Open information extraction (OpenIE) aims to extract the schema-free triplets
in the form of (\emph{subject}, \emph{predicate}, \emph{object}) from a given
sentence. Compared with general information extraction (IE), OpenIE poses more
challenges for the IE models, {especially when multiple complicated triplets
exist in a sentence. To extract these complicated triplets more effectively, in
this paper we propose a novel generative OpenIE model, namely \emph{DualOIE},
which achieves a dual task at the same time as extracting some triplets from
the sentence, i.e., converting the triplets into the sentence.} Such dual task
encourages the model to correctly recognize the structure of the given sentence
and thus is helpful to extract all potential triplets from the sentence.
Specifically, DualOIE extracts the triplets in two steps: 1) first extracting a
sequence of all potential predicates, 2) then using the predicate sequence as a
prompt to induce the generation of triplets. Our experiments on two benchmarks
and our dataset constructed from Meituan demonstrate that DualOIE achieves the
best performance among the state-of-the-art baselines. Furthermore, the online
A/B test on Meituan platform shows that 0.93\% improvement of QV-CTR and 0.56\%
improvement of UV-CTR have been obtained when the triplets extracted by DualOIE
were leveraged in Meituan's search system.

提出了一种名为 DualOIE 的新型生成式开放信息提取模型，通过实现双重任务同时从句子中提取三元组并将其转化为句子的形式，有效地从句子中提取复杂三元组，实验证明 DualOIE 在两个基准测试以及美团数据集上表现最佳，Meituan 平台上的在线 A/B 测试显示通过 DualOIE 提取的三元组在美团的搜索系统中可以获得 0.93% 的 QV-CTR 改进和 0.56% 的 UV-CTR 改进。

利用谓词提示在开放式信息抽取中挖掘对偶性

Exploiting Duality in Open Information Extraction with Predicate Prompt

In this work, we tested the Triplet Extraction (TE) capabilities of a variety
of Large Language Models (LLMs) of different sizes in the Zero- and Few-Shots
settings. In detail, we proposed a pipeline that dynamically gathers contextual
information from a Knowledge Base (KB), both in the form of context triplets
and of (sentence, triplets) pairs as examples, and provides it to the LLM
through a prompt. The additional context allowed the LLMs to be competitive
with all the older fully trained baselines based on the Bidirectional Long
Short-Term Memory (BiLSTM) Network architecture. We further conducted a
detailed analysis of the quality of the gathered KB context, finding it to be
strongly correlated with the final TE performance of the model. In contrast,
the size of the model appeared to only logarithmically improve the TE
capabilities of the LLMs.

在本研究中，我们测试了不同规模的大型语言模型在零次和少次侦查设置下的三元组提取（Triplet Extraction）能力。我们提出了一种通过从知识库（Knowledge Base）动态收集上下文信息（以上下文三元组和（句子，三元组）对的形式呈现为示例），并通过提示将其提供给语言模型的管道。附加的上下文信息使得大型语言模型在基于双向长短期记忆（BiLSTM）网络架构的所有旧的完全训练基线上具有竞争力。我们进一步对收集到的知识库上下文质量进行了详细分析，发现它与模型的最终三元组提取性能密切相关。相比之下，模型的规模似乎只会对大型语言模型的三元组提取能力带来对数级的改进。

基于大型语言模型的零射击和少射击知识图谱三元组提取

Zero- and Few-Shots Knowledge Graph Triplet Extraction with Large  Language Models

Triplet extraction aims to extract entities and their corresponding relations
in unstructured text. Most existing methods train an extraction model on
high-quality training data, and hence are incapable of extracting relations
that were not observed during training. Generalizing the model to unseen
relations typically requires fine-tuning on synthetic training data which is
often noisy and unreliable. In this paper, we argue that reducing triplet
extraction to a template filling task over a pre-trained language model can
equip the model with zero-shot learning capabilities and enable it to leverage
the implicit knowledge in the language model. Embodying these ideas, we propose
a novel framework, ZETT (ZEro-shot Triplet extraction by Template infilling),
that is based on end-to-end generative transformers. Our experiments show that
without any data augmentation or pipeline systems, ZETT can outperform previous
state-of-the-art models with 25% less parameters. We further show that ZETT is
more robust in detecting entities and can be incorporated with automatically
generated templates for relations.

本文提出一种新的框架 ZETT，基于预训练语言模型，并采用端到端生成式 Transformer 技术，将三元组抽取任务简化为模板填充任务从而具备了零 - shot 学习能力，并能利用语言模型中的隐含知识，实验表明该方法可以在不进行数据增强和流水线系统的情况下超过之前的最优模型，对实体的检测也更为稳健。