ABSTRACT
Question answering (QA) enables the system to answer questions automatically. In recent years, much research has been done in this area. In most methods, question and answer words are given equal importance, which leads to poor model performance. This paper proposed Attention-Based Bidirectional Long-Short Term Memory(BLSTM) to select the answer to the question. In our model, first, word embedding is trained in several different ways. Then, we consider two BLSTM networks for question and answer. The outputs of these two networks and the difference between them are connected and entered into a feed-forward neural network. Finally, this network assigns a score to a question-answer pair. We evaluate our proposed model on the English and Persian datasets about Covid-19. The experiments demonstrate that our model achieves better results than other compared methods.
ABSTRACT
Coronavirus disease 2019 (COVID-2019) appeared in China, in 2019. COVID-2019 expanded all over the world quickly and caused many deaths. COVID-19 has become one of the hottest research areas recently. In this paper, we create a language model (LM) to determine the probability of a given sequence of words occurring in a sentence. Some of the LM applications include machine translation, question answering, and spell checking. In this study, long short-term memory is applied to language modeling of Persian. To do this, we use unidirectional and bidirectional Long Short-Term Memory (LSTM) Models to give contextual informaton. We compared their results together. Our experiments demonstrate how different LSTM language models operate. BiLSTM with two layers is the best language model for Persian COIVD-2019 news. The corpus contains 10,000 pieces of news about COVID-2019 and more than 2,100,000 words, which were provided by the Lobkalam system. © 2021 IEEE.