Mova0.5 pre-release⌕
☰
home / docs / papers / Machine translation / T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation

T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation

What it is about

T-STAR uses AMR graphs as a style-agnostic intermediate: a text-to-AMR encoder is fine-tuned on synthetic stylised versions of AMR 3.0 sentences, and a per-style AMR-to-text decoder renders the graph in each target style. Two claims are tested. First, content is kept better: about 15% higher content preservation than the state of the art, for roughly 3% less style accuracy. Second, hallucination falls: from 90,000 human ratings, up to half as many outputs hallucinate compared with the state of the art. A probe supports the first claim: a style classifier trained on AMR input does worse than one trained on the original or paraphrased text, so the graph carries less style. An iterative variant, which retrains the encoder on its own outputs, wins on weighted style accuracy in the Shakespeare author-imitation task in both directions. Errors are sorted into hallucination, semantic drift and incompleteness, and content is scored by a word-mover distance over content words after stop-word removal.

Ideas

For Mova

The style probe (I1) and the error taxonomy (I2) are measures for tools/translate and tools/roundtrip, and they measure open problem 1 (reader noise) and the lexicon noise of problem 2. The neural encoder and the learned decoder are not for Mova; the counted probes are.

Topics: Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.emnlp-main.602

@inproceedings{jangra2022t,
  title = {{T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation}},
  author = {Jangra, Anubhav and Nema, Preksha and Raghuveer, Aravindan},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
  year = {2022},
  doi = {10.18653/v1/2022.emnlp-main.602},
  url = {https://doi.org/10.18653/v1/2022.emnlp-main.602}
}

References

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

  1. Xuefeng Bai, Yulong Chen, and Yue Zhang. 2022. Graph pre-training for amr parsing and generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6001–6015. find
  2. Xuefeng Bai, Linfeng Song, and Yue Zhang. 2020. Online back-parsing for amr-to-text generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1206–1219. find
  3. Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. Abstract Meaning Representation for sembanking. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pages 178–186, Sofia, Bulgaria. Association for Computational Linguistics. find our card
  4. Michele Bevilacqua, Rexhina Blloshmi, and Roberto Navigli. 2021. One SPRING to rule them both: Symmetric AMR semantic parsing and generation without a complex pipeline. In Proceedings of AAAI. ↗
  5. Deng Cai and Wai Lam. 2020. AMR parsing via graph-sequence iterative inference. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1290–1301, Online. Association for Computational Linguistics. find
  6. Shu Cai and Kevin Knight. 2013. Smatch: an evaluation metric for semantic feature structures. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 748–752. find
  7. Yitao Cai, Yue Cao, and Xiaojun Wan. 2021. Revisiting pivot-based paraphrase generation: Language is not the only optional pivot. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4255–4268, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. ↗
  8. Yu Cheng, Zhe Gan, Yizhe Zhang, Oussama Elachqar, Dianqi Li, and Jingjing Liu. 2020. Contextual text style transfer. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2915–2924. find
  9. Mingkai Deng, Jianyu Wang, Cheng-Ping Hsieh, Yihan Wang, Han Guo, Tianmin Shu, Meng Song, Eric P Xing, and Zhiting Hu. 2022a. Rlprompt: Optimizing discrete text prompts with reinforcement learning. arXiv preprint arXiv:2205.12548. ↗
  10. Zhenyun Deng, Yonghua Zhu, Yang Chen, Michael Witbrock, and Patricia Riddle. 2022b. Interpretable amr-based question decomposition for multi-hop question answering. arXiv preprint arXiv:2206.08486. ↗
  11. William B. Dolan and Chris Brockett. 2005. Automatically constructing a corpus of sentential paraphrases. In Proceedings of the Third International Workshop on Paraphrasing (IWP2005). find
  12. Wenchao Du and Jeffrey Flanigan. 2021. Avoiding overlap in data augmentation for amr-to-text generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 1043–1048. ↗
  13. Angela Fan and Claire Gardent. 2020. Multilingual amr-to-text generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2889–2901. find
  14. Jeffrey Flanigan, Chris Dyer, Noah A. Smith, and Jaime Carbonell. 2016. CMU at SemEval-2016 task 8: Graph-based AMR parsing with infinite ramp loss. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 1202–1206, San Diego, California. Association for Computational Linguistics. find
  15. Jeffrey Flanigan, Sam Thomson, Jaime Carbonell, Chris Dyer, and Noah A. Smith. 2014. A discriminative graph-based parser for the Abstract Meaning Representation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1426– 1436, Baltimore, Maryland. Association for Computational Linguistics. find
  16. Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, and Rui Yan. 2017. Style transfer in text: Exploration and evaluation. CoRR, abs/1711.06861. ↗
  17. Hardy Hardy and Andreas Vlachos. 2018. Guided neural language generation for abstractive summarization using Abstract Meaning Representation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 768– 773, Brussels, Belgium. Association for Computational Linguistics. ↗
  18. Junxian He, Xinyi Wang, Graham Neubig, and Taylor Berg-Kirkpatrick. 2020. A probabilistic formulation of unsupervised text style transfer. CoRR, abs/2002.03912. ↗
  19. Vu Cong Duy Hoang, Philipp Koehn, Gholamreza Haffari, and Trevor Cohn. 2018. Iterative back-translation for neural machine translation. In Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pages 18–24, Melbourne, Australia. Association for Computational Linguistics. find
  20. Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2019. The curious case of neural text degeneration. In International Conference on Learning Representations. ↗
  21. Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P. Xing. 2017. Controllable text generation. CoRR, abs/1703.00955. ↗
  22. Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, and Rada Mihalcea. 2020. Deep learning for text style transfer: A survey. CoRR, abs/2011.00416. ↗
  23. Vineet John, Lili Mou, Hareesh Bahuleyan, and Olga Vechtomova. 2019. Disentangled representation learning for non-parallel text style transfer. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 424–434, Florence, Italy. Association for Computational Linguistics. find
  24. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. ↗
  25. Kevin Knight, Bianca Badarau, Laura Baranescu, Claire Bonial, Madalina Bardocz, Kira Griffitt, Ulf Hermjakob, Daniel Marcu, Martha Palmer, Tim O’Gorman, et al. 2021. Abstract meaning representation (amr) annotation release 3.0. find
  26. Kalpesh Krishna, John Wieting, and Mohit Iyyer. 2020. Reformulating unsupervised style transfer as paraphrase generation. CoRR, abs/2010.05700. ↗ our card
  27. Surabhi Kumari, Nikhil Jaiswal, Mayur Patidar, Manasi Patwardhan, Shirish Karande, Puneet Agarwal, and Lovekesh Vig. 2021. Domain adaptation for nmt via filtered iterative back-translation. In Proceedings of the Second Workshop on Domain Adaptation for NLP, pages 263–271. find
  28. Matt J. Kusner, Yu Sun, Nicholas I. Kolkin, and Kilian Q. Weinberger. 2015. From word embeddings to document distances. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, volume 37 of JMLR Workshop and Conference Proceedings, pages 957–966. JMLR.org. find
  29. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461. ↗
  30. Juncen Li, Robin Jia, He He, and Percy Liang. 2018. Delete, retrieve, generate: A simple approach to sentiment and style transfer. CoRR, abs/1804.06437. ↗ our card
  31. Kexin Liao, Logan Lebanoff, and Fei Liu. 2018. Abstract Meaning Representation for multi-document summarization. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1178–1190, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find
  32. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized BERT pretraining approach. CoRR, abs/1907.11692. ↗
  33. Yixin Liu, Graham Neubig, and John Wieting. 2020. On learning text style transfer with direct rewards. CoRR, abs/2010.12771. ↗
  34. Lajanugen Logeswaran, Honglak Lee, and Samy Bengio. 2018. Content preserving text generation with attribute controls. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, pages 5108–5118. ↗
  35. Fuli Luo, Peng Li, Jie Zhou, Pengcheng Yang, Baobao Chang, Zhifang Sui, and Xu Sun. 2019. A dual reinforcement learning framework for unsupervised text style transfer. CoRR, abs/1905.10060. ↗
  36. Xinyao Ma, Maarten Sap, Hannah Rashkin, and Yejin Choi. 2020. Powertransformer: Unsupervised controllable revision for biased language correction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pages 7426– 7441. Association for Computational Linguistics. find
  37. Aman Madaan, Amrith Setlur, Tanmay Parekh, Barnabás Póczos, Graham Neubig, Yiming Yang, Ruslan Salakhutdinov, Alan W. Black, and Shrimai Prabhumoye. 2020. Politeness transfer: A tag and generate approach. CoRR, abs/2004.14257. ↗
  38. David D McDonald and James Pustejovsky. 1985. A computational theory of prose style for natural language generation. In Second Conference of the European Chapter of the Association for Computational Linguistics. find
  39. Tong Niu and Mohit Bansal. 2018. Polite dialogue generation without parallel data. Trans. Assoc. Comput. Linguistics, 6:373–389. ↗
  40. 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, July 6-12, 2002, Philadelphia, PA, USA, pages 311–318. ACL. find our card
  41. Xiaochang Peng, Chuan Wang, Daniel Gildea, and Nianwen Xue. 2017. Addressing the data sparsity issue in neural AMR parsing. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 366–375, Valencia, Spain. Association for Computational Linguistics. find
  42. Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov, and Alan W Black. 2018. Style transfer through back-translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 866–876, Melbourne, Australia. Association for Computational Linguistics. find
  43. 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. ↗
  44. Bidisha Samanta, Mohit Agrawal, and NIloy Ganguly. 2021. A hierarchical VAE for calibrating attributes while generating text using normalizing flow. 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 2405–2415, Online. Association for Computational Linguistics. ↗
  45. Bidisha Samanta, Niloy Ganguly, and Soumen Chakrabarti. 2019. Improved sentiment detection via label transfer from monolingual to synthetic code-switched text. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3528–3537, Florence, Italy. Association for Computational Linguistics. find
  46. Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108. ↗
  47. Noam Shazeer and Mitchell Stern. 2018. Adafactor: Adaptive learning rates with sublinear memory cost. In International Conference on Machine Learning, pages 4596–4604. PMLR. ↗
  48. Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. Advances in neural information processing systems, 30. ↗ our card
  49. Yukai Shi, Sen Zhang, Chenxing Zhou, Xiaodan Liang, Xiaojun Yang, and Liang Lin. 2021. Gtae: Graph transformer–based auto-encoders for linguistic-constrained text style transfer. 12(3). ↗
  50. Ayush Singh and Ritu Palod. 2018. Sentiment transfer using seq2seq adversarial autoencoders. CoRR, abs/1804.04003. ↗
  51. Linfeng Song, Daniel Gildea, Yue Zhang, Zhiguo Wang, and Jinsong Su. 2019. Semantic neural machine translation using AMR. CoRR, abs/1902.07282. ↗ our card
  52. Linfeng Song, Yue Zhang, Zhiguo Wang, and Daniel Gildea. 2018. A graph-to-sequence model for amr-to-text generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1616– 1626. find
  53. Sandeep Subramanian, Guillaume Lample, Eric Michael Smith, Ludovic Denoyer, Marc’Aurelio Ranzato, and Y-Lan Boureau. 2018. Multiple-attribute text style transfer. CoRR, abs/1811.00552. ↗
  54. Akhilesh Sudhakar, Bhargav Upadhyay, and Arjun Maheswaran. 2019. ”transforming” delete, retrieve, generate approach for controlled text style transfer. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, pages 3267– 3277. Association for Computational Linguistics. find
  55. Sho Takase, Jun Suzuki, Naoaki Okazaki, Tsutomu Hirao, and Masaaki Nagata. 2016. Neural headline generation on Abstract Meaning Representation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1054–1059, Austin, Texas. Association for Computational Linguistics. find
  56. Alexey Tikhonov, Viacheslav Shibaev, Aleksander Nagaev, Aigul Nugmanova, and Ivan P Yamshchikov. 2019. Style transfer for texts: Retrain, report errors, compare with rewrites. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3936–3945. find
  57. Ke Wang, Hang Hua, and Xiaojun Wan. 2019. Controllable unsupervised text attribute transfer via editing entangled latent representation. CoRR, abs/1905.12926. ↗
  58. Wei Xu, Alan Ritter, Bill Dolan, Ralph Grishman, and Colin Cherry. 2012. Paraphrasing for style. In Proceedings of COLING 2012, pages 2899–2914, Mumbai, India. find our card
  59. The COLING 2012 Organizing Committee. find
  60. Tianming Wang, Xiaojun Wan, and Hanqi Jin. 2020. Amr-to-text generation with graph transformer. Transactions of the Association for Computational Linguistics, 8:19–33. ↗
  61. Ivan Yamshchikov, Viascheslav Shibaev, and Alexey Tikhonov. 2019a. Dyr bul shchyl. proxying sound symbolism with word embeddings. In Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP, pages 90–94, Minneapolis, USA. Association for Computational Linguistics. find
  62. Tianming Wang, Xiaojun Wan, and Shaowei Yao. 2021. Better amr-to-text generation with graph structure reconstruction. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pages 3919–3925. find
  63. Ivan P. Yamshchikov, Viacheslav Shibaev, Nikolay Khlebnikov, and Alexey Tikhonov. 2020. Style-transfer and paraphrase: Looking for a sensible semantic similarity metric. CoRR, abs/2004.05001. ↗
  64. John Wieting, Taylor Berg-Kirkpatrick, Kevin Gimpel, and Graham Neubig. 2019a. Beyond BLEU: training neural machine translation with semantic similarity. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pages 4344–4355. Association for Computational Linguistics. find
  65. John Wieting, Kevin Gimpel, Graham Neubig, and Taylor Berg-Kirkpatrick. 2019b. Simple and effective paraphrastic similarity from parallel translations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4602– 4608, Florence, Italy. Association for Computational Linguistics. ↗
  66. Ivan P Yamshchikov, Viacheslav Shibaev, Aleksander Nagaev, J ürgen Jost, and Alexey Tikhonov. 2019b. Decomposing textual information for style transfer. EMNLP-IJCNLP 2019, page 128. find
  67. Sheng Zhang, Xutai Ma, Kevin Duh, and Benjamin Van Durme. 2019. Amr parsing as sequence-to-graph transduction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 80–94. find
  68. Qiji Zhou, Yue Zhang, Donghong Ji, and Hao Tang. 2020. Amr parsing with latent structural information. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4306–4319. find
  69. Yu Wu, Yunli Wang, and Shujie Liu. 2020. A dataset for low-resource stylized sequence-to-sequence generation. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pages 9290–9297. AAAI Press. find
  70. Qingrong Xia, Zhenghua Li, Rui Wang, and Min Zhang. 2021. Stacked amr parsing with silver data. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4729–4738. find
  71. Dongqin Xu, Junhui Li, Muhua Zhu, Min Zhang, and Guodong Zhou. 2020a. Improving amr parsing with sequence-to-sequence pre-training. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2501–2511. find
  72. Jin Xu, Yinuo Guo, and Junfeng Hu. 2020b. Incorporate semantic structures into machine translation evaluation via UCCA. CoRR, abs/2010.08728. ↗ our card
  73. Jingjing Xu, Xu Sun, Qi Zeng, Xuancheng Ren, Xiaodong Zhang, Houfeng Wang, and Wenjie Li. 2018. Unpaired sentiment-to-sentiment translation: A cycled reinforcement learning approach. arXiv preprint arXiv:1805.05181. ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/jangra-2022-t-star-truthful-style-transfer/