Chinese Poetry Generation with Recurrent Neural Networks

Xingxing Zhang, Mirella Lapata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a model for Chinese poem generation based on recurrent neural net- works which we argue is ideally suited to capturing poetic content and form. Our generator jointly performs content selection (“what to say”) and surface realization (“how to say”) by learning representations of individual characters, and their combinations into one or more lines as well as how these mutually reinforce and constrain each other. Poem lines are generated incrementally by taking into account the entire history of what has been generated so far rather than the limited horizon imposed by the previous line or lexical n-grams. Experimental results show that our model outperforms competitive Chinese poetry generation systems using both automatic and manual evaluation methods.
Original languageEnglish
Title of host publicationProceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Place of PublicationDoha, Qatar
PublisherAssociation for Computational Linguistics
Pages670-680
Number of pages11
Publication statusPublished - 1 Oct 2014

Fingerprint

Dive into the research topics of 'Chinese Poetry Generation with Recurrent Neural Networks'. Together they form a unique fingerprint.

Cite this