Show simple item record

dc.contributor.authorShen, A
dc.contributor.authorSalehi, B
dc.contributor.authorQi, J
dc.contributor.authorBaldwin, T
dc.date.accessioned2020-12-14T06:34:47Z
dc.date.available2020-12-14T06:34:47Z
dc.date.issued2020-07-22
dc.identifier.citationShen, A., Salehi, B., Qi, J. & Baldwin, T. (2020). A multimodal approach to assessing document quality. Journal of Artificial Intelligence Research, 68, pp.607-632. https://doi.org/10.1613/JAIR.1.11647.
dc.identifier.issn1076-9757
dc.identifier.urihttp://hdl.handle.net/11343/254262
dc.description.abstractThe perceived quality of a document is affected by various factors, including grammaticality, readability, stylistics, and expertise depth, making the task of document quality assessment a complex one. In this paper, we explore this task in the context of assessing the quality of Wikipedia articles and academic papers. Observing that the visual rendering of a document can capture implicit quality indicators that are not present in the document text - such as images, font choices, and visual layout - we propose a joint model that combines the text content with a visual rendering of the document for document quality assessment. Our joint model achieves state-of-the-art results over five datasets in two domains (Wikipedia and academic papers), which demonstrates the complementarity of textual and visual features, and the general applicability of our model. To examine what kinds of features our model has learned, we further train our model in a multi-task learning setting, where document quality assessment is the primary task and feature learning is an auxiliary task. Experimental results show that visual embeddings are better at learning structural features while textual embeddings are better at learning readability scores, which further verifies the complementarity of visual and textual features.
dc.languageEnglish
dc.publisherAI Access Foundation
dc.titleA multimodal approach to assessing document quality
dc.typeJournal Article
dc.identifier.doi10.1613/JAIR.1.11647
melbourne.affiliation.departmentComputing and Information Systems
melbourne.source.titleJournal of Artificial Intelligence Research
melbourne.source.volume68
melbourne.source.pages607-632
melbourne.elementsid1468358
melbourne.openaccess.urlhttp://doi.org/10.1613/JAIR.1.11647
melbourne.openaccess.statusPublished version
melbourne.contributor.authorSalehi, Bahar
melbourne.contributor.authorBaldwin, Timothy
melbourne.contributor.authorQi, Jianzhong
melbourne.contributor.authorShen, Aili
dc.identifier.eissn1943-5037
melbourne.accessrightsAccess this item via the Open Access location


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record