Poetry generation, and creative language generation in general, usually
suffers from the lack of large training data. In this paper, we present a novel
framework to generate sonnets that does not require training on poems. We
design a hierarchical framework which plans the poem sketch before decoding.
Specifically, a content planning module is trained on non-poetic texts to
obtain discourse-level coherence; then a rhyme module generates rhyme words and
a polishing module introduces imagery and similes for aesthetics purposes.
Finally, we design a constrained decoding algorithm to impose the
meter-and-rhyme constraint of the generated sonnets. Automatic and human
evaluation show that our multi-stage approach without training on poem corpora
generates more coherent, poetic, and creative sonnets than several strong
baselines.

本文提出了一个新的层次框架，用于生成十四行诗，不需要训练。该框架包括内容规划模块、韵脚模块和润色模块，并设计了受约束的解码算法以实现生成的十四行诗的韵律和韵脚约束。自动和人工评估表明，该框架比几个强基线更具连贯性、诗意和创造性。

使用话语级别规划和美学特征的零样本十四行诗生成

Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features

The Deep Learning Track is a new track for TREC 2019, with the goal of
studying ad hoc ranking in a large data regime. It is the first track with
large human-labeled training sets, introducing two sets corresponding to two
tasks, each with rigorous TREC-style blind evaluation and reusable test sets.
The document retrieval task has a corpus of 3.2 million documents with 367
thousand training queries, for which we generate a reusable test set of 43
queries. The passage retrieval task has a corpus of 8.8 million passages with
503 thousand training queries, for which we generate a reusable test set of 43
queries. This year 15 groups submitted a total of 75 runs, using various
combinations of deep learning, transfer learning and traditional IR ranking
methods. Deep learning runs significantly outperformed traditional IR runs.
Possible explanations for this result are that we introduced large training
data and we included deep models trained on such data in our judging pools,
whereas some past studies did not have such training data or pooling.

TREC 2019 新推出的 Deep Learning Track 使用大量标注数据，对包含三百万文档和五十万训练查询的 Ad Hoc 排名展开研究，结果 Deep Learning 方法在 15 组提交的 75 个运行中取得了优异的表现。