.png){kind=icon}
返回
Discriminative explicit instance selection for implicit discourse relation classification
.png){kind=icon}
PRE
AI
DOI：10.1007/s11704-023-3058-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Discourse relation classification is a fundamental task for discourse analysis, which is essential for understanding the structure and connection of texts. Implicit discourse relation classification aims to determine the relationship between adjacent sentences and is very challenging because it lacks explicit discourse connectives as linguistic cues and sufficient annotated training data. In this paper, we propose a discriminative instance selection method to construct synthetic implicit discourse relation data from easy-to-collect explicit discourse relations. An expanded instance consists of an argument pair and its sense label. We introduce the argument pair type classification task, which aims to distinguish between implicit and explicit argument pairs and select the explicit argument pairs that are most similar to natural implicit argument pairs for data expansion. We also propose a simple label-smoothing technique to assign robust sense labels for the selected argument pairs. We evaluate our method on PDTB 2.0 and PDTB 3.0. The results show that our method can consistently improve the performance of the baseline model, and achieve competitive results with the state-of-the-art models.
Keyword:
discourse analysis
PDTB
discourse relation
implicit discourse relation classification
data expansion
期刊
IF:
4.6
论文数:
1.6K
被引数:
2.8K
机构
引用论文
分享收藏
Tyrosine kinase B and C receptors in the neostriatum and nucleus accumbens are co-localized in enkephalin-positive and enkephalin-negative neuronal profiles and their expression is influenced by cocaine.png)
Neuroscience
NeuroscienceIF0
PREAI
分享收藏A comparative study of the effects of methyl jasmonate and abscisic acid on some rice physiological processes茉莉酸甲酯和脱落酸对某些水稻生理过程影响的比较研究
PREAI
分享收藏
查看更多内容