Chinese Poetry Generation with a Working Memory Model

Authors: Xiaoyuan Yi, Maosong Sun, Ruoyu Li, Zonghan Yang

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We experiment on three different genres of Chinese poetry: quatrain, iambic and chinoiserie lyric. Both automatic and human evaluation results show that our model outperforms current state-of-the-art methods.
Researcher Affiliation Collaboration Xiaoyuan Yi1, Maosong Sun1 , Ruoyu Li2, Zonghan Yang1 1 State Key Lab on Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing, China 2 6ESTATES PTE LTD, Singapore
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes https://github.com/xiaoyuan Yi/WMPoetry.
Open Datasets No Table 1 shows details of our corpus. We use 1,000 quatrains, 843 iambics and 100 lyrics for validation; 1,000 quatrains, 900 iambics and 100 lyrics for testing. The rest are used for training. The paper describes its own collected corpus but does not provide access information (link, DOI, specific citation to a public source).
Dataset Splits Yes We use 1,000 quatrains, 843 iambics and 100 lyrics for validation; 1,000 quatrains, 900 iambics and 100 lyrics for testing. The rest are used for training.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or memory amounts used for experiments.
Software Dependencies No The paper does not provide specific version numbers for any software dependencies, libraries, or frameworks used in the experiments.
Experiment Setup Yes We set K1 = 4 and K2 = 4. The sizes of word embedding, phonology embedding, length embedding, hidden state, global trace vector, topic trace vector are set to 256, 64, 32, 512, 512, 24 (20+4) respectively. ... Adam with shuffled mini-batches (batch size 64) is used for optimization. To avoid overfitting, 25% dropout and ℓ2 regularization are used. ... all models generate each poem with beam search (beam size 20).