arXiv (Cornell University) · 2016 · 37 citations · 10 references
ComputingLinguisticsMemoryNatural Language ProcessingPoetryDeep LearningLanguage ModelingSpeech RecognitionSpeech SynthesisText GenerationIambic PoetryInitializationLong Short-term Memory NetworksPoetic GenerationPoetry GenerationSequence GenerationSequence Representation LearningSequence-to-sequence Generation
Learning and generating Chinese poems is a charming yet challenging task. Traditional approaches involve various language modeling and machine translation techniques, however, they perform not as well when generating poems with complex pattern constraints, for example Song iambics, a famous type of poems that involve variable-length sentences and strict rhythmic patterns. This paper applies the attention-based sequence-to-sequence model to generate Chinese Song iambics. Specifically, we encode the cue sentences by a bi-directional Long-Short Term Memory (LSTM) model and then predict the entire iambic with the information provided by the encoder, in the form of an attention-based LSTM that can regularize the generation process by the fine structure of the input cues. Several techniques are investigated to improve the model, including global context integration, hybrid style training, character vector initialization and adaptation. Both the automatic and subjective evaluation results show that our model indeed can learn the complex structural and rhythmic patterns of Song iambics, and the generation is rather successful.
10
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
ADADELTA: An Adaptive Learning Rate Method
Matthew D. Zeiler · arXiv (Cornell University) · 2012 · 5.5K citations · Full text
Philipp Koehn, Richard Zens, Chris Dyer et al. · 2007 · 4.9K citations · Full text
Chinese Poetry Generation with Recurrent Neural Networks
Xingxing Zhang, Mirella Lapata · 2014 · 329 citations · Full text