{"type":"ScholarlyArticle","title":"Triple-to-Text Generation with an Anchor-to-Prototype Framework","authors":[{"name":"Ziran Li","slug":"ziran-li","given":"Ziran","family":"Li","affiliation":"Department of Computer Science and Technology , Tsinghua University; Tsinghua ShenZhen International Graduate School , Tsinghua University"},{"name":"Zibo Lin","slug":"zibo-lin","given":"Zibo","family":"Lin","affiliation":"Department of Computer Science and Technology , Tsinghua University; Tsinghua ShenZhen International Graduate School , Tsinghua University"},{"name":"Ning Ding","slug":"ning-ding","given":"Ning","family":"Ding","affiliation":"Department of Computer Science and Technology , Tsinghua University; Tsinghua ShenZhen International Graduate School , Tsinghua University"},{"name":"Hai-Tao Zheng","slug":"hai-tao-zheng","given":"Hai-Tao","family":"Zheng","affiliation":"Department of Computer Science and Technology , Tsinghua University; Tsinghua ShenZhen International Graduate School , Tsinghua University"},{"name":"Ying Shen","slug":"ying-shen","given":"Ying","family":"Shen","affiliation":"School of Intelligent Systems Engineering , Sun Yat-Sen University"}],"abstract":"Generating a textual description from a set of RDF triplets is a challenging task in natural language generation. Recent neural methods have become the mainstream for this task, which often generate sentences from scratch. However, due to the huge gap between the structured input and the unstructured output, the input triples alone are insufficient to decide an expressive and specific description. In this paper, we propose a novel anchor-to-prototype framework to bridge the gap between structured RDF triples and natural text. The model retrieves a set of prototype descriptions from the training data and extracts writing patterns from them to guide the generation process. Furthermore, to make a more precise use of the retrieved prototypes, we employ a triple anchor that aligns the input triples into groups so as to better match the prototypes. Experimental results on both English and Chinese datasets show that our method significantly outperforms the state-of-the-art baselines in terms of both automatic and manual evaluation, demonstrating the benefit of learning guidance from retrieved prototypes to facilitate triple-to-text generation.","doi":"10.24963/ijcai.2020/523","url":"https://ijcai.org/proceedings/2020/523","pdf":"https://ijcai.org/proceedings/2020/0523.pdf","markdown":"https://ijcai.org/proceedings/2020/523.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/523","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Natural Language Processing","track":"Main track","number":523,"pages":{"first":3780,"last":3786},"keywords":["Natural Language Processing: Other","Natural Language Processing: NLP Applications and Tools","Natural Language Processing: Natural Language Processing","Natural Language Processing: Natural Language Generation"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25150/file_25150.m3u8","length_sec":270,"provider":"hls"}],"references":[{"position":1,"raw":"[Bahdanau et al., 2015] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. In ICLR, 2015.","title":"Neural machine translation by jointly learning to align and translate","authors":"Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bordes et al., 2014] Antoine Bordes, Sumit Chopra, and Ja- son Weston. Question answering with subgraph embed- dings. In EMNLP, pages 615-620, 2014.","title":"Question answering with subgraph embeddings","authors":"Antoine Bordes, Sumit Chopra, Jason Weston","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cai and Lam, 2020] Deng Cai and Wai Lam. Graph trans- former for graph-to-sequence learning. In AAAI, 2020.","title":"Graph transformer for graph-to-sequence learning","authors":"Lam ; ] Deng Cai, Wai Cai, Lam","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cai et al., 2019a] Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, and Shuming Shi. Skeleton- to-response: Dialogue generation guided by retrieval memory. In NAACL-HLT, pages 1219-1228, 2019.","title":"Skeletonto-response: Dialogue generation guided by retrieval memory","authors":"Cai","year":"2019","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cai et al., 2019b] Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, and Shuming Shi. Retrieval-guided di- alogue response generation via a matching-to-generation framework. In EMNLP-IJCNLP, pages 1866-1875, 2019.","title":"Retrieval-guided dialogue response generation via a matching-to-generation framework","authors":"Cai","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cao et al., 2018] Ziqiang Cao, Wenjie Li, Sujian Li, and Furu Wei. Retrieve, rerank and rewrite: Soft template based neural summarization. In ACL, pages 152-161, 2018.","title":"Retrieve, rerank and rewrite: Soft template based neural summarization","authors":"Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chisholm et al., 2017] Andrew Chisholm, Will Radford, and Ben Hachey. Learning to generate one-sentence bi- ographies from wikidata. In EACL, pages 633-642, 2017.","title":"Learning to generate one-sentence biographies from wikidata","authors":"Andrew Chisholm, Will Radford, Ben Hachey","year":"2017","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ding et al., 2004] Li Ding, Tim Finin, Anupam Joshi, Rong Pan, R Scott Cost, Yun Peng, Pavan Reddivari, Vishal Doshi, and Joel Sachs. Swoogle: a search and metadata engine for the semantic web. In CIKM, pages 652-659, 2004.","title":"Swoogle: a search and metadata engine for the semantic web","authors":"Li Ding, Tim Finin, Anupam Joshi, Rong Pan, R Scott Cost, Yun Peng, Pavan Reddivari, Vishal Doshi, Joel Sachs","year":"2004","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Distiawan et al., 2018] Bayu Distiawan, Jianzhong Qi, Rui Zhang, and Wei Wang. Gtr-lstm: A triple encoder for sen- tence generation from rdf data. In ACL, pages 1627-1637, 2018.","title":"Gtr-lstm: A triple encoder for sentence generation from rdf data","authors":"Jianzhong Bayu Distiawan, Rui Qi, Wei Zhang, Wang","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Duma and Klein, 2013] Daniel Duma and Ewan Klein. Generating natural language from linked data: Unsuper- vised template extraction. In IWCS 2013, pages 83-94, 2013.","title":"Generating natural language from linked data: Unsupervised template extraction","authors":"Klein Duma, Daniel Duma, Ewan Klein","year":"2013","venue":"IWCS 2013","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Fader et al., 2014] Anthony Fader, Luke Zettlemoyer, and Oren Etzioni. Open question answering over curated and extracted knowledge bases. In KDD, pages 1156-1165, 2014.","title":"Open question answering over curated and extracted knowledge bases","authors":"Anthony Fader, Luke Zettlemoyer, Oren Etzioni","year":"2014","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gardent et al., 2017] Claire Gardent, Anastasia Shimorina, Shashi Narayan, and Laura Perez-Beltrachini. The webnlg challenge: Generating text from rdf data. In ICNLG, pages 124-133, 2017.","title":"The webnlg challenge: Generating text from rdf data","authors":"Claire Gardent, Anastasia Shimorina, Shashi Narayan, Laura Perez-Beltrachini","year":"2017","venue":"ICNLG","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Guu et al., 2018] Kelvin Guu, Tatsunori B Hashimoto, Yonatan Oren, and Percy Liang. Generating sentences by editing prototypes. Transactions of the Association for Computational Linguistics, 6:437-450, 2018.","title":"Generating sentences by editing prototypes","authors":"Kelvin Guu, B Tatsunori, Yonatan Hashimoto, Percy Oren, Liang","year":"2018","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hua and Wang, 2019] Xinyu Hua and Lu Wang. Sentence- level content planning and style specification for neu- ral text generation. In EMNLP-IJCNLP, pages 591-602, 2019.","title":"Sentencelevel content planning and style specification for neural text generation","authors":"Xinyu Hua, Lu Wang","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Koncel-Kedziorski et al., 2019] Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata, and Hannaneh Hajishirzi. Text generation from knowledge graphs with graph transformers. In NAACL, pages 2284-2293, 2019.","title":"Text generation from knowledge graphs with graph transformers","authors":"Koncel-Kedziorski","year":"2019","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kukich, 1983] Karen Kukich. Design of a knowledge-based report generator. In ACL, pages 145-150, 1983.","title":"Design of a knowledge-based report generator","authors":"Karen Kukich","year":"1983","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Miller, 2001] Eric Miller. An introduction to the resource description framework. Journal of library administration, 34(3-4):245-255, 2001.","title":"An introduction to the resource description framework","authors":"Eric Miller","year":"2001","venue":"Journal of library administration","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Moryossef et al., 2019] Amit Moryossef, Yoav Goldberg, and Ido Dagan. Step-by-step: Separating planning from realization in neural data-to-text generation. In NAACL, pages 2267-2277, 2019.","title":"Step-by-step: Separating planning from realization in neural data-to-text generation","authors":"Amit Moryossef, Yoav Goldberg, Ido Dagan","year":"2019","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Papineni et al., 2002] Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for au- tomatic evaluation of machine translation. In ACL, pages 311-318, 2002.","title":"Bleu: a method for automatic evaluation of machine translation","authors":"Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu","year":"2002","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shao et al., 2019] Zhihong Shao, Minlie Huang, Jiangtao Wen, Wenfei Xu, and Xiaoyan Zhu. Long and diverse text generation with planning-based hierarchical variational model. In EMNLP-IJCNLP, pages 3255-3266, 2019.","title":"Long and diverse text generation with planning-based hierarchical variational model","authors":"Zhihong Shao, Minlie Huang, Jiangtao Wen, Wenfei Xu, Xiaoyan Zhu","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sukhbaatar et al., 2015] Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, and Rob Fergus. End-to-end memory networks. In NIPS, pages 2440-2448, 2015.","title":"End-to-end memory networks","authors":"Sukhbaatar","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. Sequence to sequence learning with neural networks. In NIPS, pages 3104-3112, 2014.","title":"Le. Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Vougiouklis et al., 2018] Pavlos Vougiouklis, Hady Elsa- har, Lucie-Aimée Kaffee, Christophe Gravier, Frederique Laforest, Jonathon Hare, and Elena Simperl. Neural wikipedian: Generating textual summaries from knowl- edge base triples. Journal of Web Semantics, 52:1-15, 2018.","title":"Neural wikipedian: Generating textual summaries from knowledge base triples","authors":"Pavlos Vougiouklis, Hady Elsahar, Lucie-Aimée Kaffee, Christophe Gravier, Frederique Laforest, Jonathon Hare, Elena Simperl","year":"2018","venue":"Journal of Web Semantics","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2019] Kai Wang, Xiaojun Quan, and Rui Wang. Biset: Bi-directional selective encoding with tem- plate for abstractive summarization. In ACL, pages 2153- 2162, 2019.","title":"Biset: Bi-directional selective encoding with template for abstractive summarization","authors":"Kai Wang, Xiaojun Quan, Rui Wang","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wiseman et al., 2017] Sam Wiseman, Stuart M. Shieber, and Alexander M. Rush. Challenges in data-to-document generation. In EMNLP, pages 2253-2263, 2017.","title":"Challenges in data-to-document generation","authors":"Sam Wiseman, Stuart M Shieber, Alexander M Rush","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wu et al., 2019] Yu Wu, Furu Wei, Shaohan Huang, Yunli Wang, Zhoujun Li, and Ming Zhou. Response generation by context-aware prototype editing. In AAAI, volume 33, pages 7281-7288, 2019.","title":"Response generation by context-aware prototype editing","authors":"Yu Wu, Furu Wei, Shaohan Huang, Yunli Wang, Zhoujun Li, Ming Zhou","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhu et al., 2019] Yaoming Zhu, Juncheng Wan, Zhiming Zhou, Liheng Chen, Lin Qiu, Weinan Zhang, Xin Jiang, and Yong Yu. Triple-to-text: Converting RDF triples into high-quality natural languages via optimizing an inverse KL divergence. In SIGIR, pages 455-464, 2019.","title":"Triple-to-text: Converting RDF triples into high-quality natural languages via optimizing an inverse KL divergence","authors":"Yaoming Zhu, Juncheng Wan, Zhiming Zhou, Liheng Chen, Lin Qiu, Weinan Zhang, Xin Jiang, Yong Yu","year":"2019","venue":"SIGIR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}