Predicting the Semantic Textual Similarity with Siamese CNN and LSTM

TL;DR

This paper presents a neural network model combining CNN and LSTM to effectively measure semantic similarity between sentences, improving accuracy in NLP applications.

Contribution

The novel integration of convolutional and recurrent neural networks for semantic similarity measurement enhances sentence understanding.

Findings

Achieved competitive results with state-of-the-art systems

Effectively captures local and global sentence context

Improved semantic similarity scoring accuracy

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.