The task of measure semantic redundancy between sentences demands a thorough interpretation from the reader because phrase meaning may be ambiguous. Detecting semantic similarity is a difficult problem because natural language, besides ambiguity, offers almost infinite possibilities to express the same idea. This paper adapts a siamese neural network architecture trained to measure the semantic similarity between two sentences through metric learning. The resulting solution should help in writing more efficient and informative text.
|Title of host publication||2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Publication status||Published - 10 Oct 2018|
|Event||2018 International Joint Conference on Neural Networks, IJCNN 2018 - Rio de Janeiro, Brazil|
Duration: 8 Jul 2018 → 13 Jul 2018
|Name||Proceedings of the International Joint Conference on Neural Networks|
|Conference||2018 International Joint Conference on Neural Networks, IJCNN 2018|
|City||Rio de Janeiro|
|Period||8/07/18 → 13/07/18|
Bibliographical noteFunding Information:
Felipe thanks CNPq for partial financial support under its PQ fellowship, grant number 305969/2016-1.
© 2018 IEEE.
- metric learning
- Neural networks
- recurrent neural network
- semantic analysis
- siamese neural networks
- word embedding