2022
DOI: 10.1109/tse.2021.3078384
|View full text |Cite
|
Sign up to set email alerts
|

A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
35
0
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
2
2

Relationship

1
7

Authors

Journals

citations
Cited by 64 publications
(37 citation statements)
references
References 44 publications
1
35
0
1
Order By: Relevance
“…These components provide both NLU and dialogue management services. Abdellatif et al (2021) evaluated the NLU components that are suitable for software engineering tasks. The comparison resulted in IBM Watson being ranked as the best for intent classification and entity extraction, whereas Rasa ranked the best for confidence scores.…”
Section: Resultsmentioning
confidence: 99%
“…These components provide both NLU and dialogue management services. Abdellatif et al (2021) evaluated the NLU components that are suitable for software engineering tasks. The comparison resulted in IBM Watson being ranked as the best for intent classification and entity extraction, whereas Rasa ranked the best for confidence scores.…”
Section: Resultsmentioning
confidence: 99%
“…Also, we believe that there is a need for more studies that compare different NLUs using more datasets to benchmark NLUs in the SE context. We contribute towards this effort by making our dataset publicly available [31]. P: Precision, R: Recall, F1: F1-measure…”
Section: Discussionmentioning
confidence: 99%
“…After the merge, we discarded queries with unclear intent (total of 82), such as "JConsole Web Application". The final set includes 215 queries [31], Tables 4 and 3 show the number of intents and entities included in our evaluation, respectively.…”
Section: Facingerrormentioning
confidence: 99%
See 1 more Smart Citation
“…In the first version of our Weaver platform, we chose Dialogflow as the NLU service. When we saw some shortcomings, we introduced RASA as the most trustworthy opensource NLU service in terms of confidence score [32]. After that, we realized the problem of NLU dependency and then came up with the idea we have implemented in our architecture.…”
Section: Nlu Supportmentioning
confidence: 99%