Conversational Recommender Systems (CoRSs) are becoming increasingly popular. However, designing and developing a CoRS is a challenging task since it requires multi-disciplinary skills. Even though several third-party services are available for supporting the creation of a CoRS, a comparative study of these platforms for the specific recommendation task is not available yet. In this work, we focus our attention on two crucial steps of the Conversational Recommendation (CoR) process, namely Intent and Entity Recognition. We compared four of the most popular services, both commercial and open source. Furthermore, we proposed two custom-made solutions for Entity Recognition, whose aim is to overcome the limitations of the other services. Results are very interesting and give a clear picture of the strengths and weaknesses of each solution.

A comparison of services for intent and entity recognition for conversational recommender systems

Iovine A.;Narducci F.;de Gemmis M.;Polignano M.;Basile P.;Semeraro G.
2020-01-01

Abstract

Conversational Recommender Systems (CoRSs) are becoming increasingly popular. However, designing and developing a CoRS is a challenging task since it requires multi-disciplinary skills. Even though several third-party services are available for supporting the creation of a CoRS, a comparative study of these platforms for the specific recommendation task is not available yet. In this work, we focus our attention on two crucial steps of the Conversational Recommendation (CoR) process, namely Intent and Entity Recognition. We compared four of the most popular services, both commercial and open source. Furthermore, we proposed two custom-made solutions for Entity Recognition, whose aim is to overcome the limitations of the other services. Results are very interesting and give a clear picture of the strengths and weaknesses of each solution.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11586/348719
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact