# Bidirectional RNNs As noted earlier, if we use a simple RNN to predict the next word in a sentence, we will only be using information from words that occurred previously in the sentence. BRNNs allow us to use information from words that occur later in the sentence as well. The disadvantage is that we need the entire sequence of data to make use of it. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://vikram-bajaj.gitbook.io/deep-learning-specialization-coursera/main-10/sequence-models/recurrent-neural-networks/bidirectional-rnns.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.