PersuAIDE ! An Adaptive Persuasive Text Generation System for Fashion Domain

Munigala, Vitobha; Mishra, Abhijit; Tamilselvam, Srikanth; Khare, Shreya; Dasgupta, Riddhiman; Sankaran, Anush

doi:10.1145/3184558.3186345

Cited by 12 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many creative and non-creative systems with pragmatic goals, instead, do not focus their evaluation on the effects of the produced output, but just on its intrinsic properties [e.g. measuring BLEU scores (Munigala et al, 2018), or collecting ratings for the system without comparing them to ratings of human producers (Clark et al, 2018)]. With this work we argue that these measures are necessary but not sufficient for a complete evaluation of the systems.…”

Section: Introductionmentioning

confidence: 95%

Pragmatic evaluations of automated linguistic creativity

Gatti

Stock²,

Strapparava³

et al. 2021

Lang Resources & Evaluation

View full text Add to dashboard Cite

The optimal innovation hypothesis (OIH) offers a good aesthetic and cognitive reference for the kind of linguistic creativity where minimal variations can have a strong effect on the audience and realize an overall intended goal. The same approach can be the basis for creative systems. The question is how to concretely evaluate not only their quality, but also their pragmatic effect. This paper describes the original evaluations of two systems based on the OIH, one automatically yielding witty headlines for incoming news, the other producing song parodies, varying the song lyrics to evoke a given concept. The goal is to bring attention to the importance of evaluating the pragmatic potential of creative systems, in addition to the quality of their output, and to demonstrate how such evaluations can be done.

show abstract

Section: Introductionmentioning

confidence: 95%

Pragmatic evaluations of automated linguistic creativity

Gatti

Stock²,

Strapparava³

et al. 2021

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…Pavlick and Tetreault [32] developed a statistical model for predicting formality at a sentence level, in the context of online debate forums and undertook a large-scale annotation task (6574 sentences with 301 annotators). Munigala et al [29] develop an unsupervised, text-generation (at sentence-level) pipeline for generating persuasive descriptions (usually one sentence long) from a given set of keywords, in a fashion domain. Summary.…”

Section: Improving Brand Consistency As a Sentence Ranking Taskmentioning

confidence: 99%

An Integrated Approach for Improving Brand Consistency of Web Content: Modeling, Analysis and Recommendation

Roy,

Sural,

Chhaya

et al. 2020

Preprint

View full text Add to dashboard Cite

A consumer-dependent (business-to-consumer) organization tends to present itself as possessing a set of human qualities, which is termed as the brand personality of the company. The perception is impressed upon the consumer through the content, be it in the form of advertisement, blogs or magazines, produced by the organization. A consistent brand will generate trust and retain customers over time as they develop an affinity towards regularity and common patterns. However, maintaining a consistent messaging tone for a brand has become more challenging with the virtual explosion in the amount of content which needs to be authored and pushed to the Internet to maintain an edge in the era of digital marketing. To understand the depth of the problem, we collect around 300 web page content from around 650 companies. We develop traitspecific classification models by considering the linguistic features of the content. The classifier automatically identifies the web articles which are not consistent with the mission and vision of a company and further helps us to discover the conditions under which the consistency cannot be maintained. To address the brand inconsistency issue, we then develop a sentence ranking system that outputs the top three sentences that need to be changed for making a web article more consistent with the company's brand personality.

show abstract

“…Open Problems and Future Directions: This part will focus on various aspects of natural language generation which are far from being realized. The presenters will get highly creative and also borrow connections from some recent trends (Jain et al, 2017;Munigala et al, 2018;Hu et al, 2017;Jain et al, 2019) in NLG literature to formulate future directions for automatic text generation. The goal of this section is not only to motivate and convey open research problems, but mainly to start a discussion paving the way for newer problems in the area.…”

Section: Tutorial Overviewmentioning

confidence: 99%

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

2019

View full text Add to dashboard Cite

show abstract

PersuAIDE ! An Adaptive Persuasive Text Generation System for Fashion Domain

Cited by 12 publications

References 8 publications

Pragmatic evaluations of automated linguistic creativity

Pragmatic evaluations of automated linguistic creativity

An Integrated Approach for Improving Brand Consistency of Web Content: Modeling, Analysis and Recommendation

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

Contact Info

Product

Resources

About