抽象语义表示到文本(AMR-to-Text)生成的任务是给定AMR图,生成相同语义表示的文本。可以把此任务当作一个从源端AMR图到目标端句子的机器翻译任务。目前存在的一些方法都在探索如何更好地对图结构进行建模。然而,它们都存在一个未限定的问题,因为在生成阶段许多句法的决策并不受语义图的约束,从而忽略了句子内部潜藏的句法信息。为了明确考虑这一不足,该文提出一种直接而有效的方法,显式地在AMR-to-Text生成的任务中融入句法信息,并在Transformer和目前该任务最优性能的模型上进行了实验。实验结果表明,在现存的两份标准英文数据集LDC2015E86和LDC2017T10上,该方法取得了显著的性能提升。
Abstract
The task of AMR-to-Text generation is to generate text with the same semantic representation given an AMR graph. This task can be viewed as a translation task from the source AMR graph to the target sentence. To capture the syntactic information hidden within the sentence, this paper proposes a direct and effective method of integrating syntactic information in the AMR-to-Text task. Experiments on Transformer and the top-performed model the task show that, on the two existing standard English data sets LDC2015E86 and LDC2017T10, both have achieved significant improvements.
关键词
AMR-to-Text生成 /
句法决策 /
语义约束 /
融入句法信息
{{custom_keyword}} /
Key words
AMR-to-Text generation /
syntactic decision /
semantic constraints /
incorporate syntactic information
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Banarescu L, Bonial C, Cai S, et al. Abstract meaning representation for sembanking[C]//Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse,2013: 178-186.
[2] Tamchyna A, Quirk C, Galley M. A discriminative model for semantics-to-string translation[C]//Proceedings of the 1st Workshop on Semantics Machine Translation,2015: 30-36.
[3] Mitra A, Baral C. Addressing a question answering challenge by combining statistical[C]//Proceedings of 39th AAAI Conference on Artificial Intelligence,2016.
[4] Li X, Nguyen T, Cao K, et al. Improving event detection with abstract meaning representation[C]//Proceedings of the 1st Workshop on Computing News Storylines, 2015: 11-15.
[5] Pourdamghani N, Knight K, Hermjakob U. Generating English from abstract meaning representations[C]//Proceedings of the 9th International Natural Language Generation Conference, 2016: 21-25.
[6] Song L, Peng X,Zhang Y, et al. AMR-to-Text generation with synchronous node replacement grammar[C]//Proceedings of the ACL, 2017: 7-13.
[7] Flanigan J, Dyer C, Smith N, et al. Generation from abstract meaning representation using tree transducers[C]//Proceedings of the NAACL, 2016: 731-739.
[8] Konstas I, Iyer S, Yatskar M, et al. Neural {AMR}: sequence-to-sequence models for parsing and generation[C]//Proceedings of the ACL, 2017: 146-157.
[9] Beck D, Haffari G, Cohn T. Graph-to-sequence learning using gated graph neural networks[C]//Proceedings of the ACL, 2018: 273-283.
[10] Song L, Zhang Y, Wang Z, et al.A graph-to-sequence model for AMR-to-Text generation[C]//Proceedings of the ACL, 2018: 1616-1626.
[11] Damonte M, Cohen S. Structural neural encoders for {AMR}-to-text generation[C]//Proceedings of the NAACL, 2019: 3649-3658.
[12] Guo Z, Zhang Y, Teng Z, et al. Densely connected graph convolutional networks for graph-to-sequence learning[J]. Transactions of the Association of Computational Linguistics, 2019, 7: 297-312.
[13] Zhu J, Li J, Zhu M, et al. Modeling graph structure in transformer for better AMR-to-Text generation[C]//Proceedings of the EMNLP, 2019: 5458-5467.
[14] Li J, Xiong D,Tu Z. Modeling source syntax for neural machine translation[C]//Proceedings of the ACL, 2017: 688-697.
[15] Song L, Zhang Y, Peng X. AMR-to-Text generation as a traveling salesman problem[C]//Proceedings of the EMNLP, 2016: 2084-2089.
[16] Sutskever I, Vinyals O, Le Q. Sequence to sequence learning with neural networks[C]//Proceedings of the 27th International conference on Neural Information Processing Systems, 2014: 3104-3112.
[17] Cao K, Clark S. Factorising AMR generation through syntax[C]//Proceedings of the NAACL, 2019: 2157-2163.
[18] Shaw P, Uszkoreit J, Vaswani A. Self-attention with relative position representations[C]//Proceedings of the NAACL, 2018: 464-468.
[19] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the NIPS, 2017: 5998-6008.
[20] Kalchbrenner N,Grefenstette E,Blunsom P. A cvonvolutional neural network for modelling sentences[C]//Proceedings of the ACL, 2014: 655-665.
[21] Gulcehre C, Ahn S, Nallapati R. Pointing the unknown words[C]//Proceedings of the ACL, 2016: 140-149.
[22] Sennrich R, Haddow B, Birch A. Neural machine translation of rare words with wubword units[C]//Proceedings of the ACL, 2016: 1715-1725.
[23] Vinyals O, Kaiser L, Koo T, et al. Grammar as a foreign language[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems, 2015: 2773-2781.
[24] Manning C, Surdeanu M, Bauer J, et al. The Stanford CoreNLP natural language processing tooklkit[C]//Proceedings of the ACL, 2014: 55-60.
[25] Ge D, Li J, Zhu M, et al. Modeling source syntax and semantics for neural AMR parsing[C]//Proceedings of the IJCAI, 2019: 4975-4981.
[26] Klein G, Kim Y, Deng Y, et al. OpenNMT: open-source toolkit for neural machine translation[C]//Proceedings of the ACL, System Demonstrations, 2017: 67-72.
[27] Kingma D, Ba J. Adam: a method for stochastic optimization[C]//Proceedings of the ICLR, 2015.
[28] Papineni K, Roukos S, Todd W, et al. BLEU: a method for automatic evaluation of machine translation[C]//Proceedings of the ACL, 2002: 311-318.
[29] Banerjee S, Lavie A. METEOR: an automatic metric for MT evaluation with improved correlation with human judgments[C]//Proceedings of the ACL, 2005: 65-72.
[30] Popovi M. chrF++: words helping character n-grams[C]//Proceedings of the WMT, 2017: 612-618.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61876120)
{{custom_fund}}
PDF(1635 KB)
