This work presents a new task of Text Expansion (TE), which aims to insert
fine-grained modifiers into proper locations of the plain text to concretize or
vivify human writings. Different from existing insertion-based writing
assistance tasks, TE requires the model to be more flexible in both locating
and generation, and also more cautious in keeping basic semantics. We leverage
four complementary approaches to construct a dataset with 12 million
automatically generated instances and 2K human-annotated references for both
English and Chinese. To facilitate automatic evaluation, we design various
metrics from multiple perspectives. In particular, we propose Info-Gain to
effectively measure the informativeness of expansions, which is an important
quality dimension in TE. On top of a pre-trained text-infilling model, we build
both pipelined and joint Locate&Infill models, which demonstrate the
superiority over the Text2Text baselines, especially in expansion
informativeness. Experiments verify the feasibility of the TE task and point
out potential directions for future research toward better automatic text
expansion.

本文提出了文本扩展（TE）的新任务，旨在插入细粒度修改器到纯文本的适当位置以具象化或使人类写作更生动。通过四种互补方法，我们构建了一份包含 1200 万个自动生成实例和 2000 个人工注释的英文和中文数据集。为了便于自动评估，我们从多个角度设计了各种度量指标，特别是提出了 Info-Gain 来有效度量扩展的信息量，它是 TE 任务中一个重要的质量维度。在基于预训练的文本填充模型的基础上，我们构建了基于流水线和联合定位和填充模型，证明了其在扩展信息量上优于 Text2Text 基线方法。实验证实了 TE 任务的可行性，并指出了未来研究朝着更好的自动文本扩展方向的潜在研究方向。

文本扩展基准：数据集、度量和基准线

A Benchmark for Text Expansion: Datasets, Metrics, and Baselines

We propose Referral-Augmented Retrieval (RAR), a simple technique that
concatenates document indices with referrals, i.e. text from other documents
that cite or link to the given document, to provide significant performance
gains for zero-shot information retrieval. The key insight behind our method is
that referrals provide a more complete, multi-view representation of a
document, much like incoming page links in algorithms like PageRank provide a
comprehensive idea of a webpage's importance. RAR works with both sparse and
dense retrievers, and outperforms generative text expansion techniques such as
DocT5Query and Query2Doc a 37% and 21% absolute improvement on ACL paper
retrieval Recall@10 -- while also eliminating expensive model training and
inference. We also analyze different methods for multi-referral aggregation and
show that RAR enables up-to-date information retrieval without re-training.

提出 Referral-Augmented Retrieval（RAR），用于零 - shot 信息检索，通过链接到特定文档的其他文档的文本来提供更全面、多视角的文档表示，这种方法与稀疏型和密集型召回器一起使用可以消除模型训练和推理的昂贵成本，并取得了最多 37% 的绝对改进。