Elamur Research⌕
☰
home / papers / 2023 / Chinese Idiom Paraphrasing

Chinese Idiom Paraphrasing

Summary

Chinese idioms (chengyu), usually four characters long, carry figurative, non-compositional meanings. This makes them hard for children, non-native speakers and NLP systems such as machine translation. The authors introduce a new task, Chinese Idiom Paraphrasing (CIP). It rewrites a sentence containing an idiom into a fluent sentence with the same meaning and no idiom, and is framed as a specialized form of paraphrase generation.

No supervised data existed, so the authors built a large benchmark through human–machine collaboration. They split a Chinese–English parallel corpus using an idiom list. An English-to-Chinese MT model, trained only on idiom-free pairs, then re-translated the English side of the idiom-bearing pairs. This produced pseudo-parallel pairs, which native speakers reviewed and corrected.

The authors compare LSTM, Transformer and mT5 Seq2Seq baselines with their own infill-based model on mT5. This model regenerates only the idiom span from its context rather than the whole sentence. It beat the baselines. Used as a preprocessing step, it also improved Google Translate output. CIP could therefore support downstream Chinese NLP and reading accessibility.

Key points

  • The CIP dataset has 115,529 sentence pairs covering 8,421 idioms. It was built with a three-stage pipeline: corpus split, MT-based pseudo-pair generation, then human revision.
  • The in-domain test set contains idioms never seen in training, which tests generalization to unfamiliar expressions.
  • The baselines are LSTM-based, Transformer-based and mT5-based Seq2Seq models. The proposed Infill method fine-tunes mT5 to reconstruct the paraphrase of masked idiom spans.
  • All learned models remove idioms from about 90% of sentences. Case studies show LSTM and Transformer often keep parts of unseen idioms. Infill yields more accurate contextual interpretations than full-sentence mT5 generation.
  • The dataset and baselines are open-source on GitHub (jpqiang/Chinese-Idiom-Paraphrasing). The paper appeared in TACL vol. 11, pp. 740–754, 2023.

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

Fields: Machine translation · Natural language processing

Cited by

15 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 14 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/tacl_a_00572

@article{qiang2023chinese,
  title = {{Chinese Idiom Paraphrasing}},
  author = {Qiang, Jipeng and Li, Yang and Zhang, Chaowei and Li, Yun and Zhu, Yi and Yuan, Yunhao and Wu, Xindong},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2023},
  doi = {10.1162/tacl\_a\_00572},
  url = {https://doi.org/10.1162/tacl_a_00572}
}

References

34 references, 6 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 3rd International Conference on Learning Representations, ICLR 2015. ↗ our card
  2. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation, 9(8):1735–1780. https://doi.org/10 .1162/neco.1997.9.8.1735, PubMed: 9377276 ↗
  3. Ond rej Bojar, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Philipp Koehn, and Christof Monz. 2018. Findings of the 2018 conference on machine translation (wmt18). In Proceedings of the Third Conference on Machine Translation, Volume 2: Shared Task Papers, pages 272–307, Belgium, Brussels. Association for Computational Linguistics. https://doi.org/10 .18653/v1/W18-6401 ↗ our card
  4. Zhiying Jiang, Boliang Zhang, Lifu Huang, and Heng Ji. 2018. Chengyu cloze test. In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 154–158. find
  5. Shrey Desai and Greg Durrett. 2020. Calibration of pre-trained transformers. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 295–302, Online. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.21 ↗
  6. Sora Kadotani, Tomoyuki Kajiwara, Yuki Arase, and Makoto Onizuka. 2021. Edit distance based curriculum learning for paraphrase generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 229–234. https://doi.org/10.18653/v1/2021 .acl-srw.24 ↗
  7. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language Diederik P. Kingma, and Jimmy Ba. 2015. A method for stochastic optimization. https://doi.org/10.48550/arXiv.2203.16634 ↗
  8. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics. find
  9. Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, and Michael Auli. 2019. fairseq: A fast, extensible toolkit for sequence modeling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 48–53. https://doi.org/10 .18653/v1/N19-4009 ↗ our card
  10. Alisa Liu, Swabha Swayamdipta, Noah A. Smith, and Yejin Choi. 2022. WANLI: Worker and AI collaboration for natural language inference dataset creation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6826–6847, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find our card
  11. 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. https://doi.org/10.3115/1073083.1073135 ↗ our card
  12. Yuanchao Liu, Bo Pang, and Bingquan Liu. 2019. Neural-based Chinese idiom recommendation for enhancing elegance in essay writing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5522–5526. Florence, Italy. Association for Computational Linguistics. https://doi.org/10.18653/v1/P19-1552 ↗
  13. Xinyu Lu, Jipeng Qiang, Yun Li, Yunhao Yuan, and Yi Zhu. 2021. An unsupervised method for building sentence simplification corpora in multiple languages. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 227–237, Punta Cana, Dominican Republic. Association for Computational Linguistics. https://doi.org/10.18653/v1/2021 .findings-emnlp.22 ↗
  14. Maria Pershina, Yifan He, and Ralph Grishman. 2015. Idiom paraphrases: Seventh heaven vs cloud nine. In Proceedings of the First Workshop on Linking Computational Models of Lexical, Sentential and Discourse-level Semantics, pages 76–82. Lisbon, Portugal. Association for Computational Linguistics. https://doi.org/10.18653/v1/W15-2709 ↗
  15. Jipeng Qiang, Xinyu Lu, Yun Li, Yun-Hao Yuan, and Xindong Wu. 2021. Chinese lexical simplification. IEEE/ACM Transactions on Audio, Speech, and Language Processing, pages 1819–1828. https://doi.org/10 .1109/TASLP.2021.3078361 ↗
  16. Kathleen R. McKeown. 1979. Paraphrasing using given and new information in a question-answer system. In 17th Annual Meeting of the Association for Computational Linguistics, pages 67–72, La Jolla, California, USA. Association for Computational Linguistics. find
  17. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21:1–67. ↗
  18. Yuxian Meng, Xiang Ao, Qing He, Xiaofei Sun, Qinghong Han, Fei Wu, Chun Fan, and Jiwei Li. 2021. ConRPG: Paraphrase generation using contexts as regularizer. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2551–2562. https://doi.org/10.18653/v1/2021 .emnlp-main.199 ↗
  19. Yutong Shao, Rico Sennrich, Bonnie Webber, and Federico Fancellu. 2018. Evaluating machine translation performance on Chinese idioms with a blacklist method. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). find
  20. Marie Meteer and Varda Shaked. 1988. Strategies for effective paraphrasing. In COL-ING Budapest 1988 Volume 2: International Conference on Computational Linguistics, pages 431–436. https://doi.org/10 .3115/991719.991724 ↗
  21. Tianxiao Shen, Victor Quach, Regina Barzilay, and Tommi Jaakkola. 2020. Blank language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5186–5198. find
  22. Minghuan Tan and Jing Jiang. 2021. Learning and evaluating Chinese idiom embeddings. find
  23. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1387–1396. reconstruction. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1234–1243. find
  24. Wilson L. Taylor. 1953. ‘‘Cloze procedure’’: A new tool for measuring readability. Journalism Quarterly, 30(4):415–433. https://doi.org/10.1177/107769905303000401 ↗
  25. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 483–498, Online. Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.naacl-main.41 ↗
  26. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 5998–6008. find
  27. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38–45, Online. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-demos.6 ↗ our card
  28. Najam Zaidi, Trevor Cohn, and Gholamreza Haffari. 2020. Decoding as dynamic programming for recurrent autoregressive models. In International Conference on Learning Representations. find
  29. Yuhui Zhang, Chenghao Yang, Zhengping Zhou, and Zhiyuan Liu. 2020. Enhancing transformer with sememe knowledge. In Proceedings of the 5th Workshop on Representation Learning for NLP, pages 177–184, Online. Association for Computational Linguistics. find
  30. Chujie Zheng, Minlie Huang, and Aixin Sun. 2019. ChID: A large-scale Chinese IDiom dataset for cloze test. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 778–787. https://doi.org/10.18653/v1/P19-1075 ↗
  31. Yanling Xiao, Lemao Liu, Guoping Huang, Qu Cui, Shujian Huang, Shuming Shi, and Jiajun Chen. 2022. BiTIIMT: A bilingual text-infilling method for interactive machine translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1958–1969, Dublin, Ireland. Association for Computational Linguistics. https://doi.org/10 .18653/v1/2022.acl-long.138 ↗
  32. Jianing Zhou and Suma Bhat. 2021. Paraphrase generation: A survey of the state of the art. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5075–5086. https://doi.org/10 .18653/v1/2021.emnlp-main.414 ↗
  33. Wanrong Zhu, Zhiting Hu, and Eric P. Xing. 2019. Text infilling. CoRR, abs/1901.00158. https://doi.org/10.48550/arXiv.1901 .00158 ↗
  34. Xuhang Xie, Xuesong Lu, and Bei Chen. 2022. Multi-task learning for paraphrase generation with keyword and part-of-speech find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/qiang-2023-chinese-idiom-paraphrasing/