This document contains a discussion of the F1 score evaluation used in the
article 'Relation Classification with Entity Type Restriction' by Shengfei Lyu,
Huanhuan Chen published on Findings of the Association for Computational
Linguistics: ACL-IJCNLP 2021. The authors created a system named RECENT and
claim it achieves (then) a new state-of-the-art result 75.2 (previous 74.8) on
the TACRED dataset, while after correcting errors and reevaluation the final
result is 65.16

讨论了 Shengfei Lyu 和 Huanhuan Chen 在 ACL-IJCNLP 2021 上发表的文章 “受实体类型限制的关系分类” 中使用的 F1 分数评估，讨论了他们创建的 RECENT 系统在 TACRED 数据集上的表现，最终结果为 65.16。

关于评估最新关系抽取系统 F1 分数的研究

About Evaluation of F1 Score for RECENT Relation Extraction System

Dependency trees help relation extraction models capture long-range relations
between words. However, existing dependency-based models either neglect crucial
information (e.g., negation) by pruning the dependency trees too aggressively,
or are computationally inefficient because it is difficult to parallelize over
different tree structures. We propose an extension of graph convolutional
networks that is tailored for relation extraction, which pools information over
arbitrary dependency structures efficiently in parallel. To incorporate
relevant information while maximally removing irrelevant content, we further
apply a novel pruning strategy to the input trees by keeping words immediately
around the shortest path between the two entities among which a relation might
hold. The resulting model achieves state-of-the-art performance on the
large-scale TACRED dataset, outperforming existing sequence and
dependency-based neural models. We also show through detailed analysis that
this model has complementary strengths to sequence models, and combining them
further improves the state of the art.

本文提出了一种基于图卷积网络的关系抽取模型，针对依存句法树存在的缺陷进行了改进，通过保留两个实体间最短路径周围的词语并采用并行化方法来高效地汇总任意依存句法结构中的信息，最终在大规模 TACRED 数据集上取得最先进的性能，且与序列模型互补，二者结合可以进一步提高性能。

基于修剪依存树的图卷积改善关系抽取

Graph Convolution over Pruned Dependency Trees Improves Relation  Extraction

This paper describes how to apply self-attention with relative positional
encodings to the task of relation extraction. We propose to use the
self-attention encoder layer together with an additional position-aware
attention layer that takes into account positions of the query and the object
in the sentence. The self-attention encoder also uses a custom implementation
of relative positional encodings which allow each word in the sentence to take
into account its left and right context. The evaluation of the model is done on
the TACRED dataset. The proposed model relies only on attention (no recurrent
or convolutional layers are used), while improving performance w.r.t. the
previous state of the art.

本文提出如何在关系抽取任务中使用自注意力和相对位置编码。使用一个位置感知的注意力层，利用相对位置编码使每个单词考虑其左右上下文，仅使用注意力机制，在 TACRED 数据集上表现显著提升。