Skip to Main content Skip to Navigation
Journal articles

An Extensible and Reusable Pipeline for Automated Utterance Paraphrases

Abstract : In this demonstration paper we showcase an extensible and reusable pipeline for automatic paraphrase generation, i.e., reformulating sentences using different words. Capturing the nuances of human language is fundamental to the effectiveness of Conversational AI systems, as it allows them to deal with the different ways users can utter their requests in natural language. Traditional approaches to utterance paraphrasing acquisition, such as hiring experts or crowdsourcing, involve processes that are often costly or time consuming, and with their own trade-offs in terms of quality. Automatic paraphrasing is emerging as an attractive alternative that promises a fast, scalable and cost-effective process. In this paper we showcase how our extensible and reusable pipeline for automated utterance paraphrasing can support the development of Conversational AI systems by integrating and extending existing techniques under an unified and configurable framework.
Document type :
Journal articles
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03399085
Contributor : Hayet Brabra Connect in order to contact the contributor
Submitted on : Saturday, October 23, 2021 - 7:37:18 PM
Last modification on : Tuesday, October 26, 2021 - 4:00:24 AM

File

vldb_paper.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Auday Berro, Mohammad-Ali Yaghub Zade Fard, Marcos Baez, Boualem Benatallah, Khalid Benabdeslem. An Extensible and Reusable Pipeline for Automated Utterance Paraphrases. Proceedings of the VLDB Endowment (PVLDB), VLDB Endowment, 2021, ⟨10.14778/3476311.3476358⟩. ⟨hal-03399085⟩

Share

Metrics

Record views

34

Files downloads

24