Advances in monolingual and crosslingual automatic disability annotation in Spanish

BMC Bioinformatics

Research

Edgar Andres¹  Koldo Gojenola¹  Aitziber Atutxa¹  Iakes Goenaga² 

[1]HiTZ: Basque Center for Language Technology, University of the Basque Country UPV/EHU, Bilbao, Spain

[2]HiTZ: Basque Center for Language Technology, University of the Basque Country UPV/EHU, Donostia, Spain

关键词: Artificial intelligence;    Neural networks;    Named entity recognition;    Disability annotation;    Embeddings;    Crosslingual learning;   

DOI  :  10.1186/s12859-023-05372-3

 received in 2022-12-21, accepted in 2023-05-31,  发布年份 2023

来源: Springer

【 摘 要 】

BackgroundUnlike diseases, automatic recognition of disabilities has not received the same attention in the area of medical NLP. Progress in this direction is hampered by obstacles like the lack of annotated corpus. Neural architectures learn to translate sequences from spontaneous representations into their corresponding standard representations given a set of samples. The aim of this paper is to present the last advances in monolingual (Spanish) and crosslingual (from English to Spanish and vice versa) automatic disability annotation. The task consists of identifying disability mentions in medical texts written in Spanish within a collection of abstracts from journal papers related to the biomedical domain.ResultsIn order to carry out the task, we have combined deep learning models that use different embedding granularities for sequence to sequence tagging with a simple acronym and abbreviation detection module to boost the coverage.ConclusionsOur monolingual experiments demonstrate that a good combination of different word embedding representations provide better results than single representations, significantly outperforming the state of the art in disability annotation in Spanish. Additionally, we have experimented crosslingual transfer (zero-shot) for disability annotation between English and Spanish with interesting results that might help overcoming the data scarcity bottleneck, specially significant for the disabilities.

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

40517_2023_259_Article_IEq36.gif

40517_2023_259_Article_IEq35.gif

Fig. 2

40517_2023_259_Article_IEq32.gif

Fig. 5

Fig. 8

Fig. 5

42004_2023_919_Article_IEq171.gif

Fig. 4

Fig. 1

42004_2023_919_Article_IEq168.gif

40517_2023_259_Article_IEq13.gif

Fig. 2

40517_2023_259_Article_IEq11.gif

40517_2023_259_Article_IEq8.gif

40517_2023_259_Article_IEq7.gif

40517_2023_259_Article_IEq6.gif

40517_2023_259_Article_IEq5.gif

13011_2023_540_Article_IEq19.gif

Fig. 2

40517_2023_259_Article_IEq2.gif

13011_2023_540_Article_IEq1.gif

42004_2023_919_Article_IEq130.gif

Fig. 1

Fig. 7

41116_2023_37_Article_IEq177.gif

Fig. 1

41116_2023_37_Article_IEq291.gif

41116_2023_37_Article_IEq290.gif

41116_2023_37_Article_IEq289.gif

41116_2023_37_Article_IEq271.gif

41116_2023_37_Article_IEq246.gif

41116_2023_37_Article_IEq229.gif

41116_2023_37_Article_IEq228.gif

41116_2023_37_Article_IEq226.gif

41116_2023_37_Article_IEq213.gif

41116_2023_37_Article_IEq197.gif

41116_2023_37_Article_IEq196.gif

Fig. 1

41116_2023_37_Article_IEq194.gif

41116_2023_37_Article_IEq193.gif

Fig. 1

Fig. 1

Fig. 1

41116_2023_37_Article_IEq188.gif

41116_2023_37_Article_IEq174.gif

Fig. 2

41116_2023_37_Article_IEq152.gif

41116_2023_37_Article_IEq150.gif

Fig. 2

41116_2023_37_Article_IEq140.gif

41116_2023_37_Article_IEq128.gif

41116_2023_37_Article_IEq112.gif

Fig. 2