arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.03285cs.CL
收藏

结合预训练词嵌入和语言特征的序列隐喻识别

Combining Pre-trained Word Embeddings and Linguistic Features for Sequential Metaphor Identification

University of Aberdeen(阿伯丁大学);University of Sheffield(谢菲尔德大学)

Rui Mao, Chenghua Lin, Frank Guerin

摘要:

我们处理的问题,确定文本中的隐喻,作为一个序列标记任务。预训练的词嵌入GloVe,ELMo和BERT分别在顺序隐喻识别上表现出良好的性能。这些嵌入由不同的模型、训练目标和语料库生成,从而编码不同的语义和句法信息。我们表明,利用基于多通道CNN和双向LSTM模型的GloVe、ELMo和基于特征的BERT可以显着优于任何单个词嵌入方法以及两种嵌入的组合。将语言特征引入我们的模型可以进一步提高模型性能,在三个公共隐喻数据集上产生最先进的性能。我们还提供了利用多个词嵌入的有效性的深入分析,包括分析不同的嵌入方法的隐喻和文字的空间分布,并显示如何以及嵌入互补在不同的体裁和词性。

英文摘要:

We tackle the problem of identifying metaphors in text, treated as a sequence tagging task. The pre-trained word embeddings GloVe, ELMo and BERT have individually shown good performance on sequential metaphor identification. These embeddings are generated by different models, training targets and corpora, thus encoding different semantic and syntactic information. We show that leveraging GloVe, ELMo and feature-based BERT based on a multi-channel CNN and a Bidirectional LSTM model can significantly outperform any single word embedding method and the combination of the two embeddings. Incorporating linguistic features into our model can further improve model performance, yielding state-of-the-art performance on three public metaphor datasets. We also provide in-depth analysis on the effectiveness of leveraging multiple word embeddings, including analysing the spatial distribution of different embedding methods for metaphors and literals, and showing how well the embeddings complement each other in different genres and parts of speech.

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。

↑