Aiming to accurately predict missing edges representing relations between
entities, which are pervasive in real-world Knowledge Graphs (KGs), relation
prediction plays a critical role in enhancing the comprehensiveness and utility
of KGs. Recent research focuses on path-based methods due to their inductive
and explainable properties. However, these methods face a great challenge when
lots of reasoning paths do not form Closed Paths (CPs) in the KG. To address
this challenge, we propose Anchoring Path Sentence Transformer (APST) by
introducing Anchoring Paths (APs) to alleviate the reliance of CPs.
Specifically, we develop a search-based description retrieval method to enrich
entity descriptions and an assessment mechanism to evaluate the rationality of
APs. APST takes both APs and CPs as the inputs of a unified Sentence
Transformer architecture, enabling comprehensive predictions and high-quality
explanations. We evaluate APST on three public datasets and achieve
state-of-the-art (SOTA) performance in 30 of 36 transductive, inductive, and
few-shot experimental settings.

关于使用锚定路径来提高关系预测的方法的研究，通过引入锚定路径减轻了闭合路径的依赖性，实现了全面的预测和高质量的解释。

知识图谱中归纳关系预测的锚定路径

Anchoring Path for Inductive Relation Prediction in Knowledge Graphs

This research conducts a comparative study on multilingual text
classification methods, utilizing deep learning and embedding visualization.
The study employs LangDetect, LangId, FastText, and Sentence Transformer on a
dataset encompassing 17 languages. It explores dimensionality's impact on
clustering, revealing FastText's clearer clustering in 2D visualization due to
its extensive multilingual corpus training. Notably, the FastText multi-layer
perceptron model achieved remarkable accuracy, precision, recall, and F1 score,
outperforming the Sentence Transformer model. The study underscores the
effectiveness of these techniques in multilingual text classification,
emphasizing the importance of large multilingual corpora for training
embeddings. It lays the groundwork for future research and assists
practitioners in developing language detection and classification systems.
Additionally, it includes the comparison of multi-layer perceptron, LSTM, and
Convolution models for classification.

该研究通过深度学习和嵌入可视化对多语言文本分类方法进行比较研究，特别关注 FastText 和 Sentence Transformer 模型，并探索了维度对聚类的影响。研究结果显示，FastText 在二维可视化中显示出更清晰的聚类效果，取得了显著的准确性、精确率、召回率和 F1 分数，优于 Sentence Transformer 模型。该研究强调了这些技术在多语言文本分类中的有效性，并强调了使用大型多语言语料库进行嵌入训练的重要性。它为未来的研究奠定了基础，并辅助开发语言检测和分类系统。此外，研究还对多层感知机、LSTM 和卷积模型进行了比较。

跨语言文本分类与识别的深度学习和嵌入可视化的比较分析

Comparative Analysis of Multilingual Text Classification &  Identification through Deep Learning and Embedding Visualization

Large language models underestimate the impact of negations on how much they
change the meaning of a sentence. Therefore, learned evaluation metrics based
on these models are insensitive to negations. In this paper, we propose
NegBLEURT, a negation-aware version of the BLEURT evaluation metric. For that,
we designed a rule-based sentence negation tool and used it to create the
CANNOT negation evaluation dataset. Based on this dataset, we fine-tuned a
sentence transformer and an evaluation metric to improve their negation
sensitivity. Evaluating these models on existing benchmarks shows that our
fine-tuned models outperform existing metrics on the negated sentences by far
while preserving their base models' performances on other perturbations.

本研究旨在改进语言模型对否定词的敏感性，提出了一种基于否定词的 BLEURT 评估指标 NegBLEURT，并通过设计基于规则的句子否定工具和创建 CANNOT 数据集进行模型优化。结果表明，经过优化的模型在否定句上表现优于现有的评估指标，并且在其他扰动上保持基准模型的性能。