023-elaborative-simplification-as-implicit-questions/