Tailoring lexical choice to the user's vocabulary in multimedia explanation generation

McKeown, Kathleen; Robin, Jacques; Tanenblatt, Michael

doi:10.3115/981574.981605

Cited by 19 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This topic has been addressed in a number of previous research projects, where reader expertise has been used to inform decisions about lexical choice and terminology [80] and document structure [91]. In a similar vein, Williams [127] varied a number of linguistic parameters based on literacy level.…”

Section: Bt-family: Informing Stressed Parents About the Status Of Thmentioning

confidence: 99%

From data to text in the Neonatal Intensive Care Unit: Using NLG technology for decision support and information management

et al. 2009

View full text Add to dashboard Cite

Contemporary Neonatal Intensive Care Units collect vast amounts of patient data in various formats, making efficient processing of information by medical professionals difficult. Moreover, different stakeholders in the neonatal scenario, which include parents as well as staff occupying different roles, have different information requirements. This paper describes recent and ongoing work on building systems that automatically generate textual summaries of neonatal data. Our evaluation results show that the technology is viable and comparable in its effectiveness for decision support to existing presentation modalities. We discuss the lessons learned so far, as well as the major challenges involved in extending current technology to deal with a broader range of data types, and to improve the textual output in the form of more coherent summaries.

show abstract

Section: Bt-family: Informing Stressed Parents About the Status Of Thmentioning

confidence: 99%

From data to text in the Neonatal Intensive Care Unit: Using NLG technology for decision support and information management

et al. 2009

View full text Add to dashboard Cite

show abstract

“…The COMET system [McKeown et al 1993] tailors word choice to the vocabulary that the user is presumed to command and employs four strategies to rephrase a message in cases where the user model indicates that some word will not be understood: choose a synonym provided by the lexicon; rephrase with a conceptual definition, e.g., give a lower-level description of a term; rephrase a referring expression (the COMSEC cable) with a descriptive phrase (the cable that runs to the KY57); use past discourse to construct a new referring expression (the cable you just removed). The user model relates the lexicon entries to annotations that indicate whether a stereotypical 'good' or 'poor' reader will be familiar with the term and thus establishes additional constraints for the lexical chooser module that is in charge of selecting the words.…”

Section: Pragmatic Constraintsmentioning

confidence: 99%

Lexical Semantics and Knowledge Representation in Multilingual Text Generation

Stede

1999

View full text Add to dashboard Cite

“…With regard to tailoring texts for different readers, a number of previous NLG systems tailor texts according to whether the reader is a domain expert or a novice, (Paris, 1988; Bateman and Paris, 1989; McKeown, Robin and Tanenblatt, 1993; Milosavljevic and Oberlander, 1998). Other systems tailor content according to users' likes and dislikes, e.g.…”

Section: Introductionmentioning

confidence: 99%

Generating basic skills reports for low-skilled readers

Williams¹,

Reiter²

2008

Nat. Lang. Eng.

View full text Add to dashboard Cite

We describe SkillSum, a Natural Language Generation (NLG) system that generates a personalised feedback report for someone who has just completed a screening assessment of their basic literacy and numeracy skills. Because many SkillSum users have limited literacy, the generated reports must be easily comprehended by people with limited reading skills; this is the most novel aspect of SkillSum, and the focus of this paper. We used two approaches to maximise readability. First, for determining content and structure (document planning), we did not explicitly model readability, but rather followed a pragmatic approach of repeatedly revising content and structure following pilot experiments and interviews with domain experts. Second, for choosing linguistic expressions (microplanning), we attempted to formulate explicitly the choices that enhanced readability, using a constraints approach and preference rules; our constraints were based on corpus analysis and our preference rules were based on psycholinguistic findings. Evaluation of the SkillSum system was twofold: it compared the usefulness of NLG technology to that of canned text output, and it assessed the effectiveness of the readability model. Results showed that NLG was more effective than canned text at enhancing users' knowledge of their skills, and also suggested that the empirical 'revise based on experiments and interviews' approach made a substantial contribution to readability as well as our explicit psycholinguistically inspired models of readability choices.

show abstract

Tailoring lexical choice to the user's vocabulary in multimedia explanation generation

Cited by 19 publications

References 11 publications

From data to text in the Neonatal Intensive Care Unit: Using NLG technology for decision support and information management

From data to text in the Neonatal Intensive Care Unit: Using NLG technology for decision support and information management

Lexical Semantics and Knowledge Representation in Multilingual Text Generation

Generating basic skills reports for low-skilled readers

Contact Info

Product

Resources

About