Skip to Main content Skip to Navigation
Book sections

Boosting a rule-based chatbot using statistics and user satisfaction ratings

Abstract : Using data from user-chatbot conversations where users have rated the answers as good or bad, we propose a more efficient alternative to a chatbot's keyword-based answer retrieval heuristic. We test two neural network approaches to the near-duplicate question detection task as a first step towards a better answer retrieval method. A convolutional neural network architecture gives promising results on this difficult task.
Document type :
Book sections
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01806464
Contributor : Octavia Efraim <>
Submitted on : Saturday, June 2, 2018 - 8:44:08 PM
Last modification on : Monday, January 20, 2020 - 3:18:29 PM
Document(s) archivé(s) le : Monday, September 3, 2018 - 3:33:12 PM

File

ainl_postprint.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01806464, version 1

Citation

Octavia Efraim, Vladislav Maraev, João Rodrigues. Boosting a rule-based chatbot using statistics and user satisfaction ratings. Filchenkov A., Pivovarova L., Žižka J. (eds) Artificial Intelligence and Natural Language. AINL 2017. Communications in Computer and Information Science, vol 789. Springer, Cham, 2018. ⟨hal-01806464⟩

Share

Metrics

Record views

134

Files downloads

420