Metaphor Detection via Linguistics Enhanced Siamese Network

1 code implementation • COLING 2022 • Shenglong Zhang, Ying Liu

In this paper we present MisNet, a novel model for word level metaphor detection.

SaGE: 基于句法感知图卷积神经网络和ELECTRA的中文隐喻识别模型(SaGE: Syntax-aware GCN with ELECTRA for Chinese Metaphor Detection)

no code implementations • CCL 2021 • Shenglong Zhang, Ying Liu, Yanjun Ma

“隐喻是人类语言中经常出现的一种特殊现象, 隐喻识别对于自然语言处理各项任务来说具有十分基础和重要的意义。针对中文领域的隐喻识别任务, 我们提出了一种基于句法感知图卷积神经网络和ELECTRA的隐喻识别模型(Syntax-aware GCN withELECTRA SaGE)。该模型从语言学出发, 使用ELECTRA和Transformer编码器抽取句子的语义特征, 将句子按照依存关系组织成一张图并使用图卷积神经网络抽取其句法特征, 在此基础上对两类特征进行融合以进行隐喻识别。我们的模型在CCL2018中文隐喻识别评测数据集上以85. 22%的宏平均F1分数超越了此前的最佳成绩, 验证了融合语义信息和句法信息对于隐喻识别任务具有重要作用。”

Adversarial Multi-task Learning for End-to-end Metaphor Detection

1 code implementation • 26 May 2023 • Shenglong Zhang, Ying Liu

We leverage adversarial training to align the data distributions of MD and BSD in the same feature space, so task-invariant representations can be learned.

Multi-Task Learning Word Sense Disambiguation