On the role of linguistic descriptions of data in the building of natural language generation systems

Ramos-Soto, Alejandro; Bugarín, Alberto; Barro, Senén

doi:10.1016/j.fss.2015.06.019

Cited by 63 publications

(43 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, if we do not have any other alternative, we will probably choose re 5 because, as can be seen in table 1, there are fewer objects for which re 5 is true to some extent than there are for re 4 . That is, the fuzzy sets of objects of which re 5 is to some extent true is more specific, i.e.…”

Section: Referential Successmentioning

confidence: 99%

See 1 more Smart Citation

The Role of Graduality for Referring Expression Generation in Visual Scenes

Gatt

Marín

Portet

et al. 2016

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. Referring Expression Generation (reg) algorithms, a core component of systems that generate text from non-linguistic data, seek to identify domain objects using natural language descriptions. While reg has often been applied to visual domains, very few approaches deal with the problem of fuzziness and gradation. This paper discusses these problems and how they can be accommodated to achieve a more realistic view of the task of referring to objects in visual scenes.

show abstract

Section: Referential Successmentioning

confidence: 99%

“…In recent years, scene description has attracted a lot of attention as part of a growing trend to explore the interface between vision and language in Natural Language Generation (nlg) [1], as is the case of other kind of data [2][3][4].…”

Section: Introductionmentioning

confidence: 99%

The Role of Graduality for Referring Expression Generation in Visual Scenes

Gatt

Marín

Portet

et al. 2016

Communications in Computer and Information Science

View full text Add to dashboard Cite

show abstract

“…a) Natural Language Generation:: Natural Language Generation from time-series data has been investigated for various tasks, including, but not limited to, weather forecast generation [9], [10], [11], sportcasting [12], [13], [14], narrative generation to assist children with communication needs [15], student feedback generation [16]and report generation from students data [17] and report generation from medical time-series data [18] [19][20] [4].…”

Section: Related Workmentioning

confidence: 99%

“…There are several lines of research aiming to address this problem. For example, previous work has focused on addressing uncertainty in time-series data [17] and temporal uncertainty [29]. Our study addresses uncertainty derived from unknown first-time users.…”

Section: Related Workmentioning

confidence: 99%

How to talk to strangers: Generating medical reports for first-time users

Gkatzia

Rieser

Lemon

2016

2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

Abstract-We propose a novel approach for handling first-time users in the context of automatic report generation from timeseries data in the health domain. Handling first-time users is a common problem for Natural Language Generation (NLG) and interactive systems in general -the system cannot adapt to users without prior interaction or user knowledge. In this paper, we propose a novel framework for generating medical reports for first-time users, using multi-objective optimisation (MOO) to account for the preferences of multiple possible user types, where the content preferences of potential users are modelled as objective functions. Our proposed approach outperforms two meaningful baselines in an evaluation with prospective users, yielding large (= .79) and medium (= .46) effect sizes respectively.

show abstract

“…However, for the sake of this study, it is significant and interesting that there exists a strong theoretical relation between the concept of protoforms and the paradigm of cognitive linguistics [10], as well as interactive linguistics. The latter, lesser known in the mainstream of linguistic research, is based on an original MIC theory developed by Włodarczyk and Wło-darczyk in CELTA 1 , and provides the information technology field with valuable and methodologically effective approach to natural language modelling and analysis [2].…”

Section: Introductionmentioning

confidence: 99%

Some Notes on Extracting Linguistic Summaries Built with Epistemic Modalities and Natural Language Connectives of Equivalence

Katarzyniak

Lorkiewicz

Więcek

2017

CMST

View full text Add to dashboard Cite

In this paper we deal with an original technically oriented model for cognitive semantics. As the expected area of application we focus on the process of extraction of modal linguistic summaries from data managed by autonomous components of ambient systems and intelligent environments. As such, the cognitive semantics is defined for a particular case of modal natural language statements with epistemic modalities. The statements of interest are built with natural language operators, representing epistemic modalities (related to the main cognitive states of knowledge certainty: full certainty, strong belief and epistemic possibility), and natural language connectives of equivalence. Furthermore, an approach to their effective processing by autonomous computational systems is designed. An internal architecture of the autonomous computational component is designed with respect to modular model for natural language processing with separate modules for epistemic and semantic memory storage and processing. An original theoretical concept underlying the model of semantic memory is a holon defined as a collection of complementary linguistic protoforms. Finally, we provide several illustrative computational examples of linguistic summaries' extraction, based on artificial and real data.

show abstract

On the role of linguistic descriptions of data in the building of natural language generation systems

Cited by 63 publications

References 60 publications

The Role of Graduality for Referring Expression Generation in Visual Scenes

The Role of Graduality for Referring Expression Generation in Visual Scenes

How to talk to strangers: Generating medical reports for first-time users

Some Notes on Extracting Linguistic Summaries Built with Epistemic Modalities and Natural Language Connectives of Equivalence

Contact Info

Product

Resources

About