{"type":"ScholarlyArticle","title":"Infobox-to-text Generation with Tree-like Planning based Attention Network","authors":[{"name":"Yang Bai","slug":"yang-bai","given":"Yang","family":"Bai","affiliation":"Department of Computer Science and Technology , Tsinghua University; Tsinghua ShenZhen International Graduate School , Tsinghua University"},{"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":"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":"Ying Shen","slug":"ying-shen","given":"Ying","family":"Shen","affiliation":"School of Intelligent Systems Engineering , Sun Yat-Sen 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"}],"abstract":"We study the problem of infobox-to-text generation that aims to generate a textual description from a key-value table. Representing the input infobox as a sequence, previous neural methods using end-to-end models without order-planning suffer from the problems of incoherence and inadaptability to disordered input. Recent planning-based models only implement static order-planning to guide the generation, which may cause error propagation between planning and generation. To address these issues, we propose a Tree-like PLanning based Attention Network (Tree-PLAN) which leverages both static order-planning and dynamic tuning to guide the generation. A novel tree-like tuning encoder is designed to dynamically tune the static order-plan for better planning by merging the most relevant attributes together layer by layer. Experiments conducted on two datasets show that our model outperforms previous methods on both automatic and human evaluation, and demonstrate that our model has better adaptability to disordered input.","doi":"10.24963/ijcai.2020/522","url":"https://ijcai.org/proceedings/2020/522","pdf":"https://ijcai.org/proceedings/2020/0522.pdf","markdown":"https://ijcai.org/proceedings/2020/522.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/522","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":522,"pages":{"first":3773,"last":3779},"keywords":["Natural Language Processing: Natural Language Processing","Natural Language Processing: Natural Language Generation"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24157/file_24157.m3u8","length_sec":271,"provider":"hls"}],"references":[{"position":1,"raw":"[Barzilay and Lapata, 2005] Regina Barzilay and Mirella Lapata. Collective content selection for concept-to-text generation. In HLT/EMNLP, pages 331-338, 2005.","title":"Collective content selection for concept-to-text generation","authors":"Lapata Barzilay, Regina Barzilay, Mirella Lapata","year":"2005","venue":"HLT/EMNLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Barzilay and Lapata, 2006] Regina Barzilay and Mirella Lapata. Aggregation via set partitioning for natural lan- guage generation. In HLT-NAACL, page 359-366, New York City, USA, 2006.","title":"Aggregation via set partitioning for natural language generation","authors":"Lapata Barzilay, Regina Barzilay, Mirella Lapata","year":"2006","venue":"HLT-NAACL","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Gong et al., 2019] Heng Gong, Xiaocheng Feng, Bing Qin, and Ting Liu. Table-to-text generation with effective hi- erarchical encoder on three dimensions (row, column and time). In EMNLP-IJCNLP, 2019.","title":"Table-to-text generation with effective hierarchical encoder on three dimensions (row, column and time)","authors":"Heng Gong, Xiaocheng Feng, Bing Qin, Ting Liu","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Jain et al., 2018] Parag Jain, Anirban Laha, Karthik Sankaranarayanan, Preksha Nema, Mitesh M. Khapra, and Shreyas Shetty. A mixed hierarchical attention based encoder-decoder approach for standard table summarization. In NAACL-HLT (2), pages 622-627, 2018.","title":"A mixed hierarchical attention based encoder-decoder approach for standard table summarization","authors":"Parag Jain, Anirban Laha, Karthik Sankaranarayanan, Preksha Nema, M Mitesh, Shreyas Khapra, Shetty","year":"2018","venue":"NAACL-HLT (2)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Kaffee et al., 2018] Lucie-Aimée Kaffee, Hady ElSahar, Pavlos Vougiouklis, Christophe Gravier, Frédérique Lafor- est, Jonathon S. Hare, and Elena Simperl. Learning to generate wikipedia summaries for underserved languages from wikidata. In NAACL-HLT (2), pages 640-645, 2018.","title":"Learning to generate wikipedia summaries for underserved languages from wikidata","authors":"Lucie-Aimée Kaffee, Hady Elsahar, Pavlos Vougiouklis, Christophe Gravier, Frédérique Laforest, Jonathon S Hare, Elena Simperl","year":"2018","venue":"NAACL-HLT (2)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kim and Mooney, 2010] Joohyun Kim and Raymond Mooney. Generative alignment and semantic parsing for learning from ambiguous supervision. In Coling-2010, pages 543-551, Beijing, China, August 2010.","title":"Generative alignment and semantic parsing for learning from ambiguous supervision","authors":"Mooney Kim, Joohyun Kim, Raymond Mooney","year":"2010","venue":"Coling-2010","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Konstas and Lapata, 2012] Ioannis Konstas and Mirella La- pata. Unsupervised concept-to-text generation with hyper- graphs. In HLT-NAACL, pages 752-761, 2012.","title":"Ioannis Konstas and Mirella Lapata. Unsupervised concept-to-text generation with hypergraphs","authors":"Lapata Konstas","year":"2012","venue":"HLT-NAACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Konstas and Lapata, 2013] Ioannis Konstas and Mirella La- pata. Inducing document plans for concept-to-text genera- tion. In EMNLP, pages 1503-1514, 2013.","title":"Ioannis Konstas and Mirella Lapata. Inducing document plans for concept-to-text generation","authors":"Lapata Konstas","year":"2013","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lebret et al., 2016] Rémi Lebret, David Grangier, and Michael Auli. Neural text generation from structured data with application to the biography domain. In EMNLP, pages 1203-1213, 2016.","title":"Neural text generation from structured data with application to the biography domain","authors":"Lebret","year":"2016","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Liang et al., 2009] Percy Liang, Michael Jordan, and Dan Klein. Learning semantic correspondences with less su- pervision. In ACL-IJCNLP, pages 91-99, Suntec, Singa- pore, August 2009.","title":"Learning semantic correspondences with less supervision","authors":"Percy Liang, Michael Jordan, Dan Klein","year":"2009","venue":"ACL-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2018] Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, and Zhifang Sui. Table-to-text genera- tion by structure-aware seq2seq learning. In AAAI, pages 4881-4888, 2018.","title":"Table-to-text generation by structure-aware seq2seq learning","authors":"Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, Zhifang Sui","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2019a] Tianyu Liu, Fuli Luo, Qiaolin Xia, Shum- ing Ma, Baobao Chang, and Zhifang Sui. Hierarchical encoder with auxiliary supervision for neural table-to-text generation: Learning better representation for tables. In AAAI, pages 6786-6793, 2019.","title":"Hierarchical encoder with auxiliary supervision for neural table-to-text generation: Learning better representation for tables","authors":"Liu","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2019b] Tianyu Liu, Fuli Luo, Pengcheng Yang, Wei Wu, Baobao Chang, and Zhifang Sui. Towards com- prehensive description generation from factual attribute- value tables. In ACL, pages 5985-5996, Florence, Italy, July 2019.","title":"Towards comprehensive description generation from factual attributevalue tables","authors":"Liu","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mahapatra et al., 2016] Joy Mahapatra, Sudip Kumar Naskar, and Sivaji Bandyopadhyay. Statistical natural language generation from tabular non-textual data. In INLG, pages 143-152, 2016.","title":"Statistical natural language generation from tabular non-textual data","authors":"Mahapatra","year":"2016","venue":"INLG","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mei et al., 2016] Hongyuan Mei, Mohit Bansal, and Matthew R. Walter. What to talk about and how? selective generation using LSTMs with coarse-to-fine alignment. In NAACL, pages 720-730, San Diego, California, June 2016.","title":"What to talk about and how? selective generation using LSTMs with coarse-to-fine alignment","authors":"Hongyuan Mei, Mohit Bansal, Matthew R Walter","year":"2016","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nie et al., 2018] Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong Pan, and Chin-Yew Lin. Operation-guided neu- ral networks for high fidelity data-to-text generation. In EMNLP, pages 3879-3889, Brussels, Belgium, October- November 2018.","title":"Operation-guided neural networks for high fidelity data-to-text generation","authors":"Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong Pan, Chin-Yew Lin","year":"2018","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Novikova et al., 2017] Jekaterina Novikova, Ondřej Dušek, and Verena Rieser. The E2E dataset: New challenges for end-to-end generation. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 201- 206, Saarbrücken, Germany, August 2017.","title":"The E2E dataset: New challenges for end-to-end generation","authors":"Jekaterina Novikova, Ondřej Dušek, Verena Rieser","year":"2017","venue":"Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Puduppully et al., 2019] Ratish Puduppully, Li Dong, and Mirella Lapata. Data-to-text generation with content se- lection and planning. In AAAI, pages 6908-6915, 2019.","title":"Data-to-text generation with content selection and planning","authors":"Ratish Puduppully, Li Dong, Mirella Lapata","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sha et al., 2018] Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, and Zhifang Sui. Order-planning neural text generation from structured data. In AAAI, pages 5414-5421, 2018.","title":"Order-planning neural text generation from structured data","authors":"Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, Zhifang Sui","year":"2018","venue":"AAAI","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 varia- tional model. In EMNLP-IJCNLP, pages 3255-3266, Hong Kong, China, November 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":"[Trisedya et al., 2020] Bayu Distiawan Trisedya, Jianzhong Qi, and Rui Zhang. Sentence generation for entity descrip- tion with content-plan attention. In AAAI-2020, 2020.","title":"Sentence generation for entity description with content-plan attention","authors":"Jianzhong Bayu Distiawan Trisedya, Rui Qi, Zhang","year":"2020","venue":"AAAI-2020","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz 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, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang and Wan, 2019] Tianming Wang and Xiaojun Wan. Hierarchical attention networks for sentence ordering. In AAAI, pages 7184-7191, 2019.","title":"Hierarchical attention networks for sentence ordering","authors":"Wang, Wan ; ] Tianming Wang, Xiaojun Wan","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2019] Yaushian Wang, Hung-Yi Lee, and Yun- Nung Chen. Tree transformer: Integrating tree structures into self-attention. In EMNLP-IJCNLP, pages 1061-1070, Hong Kong, China, November 2019.","title":"Tree transformer: Integrating tree structures into self-attention","authors":"Wang","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wiseman et al., 2017] Sam Wiseman, Stuart Shieber, and Alexander Rush. Challenges in data-to-document gener- ation. In EMNLP, pages 2253-2263, Copenhagen, Den- mark, September 2017.","title":"Challenges in data-to-document generation","authors":"Sam Wiseman, Stuart Shieber, Alexander Rush","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}