Semantic Textual Similarity (STS) evaluationassesses the degree to which two partsof texts are similar, based on their semanticevaluation. In this paper, we describe threemodels submitted to STS SemEval 2017.Given two English parts of a text, each ofproposed methods outputs the assessmentof their semantic similarity.We propose an approach for computingmonolingual semantic textual similaritybased on an ensemble of three distinctmethods. Our model consists of recursiveneural network (RNN) text auto-encodersensemble with supervised a model of vectorizedsentences using reduced part ofspeech (PoS) weighted word embeddingsas well as unsupervised a method basedon word coverage (TakeLab). Additionally,we enrich our model with additionalfeatures that allow disambiguation of ensemblemethods based on their efficiency.We have used Multi-Layer Perceptron as anensemble classifier basing on estimationsof trained Gradient Boosting Regressors.Results of our research proves that usingsuch ensemble leads to a higher accuracydue to a fact that each memberalgorithmtends to specialize in particulartype of sentences. Simple model basedon PoS weighted Word2Vec word embeddingsseem to improve performance ofmore complex RNN based auto-encoders inthe ensemble. In the monolingual EnglishEnglishSTS subtask our Ensemble basedmodel achieved mean Pearson correlationof .785 compared with human annotators.