Phrase Representation Learning

• Learning Phrase Representations Using RNN Encoder–Decoder for Statistical Machine Translation
• two Recurrent neural networks Basic RNN Architectures that is together able to learn the mapping from a sequence of an arbitrary length to another sequence, possibly from a different set, of an arbitrary length.
• either score a pair of sequences (in terms of a conditional Probability) or generate a target sequence given a source sequence
• jointly trained to maximize the conditional Probability of a target sequence given a source sequence
• reset gate and an update gate that adaptively control how much each hidden unit remembers or forgets while reading/generating a sequenc
• RNN Encoder–Decoder to score each phrase pair in the phrase table
• capture linguistic regularities in the phrase pairs well
• BLEU