Sequence labeling tasks require the computation of sentence representations for each word within a given sentence. With the rise of advanced pretrained language models; one common approach involves incorporating a BiLSTM layer to enhance the sequence structure information at the output level. Nevertheless, it has been empirically demonstrated (P.-H. Li, 2020) that BiLSTM's potential for generating sentence representations for sequence labeling tasks is constrained, primarily due to the integration of fragments from past and future sentence representations to form a complete sentence representation. In this study, we observed that the entire sentence representation, found in both the first and last cells of BiLSTM, can supplement each cell's sentence representation. Accordingly, we devised a global context mechanism to integrate entire future and past sentence representations into each cell's sentence representation within BiLSTM, leading to a significant improvement in both F1 score and accuracy. By embedding the BERT model within BiLSTM as a demonstration, and conducting exhaustive experiments on nine datasets for sequence labeling tasks, including named entity recognition (NER), part of speech (POS) tagging and End-to-End Aspect-Based sentiment analysis (E2E-ABSA). We noted significant improvements in F1 scores and accuracy across all examined datasets.

翻译：序列标注任务需要为给定句子中的每个词计算句子表示。随着先进预训练语言模型的兴起，一种常见方法是在输出层引入BiLSTM层以增强序列结构信息。然而，已有实证研究表明（P.-H. Li, 2020），BiLSTM在生成用于序列标注任务的句子表示方面的潜力受到限制，这主要归因于它整合过去和未来句子表示的片段以形成完整句子表示。本研究中，我们观察到BiLSTM首尾单元中存在的完整句子表示可补充每个单元的句子表示。据此，我们设计了一种全局上下文机制，将完整的未来和过去句子表示整合到BiLSTM中每个单元的句子表示中，从而显著提升F1分数和准确率。通过将BERT模型嵌入BiLSTM作为示例，并在九个涵盖命名实体识别（NER）、词性标注（POS）和端到端方面情感分析（E2E-ABSA）等序列标注任务的数据集上进行详尽实验，我们观察到所有数据集的F1分数和准确率均得到显著提升。