.png){kind=icon}
返回
Phrase based code-switching for cross-lingual question understanding
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-023-16909-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Cross-lingual question understanding involves identifying named entities and question intent in the target language based on corresponding texts from the source-language training dataset. However, relying solely on bilingual parallel corpora has limitations, especially for low-resource languages where such corpora are scarce or unavailable. This paper argues that current cross-lingual techniques hinder the effectiveness of various phrases, particularly noun phrases and interrogative phrases. To address this, a new code-switching data augmentation method called PBCS is introduced for zero-shot cross-lingual training. Unlike recent methods, this approach utilizes small bilingual phrase dictionaries instead of relying on a large bilingual parallel corpus. Moreover, a cross-lingual question understanding model, XQUM, is proposed. At the lower level, the model shares input features and hidden layer states to mitigate error accumulation. Additionally, at the top level, model performance is enhanced through a bi-directional correlation layer based on an iterative mechanism, specifically tailored for the given task. Experimental results on the MQUC and MTOD datasets demonstrate that XQUM significantly improves the accuracy of cross-lingual question understanding tasks.
Keyword:
Cross-lingual
Question understanding
Phrase
NER
QC
Zero-shot
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
分享收藏分享收藏Novel architecture for long short-term memory used in question classification用于问题分类的长短期记忆的新型体系结构.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏分享收藏Endoscopic Nasopharyngectomy for Recurrent Nasopharyngeal Carcinoma: A Review of 31 Patients and Analysis of the Prognostic Factors内镜下鼻咽切除术治疗复发性鼻咽癌：31例患者的回顾及预后因素分析
IF0
PREAI
分享收藏Exploring the Borderlands between Media and Health: Conceptualizing ‘Critical Media Health Literacy’
OAAI
OAAI分享收藏
查看更多内容