Next Article in Journal
Smart Traffic Lights over Vehicular Named Data Networking
Next Article in Special Issue
Application of Machine Learning Models for Survival Prognosis in Breast Cancer Studies
Previous Article in Journal
Haze Image Recognition Based on Brightness Optimization Feedback and Color Correction
Previous Article in Special Issue
Evolution, Robustness and Generality of a Team of Simple Agents with Asymmetric Morphology in Predator-Prey Pursuit Problem
Open AccessArticle

Machine Reading Comprehension for Answer Re-Ranking in Customer Support Chatbots

1
Faculty of Mathematics and Informatics, Sofia University, 1164 Sofia, Bulgaria
2
Qatar Computing Research Institute, Hamad Bin Khalifa University, 34110 Doha, Qatar
*
Author to whom correspondence should be addressed.
Information 2019, 10(3), 82; https://doi.org/10.3390/info10030082
Received: 21 January 2019 / Revised: 16 February 2019 / Accepted: 19 February 2019 / Published: 26 February 2019
(This article belongs to the Special Issue Artificial Intelligence—Methodology, Systems, and Applications)
Recent advances in deep neural networks, language modeling and language generation have introduced new ideas to the field of conversational agents. As a result, deep neural models such as sequence-to-sequence, memory networks, and the Transformer have become key ingredients of state-of-the-art dialog systems. While those models are able to generate meaningful responses even in unseen situations, they need a lot of training data to build a reliable model. Thus, most real-world systems have used traditional approaches based on information retrieval (IR) and even hand-crafted rules, due to their robustness and effectiveness, especially for narrow-focused conversations. Here, we present a method that adapts a deep neural architecture from the domain of machine reading comprehension to re-rank the suggested answers from different models using the question as a context. We train our model using negative sampling based on question–answer pairs from the Twitter Customer Support Dataset. The experimental results show that our re-ranking framework can improve the performance in terms of word overlap and semantics both for individual models as well as for model combinations. View Full-Text
Keywords: conversational agents; chatbots; machine reading comprehension; question answering; information retrieval; answer re-ranking conversational agents; chatbots; machine reading comprehension; question answering; information retrieval; answer re-ranking
Show Figures

Figure 1

MDPI and ACS Style

Hardalov, M.; Koychev, I.; Nakov, P. Machine Reading Comprehension for Answer Re-Ranking in Customer Support Chatbots. Information 2019, 10, 82.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop