Towards constructive text, diagram, and layout generation for information presentation

被引:31
|
作者
Bateman, J [1 ]
Kamps, T
Kleinz, J
Reichenberger, K
机构
[1] Univ Bremen, FBIO, D-28334 Bremen, Germany
[2] GMD IPSI, Darmstadt, Germany
[3] Intelligent Views GmbH, Darmstadt, Germany
关键词
D O I
10.1162/089120101317066131
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Combining elements appropriately within a coherent page layout is a well-recognized and crucial aspect of sophisticated information presentation. The precise function and nature of layout has not, however, been sufficiently addressed within computational approaches; attention is often restricted to relatively local issues of typography and text-formatting, leaving broader issues of layout unaddressed. In this paper we focus on the selection and function of layout in pages that appropriately combine textual and graphical representation styles to yield coherent presentation designs. We demonstrate that layout offers a rich resource for achieving presentational coherence, alongside more traditional resources such as text-formatting and the text-internal marking of discourse connections. We also introduce an integrated approach to layout, text, and diagram generation. Our approach is developed on the basis of a preliminary empirical investigation of professionally produced layouts, followed by implementation within a prototype information system in the area of art history.
引用
收藏
页码:409 / 449
页数:41
相关论文
共 50 条
  • [21] Towards End-to-End Unified Scene Text Detection and Layout Analysis
    Long, Shangbang
    Qin, Siyang
    Panteleev, Dmitry
    Bissacco, Alessandro
    Fujii, Yasuhisa
    Raptis, Michalis
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1039 - 1049
  • [22] Towards Cross-Domain Transferability of Text Generation Models for Legal Text
    Kumar, Vinayshekhar Bannihatti
    Bhattacharjee, Kasturi
    Gangadharaiah, Rashmi
    NLLP 2022 - Natural Legal Language Processing Workshop 2022, Proceedings of the Workshop, 2022, : 111 - 118
  • [23] Incorporating Text Information on Presentation Slides for Spoken Lecture Retrieval
    Yamauchi, Kosuke
    Akiba, Tomoyoshi
    2015 2ND INTERNATIONAL CONFERENCE ON ADVANCED INFORMATICS: CONCEPTS, THEORY AND APPLICATIONS ICAICTA, 2015,
  • [24] WIP - INTEGRATING TEXT AND GRAPHICS DESIGN FOR ADAPTIVE INFORMATION PRESENTATION
    WAHLSTER, W
    ANDRE, E
    FINKLER, W
    GRAF, W
    PROFITLICH, HJ
    RIST, T
    SCHAUDER, A
    LECTURE NOTES IN ARTIFICIAL INTELLIGENCE, 1992, 587 : 290 - 292
  • [25] RevManHAL: towards automatic text generation in systematic reviews
    Torres, Mercedes Torres
    Adams, Clive E.
    SYSTEMATIC REVIEWS, 2017, 6
  • [26] Towards Text Generation with Adversarially Learned Neural Outlines
    Subramanian, Sandeep
    Rajeswar, Sai
    Sordoni, Alessandro
    Trischler, Adam
    Courville, Aaron
    Pal, Christopher
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [27] Towards Content Transfer through Grounded Text Generation
    Prabhumoye, Shrimai
    Quirk, Chris
    Galley, Michel
    2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 2622 - 2632
  • [28] Towards Table-to-Text Generation with Numerical Reasoning
    Suadaa, Lya Hulliyyatus
    Kamigaito, Hidetaka
    Funakoshi, Kotaro
    Okumura, Manabu
    Takamura, Hiroya
    59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 (ACL-IJCNLP 2021), 2021, : 1451 - 1465
  • [29] DiffusionPen: Towards Controlling the Style of Handwritten Text Generation
    Nikolaidou, Konstantina
    Retsinas, George
    Sfikas, Giorgos
    Liwicki, Marcus
    COMPUTER VISION - ECCV 2024, PT LXXXV, 2025, 15143 : 417 - 434
  • [30] RevManHAL: towards automatic text generation in systematic reviews
    Mercedes Torres Torres
    Clive E. Adams
    Systematic Reviews, 6