Predicting the Semantic Textual Similarity with Siamese CNN and LSTM

Elvys Linhares Pontes, Stéphane Huet, Andréa Carneiro Linhares, Juan-Manuel Torres-Moreno


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.
Anthology ID:
2018.jeptalnrecital-court.13
Volume:
Actes de la Conférence TALN. Volume 1 - Articles longs, articles courts de TALN
Month:
5
Year:
2018
Address:
Rennes, France
Editors:
Pascale Sébillot, Vincent Claveau
Venue:
JEP/TALN/RECITAL
SIG:
Publisher:
ATALA
Note:
Pages:
311–320
Language:
URL:
https://aclanthology.org/2018.jeptalnrecital-court.13
DOI:
Bibkey:
Cite (ACL):
Elvys Linhares Pontes, Stéphane Huet, Andréa Carneiro Linhares, and Juan-Manuel Torres-Moreno. 2018. Predicting the Semantic Textual Similarity with Siamese CNN and LSTM. In Actes de la Conférence TALN. Volume 1 - Articles longs, articles courts de TALN, pages 311–320, Rennes, France. ATALA.
Cite (Informal):
Predicting the Semantic Textual Similarity with Siamese CNN and LSTM (Linhares Pontes et al., JEP/TALN/RECITAL 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.jeptalnrecital-court.13.pdf