Inspired by recent advances in retrieval augmented methods in
NLP~\citep{khandelwal2019generalization,khandelwal2020nearest,meng2021gnn}, in
this paper, we introduce a $k$ nearest neighbor NER ($k$NN-NER) framework,
which augments the distribution of entity labels by assigning $k$ nearest
neighbors retrieved from the training set. This strategy makes the model more
capable of handling long-tail cases, along with better few-shot learning
abilities. $k$NN-NER requires no additional operation during the training
phase, and by interpolating $k$ nearest neighbors search into the vanilla NER
model, $k$NN-NER consistently outperforms its vanilla counterparts: we achieve
a new state-of-the-art F1-score of 72.03 (+1.25) on the Chinese Weibo dataset
and improved results on a variety of widely used NER benchmarks. Additionally,
we show that $k$NN-NER can achieve comparable results to the vanilla NER model
with 40\% less amount of training data. Code available at
https://github.com/ShannonAI/KNN-NER.

本文介绍了一种新的基于 $k$NN 的实体标注框架，运用 $k$ nearest neighbor 方法来增强实体标签的分布，提高 NER 的 few-shot 学习能力和对 long-tail cases 的处理能力，并在多个数据集上验证和比较其性能，达到了比目前最好的结果更好的 F1 分数。

$k$NN-NER：最近邻搜索的命名实体识别

$k$NN-NER: Named Entity Recognition with Nearest Neighbor Search

Structured text understanding on Visually Rich Documents (VRDs) is a crucial
part of Document Intelligence. Due to the complexity of content and layout in
VRDs, structured text understanding has been a challenging task. Most existing
studies decoupled this problem into two sub-tasks: entity labeling and entity
linking, which require an entire understanding of the context of documents at
both token and segment levels. However, little work has been concerned with the
solutions that efficiently extract the structured data from different levels.
This paper proposes a unified framework named StrucTexT, which is flexible and
effective for handling both sub-tasks. Specifically, based on the transformer,
we introduce a segment-token aligned encoder to deal with the entity labeling
and entity linking tasks at different levels of granularity. Moreover, we
design a novel pre-training strategy with three self-supervised tasks to learn
a richer representation. StrucTexT uses the existing Masked Visual Language
Modeling task and the new Sentence Length Prediction and Paired Boxes Direction
tasks to incorporate the multi-modal information across text, image, and
layout. We evaluate our method for structured text understanding at
segment-level and token-level and show it outperforms the state-of-the-art
counterparts with significantly superior performance on the FUNSD, SROIE, and
EPHOIE datasets.

本文提出一种名为 StrucTexT 的统一框架，该框架使用 transformer 构建了一个段 - 标记对齐的编码器来处理文档上下文中不同层面的实体标记和链接任务，并使用三个自监督任务设计了一种新颖的预训练策略，以有效地提取多模态信息，从而优于 FUNSD，SROIE 和 EPHOIE 数据集的现有方法。

StrucTexT: 多模态 Transformer 的结构化文本理解

StrucTexT: Structured Text Understanding with Multi-Modal Transformers

An image caption should fluently present the essential information in a given
image, including informative, fine-grained entity mentions and the manner in
which these entities interact. However, current captioning models are usually
trained to generate captions that only contain common object names, thus
falling short on an important "informativeness" dimension. We present a
mechanism for integrating image information together with fine-grained labels
(assumed to be generated by some upstream models) into a caption that describes
the image in a fluent and informative manner. We introduce a multimodal,
multi-encoder model based on Transformer that ingests both image features and
multiple sources of entity labels. We demonstrate that we can learn to control
the appearance of these entity labels in the output, resulting in captions that
are both fluent and informative.

本文提出了使用多模态、多编码器 Transformer 模型将图像信息结合细粒度标签生成信息准确、流畅的图像标注，实现了对实体标签输出的控制，提高了图像描述的准确性和信息丰富程度。