• Publications
  • Influence
DeepSentiPers: Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus
This work proposes two novel deep learning architectures comprises of bidirectional LSTM and CNN that are a part of a deep hierarchy designed precisely and also able to classify sentences in both cases.
A Novel Pipeline for Domain Detection and Selecting In-domain Sentences in Machine Translation Systems
A novel unsupervised pipeline for identifying distributions of different domains within a corpus and a data selection technique that leverages in-domain monolingual or parallel data to select domain-specific sentences from general corpora according to the distribution defined in (i).
Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts
The proposed method ranks sentences in parallel generaldomain data according to their cosine similarity with a monolingual domain-specific data set to select the top K sentences with the highest similarity score to train a new machine translation system tuned to the specific in-domain data.