Word embeddings for negation detection in health records written in Spanish

Santiso, Sara; Casillas, Arantza; Pérez, Alicia; Oronoz, Maite

doi:10.1007/s00500-018-3650-7

Cited by 11 publications

(19 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 21 shows the results for the IULA corpus. Furthermore, we compared our results with the work presented previously [ 85 ]. We used the evaluation criteria presented in this work; however, the subsets were different.…”

Section: Resultsmentioning

confidence: 90%

“…Some recent works also exploit this algorithm for negation detection in other languages, such as French, German, and Swedish [ 10 ], Swedish [ 11 ], and Spanish [ 12 ]. Machine learning methods have been applied to cope with the negation detection task, using mainly a conditional random field (CRF) algorithm with dense vector features, such as character or word embedding [ 13 , 14 ]. More recently, deep learning approaches using recurrent neural networks (RNNs), convolutional neuronal networks (CNNs), and encoder-decoder models have also been exploited to solve this task [ 15 - 17 ].…”

Section: Introductionmentioning

confidence: 99%

“…DepNeg [ 29 ] uses syntactic parsing. Among rule-based approaches, the most used negation detection tool in English is NegEx [ 13 ], which employs an exact match to a list of medical entities and negation triggers (eg, “NO history of exposure” and “DENIES any nausea”). NegEx was adapted to address negation detection for other languages, such as Swedish [ 11 ], French [ 30 ], German [ 12 ], and Spanish [ 31 ].…”

Section: Introductionmentioning

confidence: 99%

“…The best F-measure was 99% for cue detection and 94% for scope detection in Chinese text, and it was concluded that embedding features can help to achieve better performance. Santiso et al [ 13 ] proposed a similar system using spare and dense word feature representations and a CRF algorithm to detect only negated entities in Spanish clinical text. The system obtained F-measures of 45.8% and 81.2% for the IxaMed-GS corpus [ 44 ] and the IULA corpus [ 45 ], respectively.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The Impact of Pretrained Language Models on Negation and Speculation Detection in Cross-Lingual Medical Text: Comparative Study

Zavala¹,

Martı́nez²

2020

JMIR Med Inform

View full text Add to dashboard Cite

Background Negation and speculation are critical elements in natural language processing (NLP)-related tasks, such as information extraction, as these phenomena change the truth value of a proposition. In the clinical narrative that is informal, these linguistic facts are used extensively with the objective of indicating hypotheses, impressions, or negative findings. Previous state-of-the-art approaches addressed negation and speculation detection tasks using rule-based methods, but in the last few years, models based on machine learning and deep learning exploiting morphological, syntactic, and semantic features represented as spare and dense vectors have emerged. However, although such methods of named entity recognition (NER) employ a broad set of features, they are limited to existing pretrained models for a specific domain or language. Objective As a fundamental subsystem of any information extraction pipeline, a system for cross-lingual and domain-independent negation and speculation detection was introduced with special focus on the biomedical scientific literature and clinical narrative. In this work, detection of negation and speculation was considered as a sequence-labeling task where cues and the scopes of both phenomena are recognized as a sequence of nested labels recognized in a single step. Methods We proposed the following two approaches for negation and speculation detection: (1) bidirectional long short-term memory (Bi-LSTM) and conditional random field using character, word, and sense embeddings to deal with the extraction of semantic, syntactic, and contextual patterns and (2) bidirectional encoder representations for transformers (BERT) with fine tuning for NER. Results The approach was evaluated for English and Spanish languages on biomedical and review text, particularly with the BioScope corpus, IULA corpus, and SFU Spanish Review corpus, with F-measures of 86.6%, 85.0%, and 88.1%, respectively, for NeuroNER and 86.4%, 80.8%, and 91.7%, respectively, for BERT. Conclusions These results show that these architectures perform considerably better than the previous rule-based and conventional machine learning–based systems. Moreover, our analysis results show that pretrained word embedding and particularly contextualized embedding for biomedical corpora help to understand complexities inherent to biomedical text.

show abstract

Section: Resultsmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Impact of Pretrained Language Models on Negation and Speculation Detection in Cross-Lingual Medical Text: Comparative Study

Zavala¹,

Martı́nez²

2020

JMIR Med Inform

View full text Add to dashboard Cite

show abstract

“…El número de aplicaciones clínicas de PLN en inglés es mayor que en otros idiomas debido a su simplicidad como lenguaje, así como también a la gran cantidad de recursos computacionales y de texto anotado que existe en inglés 5 . Sin embargo, existen reportes de existosas aplicaciones de PLN a textos clínicos en español, tales como la identificación de enfermedades o medicamentos dentro de narrativas médicas 8,9 o la detección de expresiones que indican negación 10 . Sin embargo, la escasez de grandes volúmenes de texto clínico en español abiertos a la comunidad científica sigue siendo una dificultad.…”

unclassified

Obtención automática de palabras clave en textos clínicos: una aplicación de procesamiento del lenguaje natural a datos masivos de sospecha diagnóstica en Chile

Villena

Dunstan

2019

Rev. méd. Chile

View full text Add to dashboard Cite

Automatic keyword retrieval from clinical texts: an application of natural language processing to massive data of Chilean suspected diagnosis Background: Free-text imposes a challenge in health data analysis since the lack of structure makes the extraction and integration of information difficult, particularly in the case of massive data. An appropriate machine-interpretation of electronic health records in Chile can unleash knowledge contained in large volumes of clinical texts, expanding clinical management and national research capabilities. Aim: To illustrate the use of a weighted frequency algorithm to find keywords. This finding was carried out in the diagnostic suspicion field of the Chilean specialty consultation waiting list, for diseases not covered by the Chilean Explicit Health Guarantees plan. Material and Methods: The waiting lists for a first specialty consultation for the period 2008-2018 were obtained from 17 out of 29 Chilean health services, and total of 2,592,925 diagnostic suspicions were identified. A natural language processing technique called Term Frequency-Inverse Document Frequency was used for the retrieval of diagnostic suspicion keywords. Results: For each specialty, four key words with the highest weighted frequency were determined. Word clouds showing words weighted by their importance were created to obtain a visual representation. These are available at cimt.uchile.cl/lechile/. Conclusions: The algorithm allowed to summarize unstructured clinical free-text data, improving its usefulness and accessibility.

show abstract

Enhanced sentimental analysis using visual geometry group network-based deep learning approach

Sathish¹,

Ezhumalai

2021

Soft Comput

View full text Add to dashboard Cite

Word embeddings for negation detection in health records written in Spanish

Cited by 11 publications

References 29 publications

The Impact of Pretrained Language Models on Negation and Speculation Detection in Cross-Lingual Medical Text: Comparative Study

The Impact of Pretrained Language Models on Negation and Speculation Detection in Cross-Lingual Medical Text: Comparative Study

Obtención automática de palabras clave en textos clínicos: una aplicación de procesamiento del lenguaje natural a datos masivos de sospecha diagnóstica en Chile

Enhanced sentimental analysis using visual geometry group network-based deep learning approach

Contact Info

Product

Resources

About