arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.16210cs.CLcs.LGstat.ML
收藏

用于序列标记的局部上下文非线性CRF

Locally-Contextual Nonlinear CRFs for Sequence Labeling

University College London(伦敦大学学院);Alan Turing Institute(艾伦·图灵研究所)

Harshil Shah, Tim Xiao, David Barber

摘要:

线性链条件随机场(CRF)与上下文词嵌入相结合的序列标记任务的最先进的性能。在许多这些任务中,当预测给定单词的标签时,相邻单词的身份通常是最有用的上下文信息。然而,上下文嵌入通常以任务不可知的方式训练。这意味着,虽然它们可以编码关于相邻字的信息,但不能保证。因此,设计序列标记架构以直接从嵌入中提取该信息可能是有益的。我们提出了局部上下文的非线性CRF序列标记。我们的方法在预测给定单词的标签时直接结合来自相邻嵌入的信息,并使用深度神经网络参数化潜在函数。我们的模型作为线性链CRF的替代品,在我们的消融研究中始终优于它。在各种各样的任务,我们的结果是具有竞争力的最好的公布的方法。特别是,我们超越了以前的国家的最先进的组块在CoNLL 2000和命名实体识别OntoNotes 5.0英语。

英文摘要:

Linear chain conditional random fields (CRFs) combined with contextual word embeddings have achieved state of the art performance on sequence labeling tasks. In many of these tasks, the identity of the neighboring words is often the most useful contextual information when predicting the label of a given word. However, contextual embeddings are usually trained in a task-agnostic manner. This means that although they may encode information about the neighboring words, it is not guaranteed. It can therefore be beneficial to design the sequence labeling architecture to directly extract this information from the embeddings. We propose locally-contextual nonlinear CRFs for sequence labeling. Our approach directly incorporates information from the neighboring embeddings when predicting the label for a given word, and parametrizes the potential functions using deep neural networks. Our model serves as a drop-in replacement for the linear chain CRF, consistently outperforming it in our ablation study. On a variety of tasks, our results are competitive with those of the best published methods. In particular, we outperform the previous state of the art on chunking on CoNLL 2000 and named entity recognition on OntoNotes 5.0 English.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑