Proceedings of the 10th International Conference on Agents and Artificial Intelligence 2018
DOI: 10.5220/0006595904860492
|View full text |Cite
|
Sign up to set email alerts
|

Sentence and Word Embedding Employed in Open Question-Answering

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
2
2
2

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(7 citation statements)
references
References 0 publications
0
7
0
Order By: Relevance
“…In particular, we focus on adopting the text classification before QA matching and show its effectiveness. For the comparisons, we select two existing methods [26,27] that have not used the text classification while the used sentence embedding methods are the same as the proposed method.…”
Section: Discussionmentioning
confidence: 99%
See 4 more Smart Citations
“…In particular, we focus on adopting the text classification before QA matching and show its effectiveness. For the comparisons, we select two existing methods [26,27] that have not used the text classification while the used sentence embedding methods are the same as the proposed method.…”
Section: Discussionmentioning
confidence: 99%
“…In comparison with the existing methods, we focused on the effects of the classification model-based QA matching models because our approach can be applied into any other advanced embedding models. As a result, we selected two comparisons [26,27] that did not use the classification models while using the same embedding models as used in this paper. The existing QA matching models [26,27] extract the most similar questions from the entire datasets, while we adopt the text classification model to select the most relevant category first.…”
Section: Comparison With the Existing Methodsmentioning
confidence: 99%
See 3 more Smart Citations