Predicting the Semantic Textual Similarity with Siamese CNN and LSTM

Abstract : Semantic Textual Similarity (STS) is the basis of many applications in Natural Language Processing (NLP). Our system combines convolution and recurrent neural networks to measure the semantic similarity of sentences. It uses a convolution network to take account of the local context of words and an LSTM to consider the global context of sentences. This combination of networks helps to preserve the relevant information of sentences and improves the calculation of the similarity between sentences. Our model has achieved good results and is competitive with the best state-of-the-art systems.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01779457
Contributor : Elvys Linhares Pontes <>
Submitted on : Thursday, April 26, 2018 - 3:50:30 PM
Last modification on : Friday, March 22, 2019 - 11:34:07 AM

File

TALN_2018.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01779457, version 1

Collections

Citation

Elvys Linhares Pontes, Stéphane Huet, Andréa Carneiro Linhares, Juan-Manuel Torres-Moreno. Predicting the Semantic Textual Similarity with Siamese CNN and LSTM. Traitement Automatique des Langues Naturelles (TALN), May 2018, Rennes, France. pp.311-319. ⟨hal-01779457⟩

Share

Metrics

Record views

153

Files downloads

2611