We present mGENRE, a sequence-to-sequence system for the Multilingual Entity
Linking (MEL) problem -- the task of resolving language-specific mentions to a
multilingual Knowledge Base (KB). For a mention in a given language, mGENRE
predicts the name of the target entity left-to-right, token-by-token in an
autoregressive fashion. The autoregressive formulation allows us to effectively
cross-encode mention string and entity names to capture more interactions than
the standard dot product between mention and entity vectors. It also enables
fast search within a large KB even for mentions that do not appear in mention
tables and with no need for large-scale vector indices. While prior MEL works
use a single representation for each entity, we match against entity names of
as many languages as possible, which allows exploiting language connections
between source input and target name. Moreover, in a zero-shot setting on
languages with no training data at all, mGENRE treats the target language as a
latent variable that is marginalized at prediction time. This leads to over 50%
improvements in average accuracy. We show the efficacy of our approach through
extensive evaluation including experiments on three popular MEL benchmarks
where mGENRE establishes new state-of-the-art results. Code and pre-trained
models at this https URL

本文介绍了 mGENRE，一个多语言实体链接（MEL）问题的序列到序列系统。使用自回归网络，mGENRE 将输入句子中的实体转化为 KB 中的目标实体，采用多语言实体名称匹配方案，在零样本情境下取得 50% 以上的性能提升，实现了最新的最好表现。

多语言自回归实体链接

Multilingual Autoregressive Entity Linking

We propose a new formulation for multilingual entity linking, where
language-specific mentions resolve to a language-agnostic Knowledge Base. We
train a dual encoder in this new setting, building on prior work with improved
feature representation, negative mining, and an auxiliary entity-pairing task,
to obtain a single entity retrieval model that covers 100+ languages and 20
million entities. The model outperforms state-of-the-art results from a far
more limited cross-lingual linking task. Rare entities and low-resource
languages pose challenges at this large-scale, so we advocate for an increased
focus on zero- and few-shot evaluation. To this end, we provide Mewsli-9, a
large new multilingual dataset (this http URL) matched to our
setting, and show how frequency-based analysis provided key insights for our
model and training enhancements.

提出了一种新的多语言实体链接公式，其中语言特定的提及解析为面向语言不可知的知识库。 在改进特征表示，负面挖掘和辅助实体配对任务的先前工作的基础上，我们在这个新的环境中训练了一个双编码器，以获得单个实体检索模型，它涵盖了 100 多种语言和 2000 万个实体。该模型胜过了远远有限的跨语言链接任务的最新结果。 这个大规模的系统面临着罕见实体和低资源语言的挑战，因此我们主张增加对零点和少量射击评估的关注。 为此，我们提供了 Mewsli-9，一个新的大型多语言数据集，帮助我们了解基于频率的分析如何为我们的模型和训练增强提供关键见解。