Developing the System for Automatic Summarization of Scientific Texts.
Bibliographic record
Abstract
1. Ананьева М. И., Кобозева М. В. Разработка корпуса текстов на русском языке с разметкой на основе теории риторических структур // Компьютерная лингвистика и интеллектуальные технологии: по материалам ежегодной Международной конференции «Диалог». М., 2016. URL: www.dialog-21.ru/media/3460/ananyeva.pdf 2. Marcu D. Improving summarization through rhetorical parsing tuning // VI Workshop on Very Large Corpora. 1998. P. 206–215. 3. Hovy E., Lin Ch.-Y. Automated text summarization and the SUMMARIST system // Proc. of the TIPSTER Text Program. 1998. P. 197–214. 4. Teufel S., Moens M. Summarizing scientific articles: experiments with relevance and rhetorical status // Computational Linguistics. 2002. Vol. 28 (4). P. 409–445. 5. Bosma W. Query-Based Summarization using Rhetorical Structure Theory // 15th Meeting of CLIN. 2005. P. 29–44. 6. Huspi S. H. Improving Single Document Summarization in a Multi-Document Environment. PhD Thesis. Melbourne, Australia: RMIT University, 2017. 190 p. 7. Mithun S. Exploiting rhetorical relations in blog summarization. PhD Thesis. Montreal, Canada: Concordia University, 2012. 230 p. 8. Тревгода С. А. Методы и алгоритмы автоматического реферирования текста на основе анализа функциональных отношений: Дис. … канд. техн. наук. СПб., 2009. 157 с. 9. Осминин П. Г. Построение модели реферирования и аннотирования научно-технических текстов, ориентированной на автоматический перевод: Дис. … канд. филол. наук. Челябинск, 2016. 239 с. 10. Batura T. V., Bakiyeva A. M., Yerimbetova A. S. Mit'kovskaya M. V. Semenova N. A. Methods of constructing natural language analyzers based on Link Grammar and rhetorical structure theory // Bulletin of the Novosibirsk Computing Center. Series: Computer Science. 2016. Is. 40. P. 37–51. 11. Бакиева А. М., Батура Т. В. Исследование применимости теории риторических структур для автоматической обработки научно-технических текстов // Cloud of Science. Вып. 4, № 3. С. 450–464. 12. Pisarevskaya D., Ananyeva M., Kobozeva M., Nasedkin A., Nikiforova S., Pavlova I., Shelepov A. Towards building a discourse-annotated corpus of Russian // Computational Linguistics and Intellectual Technologies. 2017. Iss. 16 (23). Vol. 1. P. 194–204. 13. Vorontsov K., Frei O., Apishev M., Romov P., Dudarenko M. BigARTM: Open Source Library for Regularized Multimodal Topic Modeling of Large Collections // International Conference on Analysis of Images, Social Networks and Texts (AIST). Ekaterinburg, Russia, 2015. P. 370–384. 14. Mann W., Thompson C. Rhetorical structure theory: Toward a functional theory of text organization // Text-Interdisciplinary Journal for the Study of Discourse. 1988. Vol. 8. No. 3. P. 243–281. 15. Blei D. M., Lafferty J. D. Visualizing Topics with Multi-Word Expressions // Semantic Scholar. 2009. URL: https://arxiv.org/pdf/0907.1013.pdf 16. Батура Т. В., Стрекалова С. Е. Подход к построению расширенных тематических моделей текстов на русском языке // Вестн. НГУ. Серия: Информационные технологии. 2018. T. 16, № 2. С. 5–18. 17. Vorontsov K. Welcome to BigARTM’s documentation! 2015. URL: http://bigartm.read thedocs.io/en/stable/ 18. Das D., Martins A. A. Survey on Automatic Text Summarization // Literature Survey for the Language and Statistics II course at CMU. 2007. P. 192–195. 19. Lin Ch. Y. ROUGE: A Package for Automatic Evaluation of Summaries // Workshop On Text Summarization Branches Out. 2004. P. 74–81. 20. Zhang J. J., Chan H. Y., Fung P. Improving lecture speech summarization using rhetorical information // IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU). 2007. P. 195–200.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.004 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".