Joint segmentation and named entity recognition using dual decomposition in Chinese discharge summaries

Xu, Yan; Wang, Yining; Liu, Tianren; Liu, Jiahua; Fan, Yubo; Qian, Yi; Tsujii, Jun’ichi; Chang, Eric

doi:10.1136/amiajnl-2013-001806

Cited by 62 publications

(44 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As in the framework of "named entity translation", Chinese named entity recognizers (NERs) [21] play an important role in our system. They recognize test terms (i.e., Chinese terms which are terms not in the seed set and should be linked with English terms) as well as the seed terms in their contexts.…”

Section: Context-similarity-based Extraction Methods -A Baseline Systemmentioning

confidence: 99%

“…Before bilingual lexicon extraction, we first apply NERs [21,22] to discharge summaries in the two languages. These two monolingual processing phases produce a set of test terms (i.e., terms not appearing in the seed dictionary) to be linked, and locate where the predefined 1,200 seed terms appear.…”

Section: Context-similarity-based Extraction Methods -A Baseline Systemmentioning

confidence: 99%

“…In the processing flow of our system, Chinese terms are first recognized by an NER based on a joint model of NER and word segmentation [21]. The NER produces not only boundaries of terms but also segmentation of sentences into words.…”

Section: Alignment Of Multi-word Termmentioning

confidence: 99%

“…The NERs are applied to extract named entities (i.e., terms) from the summaries. We use our own English and Chinese NERs, both of which show the state of the art performance [21,23]. For the purposes of our experiments, we retain only those terms belonging to the categories Medical Problem, Treatment and Test.…”

Section: Experiments Datamentioning

confidence: 99%

See 3 more Smart Citations

Bilingual term alignment from comparable corpora in English discharge summary and Chinese discharge summary

Chen

Jiang

et al. 2015

BMC Bioinformatics

Self Cite

View full text Add to dashboard Cite

Background: Electronic medical record (EMR) systems have become widely used throughout the world to improve the quality of healthcare and the efficiency of hospital services. A bilingual medical lexicon of Chinese and English is needed to meet the demand for the multi-lingual and multi-national treatment. We make efforts to extract a bilingual lexicon from English and Chinese discharge summaries with a small seed lexicon. The lexical terms can be classified into two categories: single-word terms (SWTs) and multi-word terms (MWTs). For SWTs, we use a label propagation (LP; context-based) method to extract candidates of translation pairs. For MWTs, which are pervasive in the medical domain, we propose a term alignment method, which firstly obtains translation candidates for each component word of a Chinese MWT, and then generates their combinations, from which the system selects a set of plausible translation candidates. Results: We compare our LP method with a baseline method based on simple context-similarity. The LP based method outperforms the baseline with the accuracies: 4.44% Acc1, 24.44% Acc10, and 62.22% Acc100, where AccN means the top N accuracy. The accuracy of the LP method drops to 5.41% Acc10 and 8.11% Acc20 for MWTs. Our experiments show that the method based on term alignment improves the performance for MWTs to 16.22% Acc10 and 27.03% Acc20. Conclusions: We constructed a framework for building an English-Chinese term dictionary from discharge summaries in the two languages. Our experiments have shown that the LP-based method augmented with the term alignment method will contribute to reduction of manual work required to compile a bilingual sydictionary of clinical terms.

show abstract

Section: Context-similarity-based Extraction Methods -A Baseline Systemmentioning

confidence: 99%

Section: Context-similarity-based Extraction Methods -A Baseline Systemmentioning

confidence: 99%

Section: Alignment Of Multi-word Termmentioning

confidence: 99%

Section: Experiments Datamentioning

confidence: 99%

See 2 more Smart Citations

Bilingual term alignment from comparable corpora in English discharge summary and Chinese discharge summary

Chen

Jiang

et al. 2015

BMC Bioinformatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, hospitals in China have been rapidly deploying EHR systems, which generate a great amount of clinical data. Efforts have been made in the research community to construct NLP components for Chinese clinical notes [5–8], but to our best knowledge there is no established system identifying clinical speculations.…”

Section: Introductionmentioning

confidence: 99%

Speculation detection for Chinese clinical notes: Impacts of word segmentation and embedding models

Zhang

Kang

Zhang

et al. 2016

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Speculations represent uncertainty towards certain facts. In clinical texts, identifying speculations is a critical step of natural language processing (NLP). While it is a nontrivial task in many languages, detecting speculations in Chinese clinical notes can be particularly challenging because word segmentation may be necessary as an upstream operation. The objective of this paper is to construct a state-of-the-art speculation detection system for Chinese clinical notes and to investigate whether embedding features and word segmentations are worth exploiting towards this overall task. We propose a sequence labeling based system for speculation detection, which relies on features from bag of characters, bag of words, character embedding, and word embedding. We experiment on a novel dataset of 36,828 clinical notes with 5,103 gold-standard speculation annotations on 2,000 notes, and compare the systems in which word embeddings are calculated based on word segmentations given by general and by domain specific segmenters respectively. Our systems are able to reach performance as high as 92.2% measured by F score. We demonstrate that word segmentation is critical to produce high quality word embedding to facilitate downstream information extraction applications, and suggest that a domain dependent word segmenter can be vital to such a clinical NLP task in Chinese language.

show abstract

Medical Knowledge Attention Enhanced Neural Model for Named Entity Recognition in Chinese EMR

Zhang

Zhou

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Joint segmentation and named entity recognition using dual decomposition in Chinese discharge summaries

Abstract: The joint model is efficient and effective in both segmentation and recognition compared with the two individual tasks. The model achieved encouraging results, demonstrating the feasibility of the two tasks.

Cited by 62 publications

References 19 publications

Bilingual term alignment from comparable corpora in English discharge summary and Chinese discharge summary

Bilingual term alignment from comparable corpora in English discharge summary and Chinese discharge summary

Speculation detection for Chinese clinical notes: Impacts of word segmentation and embedding models

Medical Knowledge Attention Enhanced Neural Model for Named Entity Recognition in Chinese EMR

Contact Info

Product

Resources

About