BERTScore is an effective and robust automatic metric for referencebased
machine translation evaluation. In this paper, we incorporate multilingual
knowledge graph into BERTScore and propose a metric named KG-BERTScore, which
linearly combines the results of BERTScore and bilingual named entity matching
for reference-free machine translation evaluation. From the experimental
results on WMT19 QE as a metric without references shared tasks, our metric
KG-BERTScore gets higher overall correlation with human judgements than the
current state-of-the-art metrics for reference-free machine translation
evaluation.1 Moreover, the pre-trained multilingual model used by KG-BERTScore
and the parameter for linear combination are also studied in this paper.

本文研究了机器翻译自动评估方法，并将多语言知识图谱融入 BERTScore 之中，提出了一种名为 KG-BERTScore 的评估指标，通过线性组合 BERTScore 和双语命名实体匹配的结果来评估无需参考译文的机器翻译质量，并在实验中证明 KG-BERTScore 相比当前无参考机器翻译评价方法更接近于人工评估结果。同时，本文还探究了 KG-BERTScore 所用到的预训练多语言模型和线性组合参数。

KG-BERTScore：将知识图谱融入 BERTScore 用于无参考机器翻译评价

KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation

Knowledge-enhanced language representation learning has shown promising
results across various knowledge-intensive NLP tasks. However, prior methods
are limited in efficient utilization of multilingual knowledge graph (KG) data
for language model (LM) pretraining. They often train LMs with KGs in indirect
ways, relying on extra entity/relation embeddings to facilitate knowledge
injection. In this work, we explore methods to make better use of the
multilingual annotation and language agnostic property of KG triples, and
present novel knowledge based multilingual language models (KMLMs) trained
directly on the knowledge triples. We first generate a large amount of
multilingual synthetic sentences using the Wikidata KG triples. Then based on
the intra- and inter-sentence structures of the generated data, we design
pretraining tasks to enable the LMs to not only memorize the factual knowledge
but also learn useful logical patterns. Our pretrained KMLMs demonstrate
significant performance improvements on a wide range of knowledge-intensive
cross-lingual tasks, including named entity recognition (NER), factual
knowledge retrieval, relation classification, and a newly designed logical
reasoning task.

本文提出了使用多语言知识图谱三元组进行直接训练的基于知识的多语言语言模型。通过生成大量的多语言合成句子并设计预训练任务，实现了 KMLMs 对事实知识和逻辑模式的学习，并在跨语言任务中展示了显著的性能提升，包括命名实体识别（NER）、事实知识检索、关系分类和新设计的逻辑推理任务。

利用大量多语种知识三元组增强多语言模型

Enhancing Multilingual Language Model with Massive Multilingual  Knowledge Triples

Much research effort has been put to multilingual knowledge graph (KG)
embedding methods to address the entity alignment task, which seeks to match
entities in different languagespecific KGs that refer to the same real-world
object. Such methods are often hindered by the insufficiency of seed alignment
provided between KGs. Therefore, we propose an incidentally supervised model,
JEANS , which jointly represents multilingual KGs and text corpora in a shared
embedding scheme, and seeks to improve entity alignment with incidental
supervision signals from text. JEANS first deploys an entity grounding process
to combine each KG with the monolingual text corpus. Then, two learning
processes are conducted: (i) an embedding learning process to encode the KG and
text of each language in one embedding space, and (ii) a selflearning based
alignment learning process to iteratively induce the matching of entities and
that of lexemes between embeddings. Experiments on benchmark datasets show that
JEANS leads to promising improvement on entity alignment with incidental
supervision, and significantly outperforms state-of-the-art methods that solely
rely on internal information of KGs.

本研究提出了一种名为 JEANS 的 incidentally supervised 模型，该模型联合表示多语言知识图谱和文本语料库，并通过文本提供一定程度的监督信号来改进实体对齐任务。实验结果表明，JEANS 在实体对齐方面具有较好的性能，且显著优于仅依赖于知识图谱内部信息的现有方法。